Token | More |
Token ID | 3125 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
KEN | +0.083 |
annis | +0.078 |
biased | +0.078 |
comment | +0.077 |
rank | +0.077 |
Neg logit contributions | |
estial | -0.088 |
ergic | -0.088 |
alog | -0.083 |
ysis | -0.081 |
anchester | -0.081 |
Token | Advanced |
Token ID | 13435 |
Feature activation | +7.46e-02 |
Pos logit contributions | |
KEN | +0.372 |
annis | +0.350 |
biased | +0.349 |
comment | +0.347 |
rank | +0.346 |
Neg logit contributions | |
estial | -0.355 |
ergic | -0.353 |
alog | -0.333 |
ysis | -0.323 |
anchester | -0.323 |
Token | Ruby |
Token ID | 10888 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
KEN | +0.183 |
annis | +0.173 |
biased | +0.173 |
comment | +0.171 |
rank | +0.171 |
Neg logit contributions | |
estial | -0.155 |
ergic | -0.155 |
alog | -0.145 |
ysis | -0.141 |
anchester | -0.141 |
Token | Method |
Token ID | 11789 |
Feature activation | -9.28e-03 |
Pos logit contributions | |
estial | +0.062 |
ergic | +0.062 |
alog | +0.058 |
anchester | +0.056 |
ysis | +0.056 |
Neg logit contributions | |
KEN | -0.072 |
annis | -0.068 |
biased | -0.068 |
comment | -0.067 |
rank | -0.067 |
Token | Arg |
Token ID | 20559 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
estial | +0.020 |
ergic | +0.020 |
alog | +0.019 |
anchester | +0.018 |
ysis | +0.018 |
Neg logit contributions | |
KEN | -0.022 |
annis | -0.021 |
biased | -0.021 |
comment | -0.021 |
rank | -0.021 |
Token | uments |
Token ID | 2886 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
KEN | +0.419 |
annis | +0.397 |
biased | +0.396 |
comment | +0.396 |
rank | +0.395 |
Neg logit contributions | |
estial | -0.291 |
ergic | -0.288 |
alog | -0.267 |
ysis | -0.260 |
anchester | -0.259 |
Token | – |
Token ID | 784 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
KEN | +1.194 |
annis | +1.101 |
biased | +1.099 |
comment | +1.094 |
rank | +1.092 |
Neg logit contributions | |
estial | -1.713 |
ergic | -1.696 |
alog | -1.610 |
ysis | -1.574 |
anchester | -1.572 |
Token | H |
Token ID | 367 |
Feature activation | -7.66e-02 |
Pos logit contributions | |
KEN | +0.155 |
annis | +0.146 |
biased | +0.145 |
comment | +0.144 |
rank | +0.144 |
Neg logit contributions | |
estial | -0.147 |
ergic | -0.146 |
alog | -0.138 |
anchester | -0.134 |
ysis | -0.134 |
Token | ashes |
Token ID | 7465 |
Feature activation | +7.18e-02 |
Pos logit contributions | |
estial | +0.196 |
ergic | +0.195 |
alog | +0.185 |
ysis | +0.181 |
anchester | +0.181 |
Neg logit contributions | |
KEN | -0.152 |
annis | -0.141 |
biased | -0.141 |
comment | -0.140 |
rank | -0.139 |
Token | And |
Token ID | 843 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
KEN | +0.137 |
annis | +0.127 |
biased | +0.126 |
comment | +0.125 |
rank | +0.125 |
Neg logit contributions | |
estial | -0.189 |
ergic | -0.189 |
alog | -0.179 |
anchester | -0.175 |
ysis | -0.175 |
Token | Block |
Token ID | 9726 |
Feature activation | -6.07e-02 |
Pos logit contributions | |
KEN | +0.256 |
annis | +0.240 |
biased | +0.240 |
comment | +0.239 |
rank | +0.238 |
Neg logit contributions | |
estial | -0.223 |
ergic | -0.221 |
alog | -0.207 |
anchester | -0.202 |
ysis | -0.202 |
Token | icide |
Token ID | 5285 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
estial | +0.296 |
ergic | +0.293 |
alog | +0.274 |
anchester | +0.269 |
ysis | +0.268 |
Neg logit contributions | |
KEN | -0.325 |
biased | -0.307 |
annis | -0.307 |
comment | -0.307 |
rank | -0.306 |
Token | pre |
Token ID | 3866 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
estial | +0.482 |
ergic | +0.480 |
alog | +0.457 |
ysis | +0.446 |
anchester | +0.446 |
Neg logit contributions | |
KEN | -0.353 |
annis | -0.327 |
biased | -0.325 |
comment | -0.322 |
rank | -0.320 |
Token | vention |
Token ID | 4018 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
estial | +0.281 |
ergic | +0.279 |
alog | +0.263 |
anchester | +0.257 |
ysis | +0.256 |
Neg logit contributions | |
KEN | -0.271 |
annis | -0.254 |
biased | -0.254 |
comment | -0.253 |
rank | -0.252 |
Token | / |
Token ID | 14 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
estial | +0.082 |
ergic | +0.082 |
alog | +0.078 |
anchester | +0.076 |
ysis | +0.076 |
Neg logit contributions | |
KEN | -0.063 |
annis | -0.058 |
biased | -0.058 |
comment | -0.058 |
rank | -0.057 |
Token | doc |
Token ID | 15390 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
estial | +0.263 |
ergic | +0.262 |
alog | +0.249 |
ysis | +0.244 |
anchester | +0.243 |
Neg logit contributions | |
KEN | -0.194 |
annis | -0.180 |
biased | -0.180 |
comment | -0.178 |
rank | -0.177 |
Token | uments |
Token ID | 2886 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
KEN | +0.046 |
annis | +0.043 |
biased | +0.043 |
comment | +0.043 |
rank | +0.043 |
Neg logit contributions | |
estial | -0.033 |
ergic | -0.033 |
alog | -0.030 |
anchester | -0.030 |
ysis | -0.030 |
Token | / |
Token ID | 14 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
KEN | +1.382 |
comment | +1.296 |
biased | +1.294 |
annis | +1.293 |
rank | +1.289 |
Neg logit contributions | |
estial | -1.512 |
ergic | -1.497 |
alog | -1.406 |
anchester | -1.379 |
ysis | -1.372 |
Token | older |
Token ID | 19892 |
Feature activation | -3.40e-03 |
Pos logit contributions | |
estial | +0.066 |
ergic | +0.066 |
alog | +0.062 |
ysis | +0.061 |
anchester | +0.061 |
Neg logit contributions | |
KEN | -0.048 |
annis | -0.045 |
biased | -0.045 |
comment | -0.044 |
rank | -0.044 |
Token | adult |
Token ID | 49922 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
estial | +0.009 |
ergic | +0.009 |
alog | +0.009 |
anchester | +0.009 |
ysis | +0.009 |
Neg logit contributions | |
KEN | -0.006 |
annis | -0.006 |
biased | -0.006 |
comment | -0.006 |
rank | -0.006 |
Token | / |
Token ID | 14 |
Feature activation | -6.12e-02 |
Pos logit contributions | |
KEN | +0.035 |
biased | +0.033 |
annis | +0.033 |
comment | +0.032 |
rank | +0.032 |
Neg logit contributions | |
estial | -0.041 |
ergic | -0.041 |
alog | -0.039 |
anchester | -0.038 |
ysis | -0.038 |
Token | plan |
Token ID | 11578 |
Feature activation | -6.68e-02 |
Pos logit contributions | |
estial | +0.154 |
ergic | +0.153 |
alog | +0.145 |
ysis | +0.141 |
anchester | +0.141 |
Neg logit contributions | |
KEN | -0.124 |
annis | -0.116 |
biased | -0.115 |
comment | -0.115 |
rank | -0.114 |
Token | box |
Token ID | 3524 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
KEN | +0.302 |
biased | +0.285 |
comment | +0.284 |
rank | +0.284 |
annis | +0.284 |
Neg logit contributions | |
estial | -0.326 |
ergic | -0.326 |
alog | -0.307 |
anchester | -0.303 |
issance | -0.297 |
Token | of |
Token ID | 286 |
Feature activation | +7.24e-03 |
Pos logit contributions | |
KEN | +0.034 |
annis | +0.031 |
biased | +0.031 |
comment | +0.031 |
rank | +0.031 |
Neg logit contributions | |
estial | -0.050 |
ergic | -0.050 |
alog | -0.048 |
anchester | -0.047 |
ysis | -0.047 |
Token | our |
Token ID | 674 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
KEN | +0.016 |
biased | +0.015 |
annis | +0.015 |
comment | +0.015 |
rank | +0.015 |
Neg logit contributions | |
estial | -0.017 |
ergic | -0.017 |
alog | -0.016 |
ysis | -0.016 |
anchester | -0.016 |
Token | old |
Token ID | 1468 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
estial | +0.098 |
ergic | +0.097 |
alog | +0.092 |
anchester | +0.090 |
ysis | +0.090 |
Neg logit contributions | |
KEN | -0.091 |
annis | -0.085 |
biased | -0.084 |
comment | -0.084 |
rank | -0.084 |
Token | Pont |
Token ID | 26345 |
Feature activation | -3.70e-02 |
Pos logit contributions | |
estial | +0.292 |
ergic | +0.291 |
alog | +0.274 |
ysis | +0.267 |
anchester | +0.267 |
Neg logit contributions | |
KEN | -0.283 |
annis | -0.265 |
biased | -0.265 |
comment | -0.263 |
rank | -0.262 |
Token | iac |
Token ID | 9607 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
estial | +0.063 |
ergic | +0.063 |
alog | +0.057 |
anchester | +0.056 |
ysis | +0.056 |
Neg logit contributions | |
KEN | -0.104 |
annis | -0.100 |
biased | -0.099 |
rank | -0.099 |
comment | -0.099 |
Token | Bon |
Token ID | 7979 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
KEN | +1.496 |
annis | +1.411 |
biased | +1.404 |
comment | +1.392 |
queue | +1.388 |
Neg logit contributions | |
estial | -1.331 |
ergic | -1.314 |
alog | -1.232 |
ysis | -1.202 |
anchester | -1.201 |
Token | ne |
Token ID | 710 |
Feature activation | -8.38e-03 |
Pos logit contributions | |
KEN | +0.034 |
annis | +0.032 |
biased | +0.032 |
comment | +0.031 |
rank | +0.031 |
Neg logit contributions | |
estial | -0.051 |
ergic | -0.051 |
alog | -0.048 |
ysis | -0.047 |
anchester | -0.047 |
Token | ville |
Token ID | 4244 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
estial | +0.018 |
ergic | +0.018 |
alog | +0.016 |
anchester | +0.016 |
ysis | +0.016 |
Neg logit contributions | |
KEN | -0.020 |
annis | -0.019 |
biased | -0.019 |
comment | -0.019 |
queue | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
estial | +0.039 |
ergic | +0.039 |
alog | +0.037 |
anchester | +0.036 |
ysis | +0.036 |
Neg logit contributions | |
KEN | -0.036 |
annis | -0.034 |
biased | -0.034 |
comment | -0.033 |
rank | -0.033 |
Token | Sally |
Token ID | 25737 |
Feature activation | +7.14e-02 |
Pos logit contributions | |
KEN | +0.129 |
annis | +0.121 |
biased | +0.121 |
comment | +0.120 |
rank | +0.120 |
Neg logit contributions | |
estial | -0.118 |
ergic | -0.118 |
alog | -0.111 |
ysis | -0.107 |
anchester | -0.107 |
Token | Sweden |
Token ID | 10710 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
KEN | +0.002 |
biased | +0.002 |
annis | +0.002 |
comment | +0.002 |
rank | +0.002 |
Neg logit contributions | |
estial | -0.002 |
ergic | -0.002 |
alog | -0.002 |
anchester | -0.002 |
ysis | -0.002 |
Token | is |
Token ID | 318 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
KEN | +0.050 |
annis | +0.047 |
biased | +0.046 |
comment | +0.046 |
rank | +0.046 |
Neg logit contributions | |
estial | -0.064 |
ergic | -0.064 |
alog | -0.061 |
anchester | -0.059 |
ysis | -0.059 |
Token | not |
Token ID | 407 |
Feature activation | +8.87e-02 |
Pos logit contributions | |
KEN | +0.038 |
annis | +0.035 |
biased | +0.035 |
comment | +0.035 |
rank | +0.034 |
Neg logit contributions | |
estial | -0.050 |
ergic | -0.050 |
alog | -0.047 |
anchester | -0.046 |
ysis | -0.046 |
Token | a |
Token ID | 257 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
KEN | +0.174 |
annis | +0.162 |
biased | +0.162 |
comment | +0.161 |
rank | +0.160 |
Neg logit contributions | |
estial | -0.229 |
ergic | -0.228 |
alog | -0.216 |
anchester | -0.211 |
ysis | -0.211 |
Token | fanc |
Token ID | 39980 |
Feature activation | -9.40e-02 |
Pos logit contributions | |
KEN | +0.070 |
annis | +0.065 |
biased | +0.065 |
comment | +0.064 |
rank | +0.064 |
Neg logit contributions | |
estial | -0.088 |
ergic | -0.087 |
alog | -0.083 |
ysis | -0.081 |
anchester | -0.081 |
Token | iful |
Token ID | 4135 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
estial | +0.201 |
ergic | +0.201 |
alog | +0.188 |
ysis | +0.184 |
anchester | +0.183 |
Neg logit contributions | |
KEN | -0.224 |
biased | -0.212 |
comment | -0.211 |
annis | -0.211 |
rank | -0.210 |
Token | notion |
Token ID | 9495 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
KEN | +1.193 |
annis | +1.106 |
biased | +1.100 |
comment | +1.100 |
rank | +1.087 |
Neg logit contributions | |
estial | -1.616 |
ergic | -1.612 |
alog | -1.523 |
anchester | -1.495 |
ysis | -1.494 |
Token | . |
Token ID | 13 |
Feature activation | -7.00e-03 |
Pos logit contributions | |
KEN | +0.221 |
annis | +0.204 |
biased | +0.204 |
comment | +0.202 |
rank | +0.200 |
Neg logit contributions | |
estial | -0.346 |
ergic | -0.345 |
alog | -0.328 |
ysis | -0.321 |
anchester | -0.321 |
Token | There |
Token ID | 1318 |
Feature activation | -3.10e-03 |
Pos logit contributions | |
estial | +0.015 |
ergic | +0.015 |
alog | +0.015 |
ysis | +0.014 |
anchester | +0.014 |
Neg logit contributions | |
KEN | -0.016 |
annis | -0.015 |
biased | -0.015 |
comment | -0.015 |
rank | -0.015 |
Token | is |
Token ID | 318 |
Feature activation | +4.10e-02 |
Pos logit contributions | |
estial | +0.008 |
ergic | +0.008 |
alog | +0.008 |
ysis | +0.008 |
anchester | +0.008 |
Neg logit contributions | |
KEN | -0.006 |
annis | -0.005 |
biased | -0.005 |
comment | -0.005 |
rank | -0.005 |
Token | talk |
Token ID | 1561 |
Feature activation | +1.10e-03 |
Pos logit contributions | |
KEN | +0.087 |
annis | +0.081 |
biased | +0.081 |
comment | +0.081 |
rank | +0.080 |
Neg logit contributions | |
estial | -0.099 |
ergic | -0.099 |
alog | -0.093 |
ysis | -0.091 |
anchester | -0.091 |
Token | control |
Token ID | 1630 |
Feature activation | +1.10e-04 |
Pos logit contributions | |
KEN | +0.057 |
annis | +0.053 |
biased | +0.053 |
comment | +0.052 |
rank | +0.052 |
Neg logit contributions | |
estial | -0.080 |
ergic | -0.080 |
alog | -0.076 |
anchester | -0.074 |
ysis | -0.074 |
Token | , |
Token ID | 11 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
KEN | +0.000 |
annis | +0.000 |
biased | +0.000 |
comment | +0.000 |
rank | +0.000 |
Neg logit contributions | |
estial | -0.000 |
ergic | -0.000 |
alog | -0.000 |
anchester | -0.000 |
ysis | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
estial | +0.053 |
ergic | +0.052 |
alog | +0.049 |
anchester | +0.048 |
ysis | +0.048 |
Neg logit contributions | |
KEN | -0.052 |
annis | -0.049 |
biased | -0.049 |
comment | -0.048 |
rank | -0.048 |
Token | currency |
Token ID | 7395 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
estial | +0.053 |
ergic | +0.053 |
alog | +0.050 |
anchester | +0.049 |
ysis | +0.049 |
Neg logit contributions | |
KEN | -0.049 |
annis | -0.046 |
biased | -0.046 |
comment | -0.046 |
rank | -0.046 |
Token | reb |
Token ID | 3405 |
Feature activation | +2.54e-03 |
Pos logit contributions | |
KEN | +0.024 |
annis | +0.023 |
biased | +0.023 |
comment | +0.023 |
rank | +0.022 |
Neg logit contributions | |
estial | -0.031 |
ergic | -0.031 |
alog | -0.030 |
anchester | -0.029 |
ysis | -0.029 |
Token | ounded |
Token ID | 6302 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
KEN | +0.005 |
biased | +0.004 |
annis | +0.004 |
rank | +0.004 |
comment | +0.004 |
Neg logit contributions | |
estial | -0.007 |
ergic | -0.007 |
alog | -0.006 |
ysis | -0.006 |
anchester | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +6.11e-02 |
Pos logit contributions | |
KEN | +1.072 |
annis | +0.986 |
biased | +0.984 |
comment | +0.976 |
rank | +0.971 |
Neg logit contributions | |
estial | -1.697 |
ergic | -1.690 |
alog | -1.611 |
anchester | -1.576 |
ysis | -1.576 |
Token | near |
Token ID | 1474 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
KEN | +0.131 |
annis | +0.122 |
biased | +0.122 |
comment | +0.121 |
rank | +0.121 |
Neg logit contributions | |
estial | -0.147 |
ergic | -0.146 |
alog | -0.138 |
ysis | -0.135 |
anchester | -0.135 |
Token | its |
Token ID | 663 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
KEN | +0.027 |
annis | +0.025 |
biased | +0.025 |
comment | +0.024 |
rank | +0.024 |
Neg logit contributions | |
estial | -0.039 |
ergic | -0.039 |
alog | -0.037 |
ysis | -0.036 |
anchester | -0.036 |
Token | previous |
Token ID | 2180 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
KEN | +0.227 |
annis | +0.211 |
biased | +0.211 |
comment | +0.210 |
rank | +0.209 |
Neg logit contributions | |
estial | -0.282 |
ergic | -0.280 |
alog | -0.264 |
ysis | -0.259 |
anchester | -0.259 |
Token | highs |
Token ID | 28227 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
estial | +0.048 |
ergic | +0.048 |
alog | +0.046 |
ysis | +0.045 |
anchester | +0.045 |
Neg logit contributions | |
KEN | -0.034 |
annis | -0.031 |
biased | -0.031 |
comment | -0.031 |
rank | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +8.42e-03 |
Pos logit contributions | |
estial | +0.059 |
ergic | +0.059 |
alog | +0.056 |
ysis | +0.055 |
anchester | +0.055 |
Neg logit contributions | |
KEN | -0.040 |
annis | -0.037 |
biased | -0.036 |
comment | -0.036 |
rank | -0.036 |
Token | three |
Token ID | 1115 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
KEN | +0.017 |
annis | +0.015 |
biased | +0.015 |
comment | +0.015 |
rank | +0.015 |
Neg logit contributions | |
estial | -0.022 |
ergic | -0.022 |
alog | -0.020 |
ysis | -0.020 |
anchester | -0.020 |
Token | counts |
Token ID | 9853 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
KEN | +0.104 |
annis | +0.098 |
biased | +0.098 |
comment | +0.097 |
rank | +0.097 |
Neg logit contributions | |
estial | -0.101 |
ergic | -0.100 |
alog | -0.094 |
ysis | -0.091 |
anchester | -0.091 |
Token | of |
Token ID | 286 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
estial | +0.325 |
ergic | +0.323 |
alog | +0.307 |
anchester | +0.299 |
ysis | +0.299 |
Neg logit contributions | |
KEN | -0.219 |
annis | -0.202 |
biased | -0.201 |
comment | -0.200 |
rank | -0.199 |
Token | tresp |
Token ID | 29723 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
KEN | +0.031 |
annis | +0.029 |
biased | +0.029 |
comment | +0.029 |
rank | +0.029 |
Neg logit contributions | |
estial | -0.040 |
ergic | -0.040 |
alog | -0.038 |
ysis | -0.037 |
anchester | -0.037 |
Token | assing |
Token ID | 19696 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
ergic | +0.271 |
estial | +0.270 |
alog | +0.258 |
ysis | +0.252 |
anchester | +0.250 |
Neg logit contributions | |
KEN | -0.218 |
annis | -0.198 |
200000 | -0.197 |
biased | -0.197 |
rank | -0.195 |
Token | and |
Token ID | 290 |
Feature activation | +6.11e-02 |
Pos logit contributions | |
KEN | +0.967 |
annis | +0.883 |
biased | +0.878 |
comment | +0.871 |
rank | +0.867 |
Neg logit contributions | |
estial | -1.713 |
ergic | -1.706 |
alog | -1.628 |
anchester | -1.592 |
ysis | -1.591 |
Token | damage |
Token ID | 2465 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
KEN | +0.118 |
biased | +0.109 |
annis | +0.109 |
comment | +0.108 |
rank | +0.108 |
Neg logit contributions | |
estial | -0.159 |
ergic | -0.159 |
alog | -0.151 |
ysis | -0.148 |
anchester | -0.148 |
Token | to |
Token ID | 284 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
KEN | +0.357 |
biased | +0.325 |
annis | +0.325 |
comment | +0.323 |
rank | +0.320 |
Neg logit contributions | |
estial | -0.701 |
ergic | -0.696 |
alog | -0.667 |
anchester | -0.655 |
ysis | -0.654 |
Token | property |
Token ID | 3119 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
estial | +0.062 |
ergic | +0.062 |
alog | +0.058 |
anchester | +0.057 |
ysis | +0.057 |
Neg logit contributions | |
KEN | -0.057 |
annis | -0.053 |
biased | -0.053 |
comment | -0.052 |
rank | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
estial | +0.055 |
ergic | +0.055 |
alog | +0.052 |
ysis | +0.051 |
anchester | +0.051 |
Neg logit contributions | |
KEN | -0.038 |
annis | -0.035 |
biased | -0.035 |
comment | -0.035 |
rank | -0.034 |
Token | oto |
Token ID | 2069 |
Feature activation | -8.75e-02 |
Pos logit contributions | |
KEN | +0.074 |
annis | +0.069 |
biased | +0.069 |
comment | +0.069 |
rank | +0.069 |
Neg logit contributions | |
estial | -0.080 |
ergic | -0.080 |
alog | -0.075 |
anchester | -0.074 |
ysis | -0.074 |
Token | , |
Token ID | 11 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
estial | +0.241 |
ergic | +0.240 |
alog | +0.228 |
anchester | +0.223 |
ysis | +0.223 |
Neg logit contributions | |
KEN | -0.157 |
annis | -0.144 |
biased | -0.144 |
comment | -0.143 |
rank | -0.142 |
Token | a |
Token ID | 257 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
KEN | +0.024 |
biased | +0.022 |
annis | +0.022 |
comment | +0.022 |
rank | +0.022 |
Neg logit contributions | |
estial | -0.025 |
ergic | -0.025 |
alog | -0.024 |
ysis | -0.023 |
anchester | -0.023 |
Token | y |
Token ID | 331 |
Feature activation | -9.66e-02 |
Pos logit contributions | |
KEN | +0.035 |
annis | +0.033 |
biased | +0.033 |
comment | +0.033 |
rank | +0.033 |
Neg logit contributions | |
estial | -0.034 |
ergic | -0.034 |
alog | -0.032 |
ysis | -0.031 |
anchester | -0.031 |
Token | aku |
Token ID | 8719 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
ergic | +0.223 |
estial | +0.222 |
alog | +0.211 |
ysis | +0.201 |
anchester | +0.201 |
Neg logit contributions | |
KEN | -0.217 |
biased | -0.205 |
comment | -0.201 |
annis | -0.200 |
200000 | -0.199 |
Token | za |
Token ID | 4496 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
ergic | +0.383 |
estial | +0.379 |
alog | +0.366 |
ysis | +0.354 |
anchester | +0.354 |
Neg logit contributions | |
KEN | -0.211 |
biased | -0.193 |
annis | -0.189 |
rank | -0.187 |
200000 | -0.187 |
Token | boss |
Token ID | 6478 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
KEN | +1.163 |
annis | +1.078 |
biased | +1.073 |
comment | +1.068 |
rank | +1.067 |
Neg logit contributions | |
estial | -1.509 |
ergic | -1.496 |
alog | -1.418 |
anchester | -1.390 |
ysis | -1.389 |
Token | who |
Token ID | 508 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
KEN | +0.044 |
annis | +0.041 |
biased | +0.040 |
comment | +0.040 |
rank | +0.040 |
Neg logit contributions | |
estial | -0.056 |
ergic | -0.056 |
alog | -0.053 |
ysis | -0.052 |
anchester | -0.052 |
Token | was |
Token ID | 373 |
Feature activation | +6.92e-02 |
Pos logit contributions | |
KEN | +0.080 |
annis | +0.075 |
biased | +0.074 |
comment | +0.074 |
rank | +0.074 |
Neg logit contributions | |
estial | -0.092 |
ergic | -0.092 |
alog | -0.087 |
ysis | -0.085 |
anchester | -0.084 |
Token | ordered |
Token ID | 6149 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
KEN | +0.140 |
annis | +0.131 |
biased | +0.131 |
comment | +0.130 |
rank | +0.129 |
Neg logit contributions | |
estial | -0.174 |
ergic | -0.173 |
alog | -0.164 |
ysis | -0.160 |
anchester | -0.160 |
Token | to |
Token ID | 284 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
KEN | +0.039 |
annis | +0.035 |
biased | +0.035 |
comment | +0.035 |
rank | +0.035 |
Neg logit contributions | |
estial | -0.068 |
ergic | -0.067 |
alog | -0.064 |
anchester | -0.063 |
ysis | -0.063 |
Token | history |
Token ID | 2106 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
KEN | +0.178 |
annis | +0.166 |
biased | +0.166 |
comment | +0.165 |
rank | +0.164 |
Neg logit contributions | |
estial | -0.195 |
ergic | -0.194 |
alog | -0.184 |
anchester | -0.179 |
ysis | -0.179 |
Token | is |
Token ID | 318 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
KEN | +0.275 |
annis | +0.255 |
biased | +0.255 |
comment | +0.254 |
rank | +0.252 |
Neg logit contributions | |
estial | -0.370 |
ergic | -0.368 |
alog | -0.349 |
anchester | -0.342 |
ysis | -0.342 |
Token | made |
Token ID | 925 |
Feature activation | +5.45e-02 |
Pos logit contributions | |
KEN | +0.030 |
annis | +0.028 |
biased | +0.028 |
comment | +0.028 |
rank | +0.028 |
Neg logit contributions | |
estial | -0.036 |
ergic | -0.035 |
alog | -0.034 |
anchester | -0.033 |
ysis | -0.033 |
Token | to |
Token ID | 284 |
Feature activation | -5.68e-03 |
Pos logit contributions | |
KEN | +0.100 |
annis | +0.092 |
biased | +0.092 |
comment | +0.091 |
rank | +0.091 |
Neg logit contributions | |
estial | -0.148 |
ergic | -0.148 |
alog | -0.141 |
anchester | -0.137 |
ysis | -0.137 |
Token | rev |
Token ID | 2710 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
estial | +0.015 |
ergic | +0.015 |
alog | +0.014 |
ysis | +0.014 |
anchester | +0.014 |
Neg logit contributions | |
KEN | -0.011 |
annis | -0.010 |
biased | -0.010 |
comment | -0.010 |
rank | -0.010 |
Token | olve |
Token ID | 6442 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
estial | +0.052 |
ergic | +0.052 |
alog | +0.050 |
ysis | +0.049 |
anchester | +0.049 |
Neg logit contributions | |
KEN | -0.021 |
annis | -0.018 |
biased | -0.018 |
comment | -0.018 |
rank | -0.018 |
Token | in |
Token ID | 287 |
Feature activation | +5.34e-02 |
Pos logit contributions | |
KEN | +1.032 |
biased | +0.949 |
comment | +0.947 |
annis | +0.946 |
rank | +0.934 |
Neg logit contributions | |
estial | -1.623 |
ergic | -1.617 |
alog | -1.537 |
ysis | -1.507 |
anchester | -1.503 |
Token | a |
Token ID | 257 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
KEN | +0.115 |
annis | +0.107 |
biased | +0.107 |
comment | +0.106 |
rank | +0.106 |
Neg logit contributions | |
estial | -0.128 |
ergic | -0.127 |
alog | -0.120 |
ysis | -0.117 |
anchester | -0.117 |
Token | P |
Token ID | 350 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
KEN | +0.119 |
annis | +0.112 |
biased | +0.110 |
comment | +0.109 |
rank | +0.109 |
Neg logit contributions | |
estial | -0.156 |
ergic | -0.155 |
alog | -0.148 |
ysis | -0.144 |
anchester | -0.144 |
Token | to |
Token ID | 1462 |
Feature activation | -7.62e-03 |
Pos logit contributions | |
KEN | +0.366 |
annis | +0.341 |
biased | +0.341 |
comment | +0.339 |
rank | +0.337 |
Neg logit contributions | |
estial | -0.422 |
ergic | -0.420 |
alog | -0.397 |
ysis | -0.387 |
anchester | -0.387 |
Token | le |
Token ID | 293 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
estial | +0.019 |
ergic | +0.019 |
alog | +0.018 |
ysis | +0.018 |
anchester | +0.018 |
Neg logit contributions | |
KEN | -0.015 |
annis | -0.014 |
biased | -0.014 |
comment | -0.014 |
rank | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
KEN | +0.012 |
annis | +0.011 |
biased | +0.011 |
comment | +0.011 |
rank | +0.011 |
Neg logit contributions | |
estial | -0.020 |
ergic | -0.020 |
alog | -0.019 |
ysis | -0.019 |
anchester | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
KEN | +0.369 |
comment | +0.344 |
annis | +0.344 |
biased | +0.343 |
rank | +0.341 |
Neg logit contributions | |
estial | -0.409 |
ergic | -0.407 |
alog | -0.385 |
ysis | -0.376 |
anchester | -0.375 |
Token |
|
Token ID | 198 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
KEN | +0.029 |
annis | +0.028 |
biased | +0.027 |
suspic | +0.027 |
queue | +0.027 |
Neg logit contributions | |
ergic | -0.026 |
estial | -0.025 |
alog | -0.024 |
ysis | -0.023 |
opsis | -0.023 |
Token | ( |
Token ID | 7 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
KEN | +0.047 |
annis | +0.043 |
biased | +0.043 |
comment | +0.043 |
rank | +0.042 |
Neg logit contributions | |
estial | -0.076 |
ergic | -0.076 |
alog | -0.072 |
anchester | -0.071 |
ysis | -0.071 |
Token | Vis |
Token ID | 15854 |
Feature activation | +6.88e-03 |
Pos logit contributions | |
estial | +0.043 |
ergic | +0.043 |
alog | +0.041 |
anchester | +0.040 |
ysis | +0.040 |
Neg logit contributions | |
KEN | -0.027 |
annis | -0.025 |
biased | -0.025 |
comment | -0.025 |
rank | -0.025 |
Token | ited |
Token ID | 863 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
KEN | +0.015 |
biased | +0.014 |
comment | +0.014 |
annis | +0.014 |
rank | +0.014 |
Neg logit contributions | |
estial | -0.016 |
ergic | -0.016 |
alog | -0.015 |
ysis | -0.015 |
anchester | -0.015 |
Token | 5 |
Token ID | 642 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
KEN | +1.320 |
biased | +1.233 |
annis | +1.232 |
comment | +1.231 |
rank | +1.226 |
Neg logit contributions | |
estial | -1.332 |
ergic | -1.323 |
alog | -1.244 |
anchester | -1.215 |
ysis | -1.211 |
Token | , |
Token ID | 11 |
Feature activation | +9.45e-02 |
Pos logit contributions | |
estial | +0.031 |
ergic | +0.031 |
alog | +0.030 |
ysis | +0.029 |
anchester | +0.029 |
Neg logit contributions | |
KEN | -0.021 |
annis | -0.020 |
biased | -0.019 |
comment | -0.019 |
rank | -0.019 |
Token | 855 |
Token ID | 45432 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
KEN | +0.178 |
comment | +0.165 |
biased | +0.164 |
annis | +0.164 |
rank | +0.163 |
Neg logit contributions | |
estial | -0.251 |
ergic | -0.250 |
alog | -0.238 |
anchester | -0.233 |
ysis | -0.232 |
Token | times |
Token ID | 1661 |
Feature activation | +5.62e-02 |
Pos logit contributions | |
KEN | +0.132 |
biased | +0.124 |
annis | +0.124 |
comment | +0.124 |
rank | +0.124 |
Neg logit contributions | |
estial | -0.086 |
ergic | -0.085 |
alog | -0.079 |
anchester | -0.077 |
ysis | -0.077 |
Token | , |
Token ID | 11 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
KEN | +0.101 |
biased | +0.093 |
annis | +0.093 |
comment | +0.091 |
rank | +0.091 |
Neg logit contributions | |
ergic | -0.155 |
estial | -0.155 |
alog | -0.147 |
ysis | -0.143 |
anchester | -0.143 |
Token | It |
Token ID | 632 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
KEN | +0.060 |
annis | +0.056 |
biased | +0.056 |
comment | +0.056 |
rank | +0.056 |
Neg logit contributions | |
estial | -0.055 |
ergic | -0.055 |
alog | -0.051 |
ysis | -0.050 |
anchester | -0.050 |
Token | � |
Token ID | 447 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
KEN | +0.052 |
annis | +0.048 |
biased | +0.048 |
comment | +0.048 |
rank | +0.047 |
Neg logit contributions | |
estial | -0.066 |
ergic | -0.066 |
alog | -0.063 |
ysis | -0.061 |
anchester | -0.061 |
Token | � |
Token ID | 247 |
Feature activation | +5.11e-02 |
Pos logit contributions | |
KEN | +0.037 |
biased | +0.035 |
annis | +0.035 |
comment | +0.035 |
rank | +0.035 |
Neg logit contributions | |
estial | -0.019 |
ergic | -0.019 |
alog | -0.018 |
ysis | -0.017 |
anchester | -0.017 |
Token | s |
Token ID | 82 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
KEN | +0.112 |
annis | +0.105 |
biased | +0.105 |
comment | +0.104 |
rank | +0.104 |
Neg logit contributions | |
estial | -0.120 |
ergic | -0.119 |
alog | -0.113 |
anchester | -0.110 |
ysis | -0.109 |
Token | tresp |
Token ID | 29723 |
Feature activation | -5.13e-02 |
Pos logit contributions | |
KEN | +0.091 |
annis | +0.084 |
biased | +0.084 |
rank | +0.083 |
comment | +0.083 |
Neg logit contributions | |
ergic | -0.126 |
estial | -0.126 |
alog | -0.120 |
anchester | -0.117 |
ysis | -0.117 |
Token | assing |
Token ID | 19696 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
ergic | +0.133 |
estial | +0.133 |
alog | +0.127 |
anchester | +0.124 |
ysis | +0.123 |
Neg logit contributions | |
KEN | -0.100 |
annis | -0.092 |
biased | -0.091 |
comment | -0.091 |
rank | -0.091 |
Token | and |
Token ID | 290 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
KEN | +1.061 |
annis | +0.978 |
biased | +0.975 |
comment | +0.968 |
rank | +0.964 |
Neg logit contributions | |
estial | -1.587 |
ergic | -1.582 |
alog | -1.506 |
anchester | -1.473 |
ysis | -1.472 |
Token | theft |
Token ID | 12402 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
KEN | +0.083 |
annis | +0.077 |
biased | +0.077 |
rank | +0.076 |
comment | +0.076 |
Neg logit contributions | |
estial | -0.110 |
ergic | -0.110 |
alog | -0.104 |
anchester | -0.102 |
ysis | -0.101 |
Token | . |
Token ID | 13 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
KEN | +0.462 |
annis | +0.426 |
biased | +0.424 |
comment | +0.422 |
rank | +0.420 |
Neg logit contributions | |
estial | -0.674 |
ergic | -0.672 |
alog | -0.640 |
anchester | -0.625 |
ysis | -0.625 |
Token | And |
Token ID | 843 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
KEN | +0.107 |
annis | +0.101 |
biased | +0.101 |
comment | +0.100 |
rank | +0.100 |
Neg logit contributions | |
estial | -0.100 |
ergic | -0.099 |
alog | -0.093 |
ysis | -0.091 |
anchester | -0.091 |
Token | it |
Token ID | 340 |
Feature activation | +7.06e-02 |
Pos logit contributions | |
KEN | +0.120 |
annis | +0.112 |
biased | +0.111 |
comment | +0.110 |
rank | +0.110 |
Neg logit contributions | |
ergic | -0.146 |
estial | -0.146 |
alog | -0.139 |
anchester | -0.135 |
ysis | -0.135 |
Token | is |
Token ID | 318 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
estial | +0.031 |
ergic | +0.030 |
alog | +0.029 |
ysis | +0.028 |
anchester | +0.028 |
Neg logit contributions | |
KEN | -0.024 |
annis | -0.022 |
biased | -0.022 |
comment | -0.022 |
rank | -0.022 |
Token | stepping |
Token ID | 17413 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
KEN | +0.032 |
annis | +0.029 |
biased | +0.029 |
comment | +0.029 |
rank | +0.028 |
Neg logit contributions | |
estial | -0.051 |
ergic | -0.051 |
alog | -0.048 |
anchester | -0.047 |
ysis | -0.047 |
Token | in |
Token ID | 287 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
KEN | +0.334 |
annis | +0.311 |
biased | +0.310 |
comment | +0.308 |
rank | +0.307 |
Neg logit contributions | |
estial | -0.404 |
ergic | -0.402 |
alog | -0.381 |
ysis | -0.372 |
anchester | -0.372 |
Token | on |
Token ID | 319 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
KEN | +0.028 |
annis | +0.026 |
biased | +0.025 |
comment | +0.025 |
rank | +0.025 |
Neg logit contributions | |
estial | -0.048 |
ergic | -0.048 |
alog | -0.046 |
anchester | -0.045 |
ysis | -0.045 |
Token | mand |
Token ID | 6855 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
KEN | +0.074 |
biased | +0.069 |
annis | +0.069 |
comment | +0.069 |
rank | +0.069 |
Neg logit contributions | |
estial | -0.074 |
ergic | -0.074 |
alog | -0.069 |
anchester | -0.067 |
ysis | -0.067 |
Token | ating |
Token ID | 803 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
estial | +0.034 |
ergic | +0.033 |
alog | +0.031 |
ysis | +0.030 |
anchester | +0.030 |
Neg logit contributions | |
KEN | -0.054 |
annis | -0.052 |
biased | -0.051 |
comment | -0.051 |
rank | -0.051 |
Token | parental |
Token ID | 21694 |
Feature activation | +7.29e-02 |
Pos logit contributions | |
KEN | +1.150 |
biased | +1.072 |
annis | +1.068 |
comment | +1.064 |
rank | +1.060 |
Neg logit contributions | |
estial | -1.481 |
ergic | -1.473 |
alog | -1.387 |
anchester | -1.361 |
issance | -1.349 |
Token | leave |
Token ID | 2666 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
KEN | +0.129 |
biased | +0.119 |
annis | +0.118 |
comment | +0.118 |
rank | +0.117 |
Neg logit contributions | |
estial | -0.203 |
ergic | -0.202 |
alog | -0.192 |
anchester | -0.188 |
ysis | -0.188 |
Token | . |
Token ID | 13 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
KEN | +0.072 |
annis | +0.067 |
biased | +0.066 |
comment | +0.066 |
rank | +0.065 |
Neg logit contributions | |
estial | -0.106 |
ergic | -0.106 |
alog | -0.101 |
ysis | -0.099 |
anchester | -0.098 |
Token | OS |
Token ID | 7294 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
estial | +0.054 |
ergic | +0.053 |
alog | +0.050 |
ysis | +0.049 |
anchester | +0.049 |
Neg logit contributions | |
KEN | -0.057 |
annis | -0.054 |
biased | -0.053 |
comment | -0.053 |
rank | -0.053 |
Token | HA |
Token ID | 7801 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
KEN | +0.041 |
annis | +0.037 |
biased | +0.037 |
comment | +0.037 |
rank | +0.036 |
Neg logit contributions | |
estial | -0.088 |
ergic | -0.088 |
alog | -0.084 |
anchester | -0.083 |
ysis | -0.083 |
Token | physical |
Token ID | 3518 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
estial | +0.087 |
ergic | +0.087 |
alog | +0.083 |
ysis | +0.081 |
anchester | +0.081 |
Neg logit contributions | |
KEN | -0.072 |
annis | -0.067 |
biased | -0.067 |
comment | -0.067 |
rank | -0.066 |
Token | fitness |
Token ID | 13547 |
Feature activation | -6.73e-03 |
Pos logit contributions | |
KEN | +0.058 |
annis | +0.053 |
biased | +0.053 |
comment | +0.053 |
rank | +0.053 |
Neg logit contributions | |
estial | -0.074 |
ergic | -0.074 |
alog | -0.070 |
anchester | -0.069 |
ysis | -0.069 |
Token | test |
Token ID | 1332 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
estial | +0.018 |
ergic | +0.018 |
alog | +0.017 |
ysis | +0.017 |
anchester | +0.017 |
Neg logit contributions | |
KEN | -0.012 |
annis | -0.011 |
biased | -0.011 |
comment | -0.011 |
rank | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
estial | +0.101 |
ergic | +0.101 |
alog | +0.096 |
ysis | +0.094 |
anchester | +0.094 |
Neg logit contributions | |
KEN | -0.068 |
annis | -0.062 |
biased | -0.062 |
comment | -0.062 |
rank | -0.061 |
Token | mand |
Token ID | 6855 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
KEN | +0.036 |
annis | +0.033 |
biased | +0.033 |
comment | +0.033 |
rank | +0.033 |
Neg logit contributions | |
estial | -0.052 |
ergic | -0.052 |
alog | -0.049 |
ysis | -0.048 |
anchester | -0.048 |
Token | ating |
Token ID | 803 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
estial | +0.070 |
ergic | +0.069 |
alog | +0.065 |
ysis | +0.063 |
anchester | +0.063 |
Neg logit contributions | |
KEN | -0.076 |
annis | -0.072 |
biased | -0.072 |
comment | -0.072 |
rank | -0.072 |
Token | that |
Token ID | 326 |
Feature activation | -9.06e-03 |
Pos logit contributions | |
KEN | +1.201 |
annis | +1.117 |
biased | +1.113 |
comment | +1.106 |
rank | +1.102 |
Neg logit contributions | |
estial | -1.438 |
ergic | -1.428 |
alog | -1.353 |
anchester | -1.322 |
issance | -1.308 |
Token | the |
Token ID | 262 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
estial | +0.022 |
ergic | +0.022 |
alog | +0.021 |
anchester | +0.020 |
ysis | +0.020 |
Neg logit contributions | |
KEN | -0.019 |
annis | -0.018 |
biased | -0.018 |
comment | -0.017 |
rank | -0.017 |
Token | rest |
Token ID | 1334 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
KEN | +0.041 |
annis | +0.038 |
biased | +0.038 |
comment | +0.038 |
rank | +0.037 |
Neg logit contributions | |
estial | -0.046 |
ergic | -0.046 |
alog | -0.043 |
anchester | -0.042 |
ysis | -0.042 |
Token | of |
Token ID | 286 |
Feature activation | -3.89e-03 |
Pos logit contributions | |
estial | +0.062 |
ergic | +0.062 |
alog | +0.059 |
anchester | +0.058 |
issance | +0.057 |
Neg logit contributions | |
KEN | -0.041 |
rank | -0.037 |
biased | -0.037 |
comment | -0.037 |
annis | -0.037 |
Token | the |
Token ID | 262 |
Feature activation | -2.53e-04 |
Pos logit contributions | |
estial | +0.009 |
ergic | +0.009 |
alog | +0.008 |
anchester | +0.008 |
ysis | +0.008 |
Neg logit contributions | |
KEN | -0.009 |
comment | -0.008 |
annis | -0.008 |
biased | -0.008 |
rank | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | -6.52e-02 |
Pos logit contributions | |
KEN | +0.080 |
biased | +0.072 |
comment | +0.072 |
annis | +0.072 |
rank | +0.070 |
Neg logit contributions | |
estial | -0.174 |
ergic | -0.173 |
alog | -0.166 |
ysis | -0.162 |
anchester | -0.161 |
Token | dangerous |
Token ID | 4923 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
estial | +0.157 |
ergic | +0.157 |
alog | +0.148 |
anchester | +0.144 |
ysis | +0.144 |
Neg logit contributions | |
KEN | -0.139 |
annis | -0.130 |
biased | -0.129 |
comment | -0.129 |
rank | -0.128 |
Token | , |
Token ID | 11 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
KEN | +0.143 |
annis | +0.134 |
biased | +0.133 |
comment | +0.132 |
rank | +0.132 |
Neg logit contributions | |
estial | -0.171 |
ergic | -0.170 |
alog | -0.161 |
ysis | -0.157 |
anchester | -0.157 |
Token | illegal |
Token ID | 5293 |
Feature activation | +5.76e-02 |
Pos logit contributions | |
KEN | +0.048 |
annis | +0.044 |
biased | +0.044 |
comment | +0.043 |
rank | +0.043 |
Neg logit contributions | |
ergic | -0.070 |
estial | -0.070 |
alog | -0.066 |
anchester | -0.065 |
ysis | -0.065 |
Token | tresp |
Token ID | 29723 |
Feature activation | -8.66e-02 |
Pos logit contributions | |
KEN | +0.112 |
annis | +0.104 |
biased | +0.103 |
comment | +0.103 |
rank | +0.102 |
Neg logit contributions | |
estial | -0.150 |
ergic | -0.149 |
alog | -0.142 |
ysis | -0.138 |
anchester | -0.138 |
Token | assing |
Token ID | 19696 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
estial | +0.230 |
ergic | +0.229 |
alog | +0.218 |
anchester | +0.213 |
ysis | +0.213 |
Neg logit contributions | |
KEN | -0.164 |
annis | -0.151 |
biased | -0.151 |
comment | -0.150 |
rank | -0.149 |
Token | . |
Token ID | 13 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
KEN | +1.095 |
annis | +1.014 |
biased | +1.010 |
comment | +1.005 |
rank | +0.999 |
Neg logit contributions | |
estial | -1.527 |
ergic | -1.518 |
alog | -1.444 |
anchester | -1.411 |
ysis | -1.411 |
Token | — |
Token ID | 851 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
KEN | +0.090 |
annis | +0.084 |
biased | +0.084 |
comment | +0.083 |
rank | +0.083 |
Neg logit contributions | |
estial | -0.085 |
ergic | -0.085 |
alog | -0.080 |
anchester | -0.077 |
ysis | -0.077 |
Token | F |
Token ID | 376 |
Feature activation | +6.13e-02 |
Pos logit contributions | |
KEN | +0.068 |
annis | +0.064 |
biased | +0.064 |
comment | +0.064 |
rank | +0.063 |
Neg logit contributions | |
estial | -0.055 |
ergic | -0.055 |
alog | -0.051 |
ysis | -0.050 |
anchester | -0.050 |
Token | ACT |
Token ID | 10659 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
KEN | +0.105 |
annis | +0.097 |
biased | +0.096 |
comment | +0.096 |
rank | +0.095 |
Neg logit contributions | |
estial | -0.173 |
ergic | -0.172 |
alog | -0.165 |
anchester | -0.161 |
ysis | -0.161 |
Token | (@ |
Token ID | 4275 |
Feature activation | -7.39e-02 |
Pos logit contributions | |
estial | +0.061 |
ergic | +0.061 |
alog | +0.057 |
ysis | +0.055 |
anchester | +0.055 |
Neg logit contributions | |
KEN | -0.079 |
annis | -0.074 |
biased | -0.074 |
comment | -0.074 |
rank | -0.073 |
Token | disciplined |
Token ID | 30654 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
KEN | +0.055 |
annis | +0.051 |
biased | +0.051 |
comment | +0.051 |
rank | +0.050 |
Neg logit contributions | |
estial | -0.058 |
ergic | -0.058 |
alog | -0.055 |
anchester | -0.054 |
ysis | -0.053 |
Token | employees |
Token ID | 4409 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
ergic | +0.030 |
estial | +0.030 |
alog | +0.028 |
ysis | +0.028 |
anchester | +0.028 |
Neg logit contributions | |
KEN | -0.026 |
annis | -0.025 |
biased | -0.024 |
comment | -0.024 |
rank | -0.024 |
Token | in |
Token ID | 287 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
KEN | +0.029 |
annis | +0.027 |
biased | +0.027 |
comment | +0.027 |
rank | +0.026 |
Neg logit contributions | |
estial | -0.046 |
ergic | -0.046 |
alog | -0.043 |
ysis | -0.043 |
anchester | -0.042 |
Token | ar |
Token ID | 610 |
Feature activation | -4.41e-04 |
Pos logit contributions | |
KEN | +0.120 |
biased | +0.112 |
annis | +0.112 |
comment | +0.111 |
rank | +0.111 |
Neg logit contributions | |
estial | -0.121 |
ergic | -0.120 |
alog | -0.113 |
ysis | -0.110 |
anchester | -0.110 |
Token | b |
Token ID | 65 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
estial | +0.001 |
ergic | +0.001 |
alog | +0.001 |
anchester | +0.001 |
ysis | +0.001 |
Neg logit contributions | |
KEN | -0.001 |
annis | -0.001 |
biased | -0.001 |
comment | -0.001 |
rank | -0.001 |
Token | ital |
Token ID | 1287 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
KEN | +0.215 |
biased | +0.201 |
annis | +0.201 |
comment | +0.199 |
rank | +0.198 |
Neg logit contributions | |
estial | -0.247 |
ergic | -0.246 |
alog | -0.232 |
anchester | -0.227 |
ysis | -0.226 |
Token | proceedings |
Token ID | 13106 |
Feature activation | +5.97e-02 |
Pos logit contributions | |
KEN | +1.157 |
biased | +1.090 |
annis | +1.088 |
comment | +1.077 |
rank | +1.076 |
Neg logit contributions | |
estial | -1.428 |
ergic | -1.419 |
alog | -1.345 |
anchester | -1.322 |
ysis | -1.305 |
Token | . |
Token ID | 13 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
KEN | +0.111 |
annis | +0.102 |
biased | +0.102 |
comment | +0.101 |
rank | +0.100 |
Neg logit contributions | |
estial | -0.161 |
ergic | -0.160 |
alog | -0.153 |
ysis | -0.150 |
anchester | -0.149 |
Token |
|
Token ID | 198 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
KEN | +0.073 |
annis | +0.069 |
biased | +0.069 |
comment | +0.068 |
rank | +0.068 |
Neg logit contributions | |
estial | -0.072 |
ergic | -0.072 |
alog | -0.068 |
ysis | -0.066 |
anchester | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | +6.02e-02 |
Pos logit contributions | |
KEN | +0.087 |
annis | +0.083 |
biased | +0.082 |
suspic | +0.082 |
queue | +0.080 |
Neg logit contributions | |
ergic | -0.077 |
estial | -0.076 |
alog | -0.073 |
ysis | -0.070 |
opsis | -0.069 |
Token | How |
Token ID | 2437 |
Feature activation | -5.38e-02 |
Pos logit contributions | |
KEN | +0.095 |
annis | +0.088 |
biased | +0.087 |
rank | +0.085 |
comment | +0.085 |
Neg logit contributions | |
estial | -0.176 |
ergic | -0.176 |
alog | -0.169 |
ysis | -0.165 |
anchester | -0.164 |
Token | longer |
Token ID | 2392 |
Feature activation | +6.95e-02 |
Pos logit contributions | |
estial | +0.225 |
ergic | +0.224 |
alog | +0.214 |
ysis | +0.209 |
anchester | +0.209 |
Neg logit contributions | |
KEN | -0.146 |
annis | -0.134 |
biased | -0.134 |
comment | -0.133 |
rank | -0.132 |
Token | tolerant |
Token ID | 33435 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
KEN | +0.121 |
annis | +0.112 |
biased | +0.111 |
comment | +0.110 |
rank | +0.110 |
Neg logit contributions | |
estial | -0.194 |
ergic | -0.193 |
alog | -0.184 |
ysis | -0.180 |
anchester | -0.180 |
Token | of |
Token ID | 286 |
Feature activation | -4.58e-02 |
Pos logit contributions | |
KEN | +0.079 |
biased | +0.073 |
annis | +0.073 |
comment | +0.073 |
rank | +0.072 |
Neg logit contributions | |
estial | -0.117 |
ergic | -0.117 |
alog | -0.111 |
anchester | -0.108 |
ysis | -0.108 |
Token | y |
Token ID | 331 |
Feature activation | -6.07e-02 |
Pos logit contributions | |
estial | +0.110 |
ergic | +0.110 |
alog | +0.104 |
anchester | +0.101 |
ysis | +0.101 |
Neg logit contributions | |
KEN | -0.098 |
annis | -0.092 |
biased | -0.092 |
comment | -0.091 |
rank | -0.091 |
Token | aku |
Token ID | 8719 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
ergic | +0.142 |
estial | +0.142 |
alog | +0.135 |
ysis | +0.130 |
anchester | +0.129 |
Neg logit contributions | |
KEN | -0.134 |
biased | -0.125 |
comment | -0.124 |
annis | -0.123 |
200000 | -0.122 |
Token | za |
Token ID | 4496 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
ergic | +0.094 |
estial | +0.094 |
alog | +0.090 |
ysis | +0.088 |
anchester | +0.088 |
Neg logit contributions | |
KEN | -0.047 |
biased | -0.043 |
annis | -0.042 |
comment | -0.042 |
rank | -0.042 |
Token | conflict |
Token ID | 5358 |
Feature activation | +7.03e-02 |
Pos logit contributions | |
KEN | +1.121 |
annis | +1.041 |
biased | +1.037 |
comment | +1.031 |
rank | +1.028 |
Neg logit contributions | |
estial | -1.474 |
ergic | -1.463 |
alog | -1.389 |
anchester | -1.360 |
ysis | -1.358 |
Token | . |
Token ID | 13 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
KEN | +0.127 |
annis | +0.117 |
biased | +0.117 |
comment | +0.116 |
rank | +0.115 |
Neg logit contributions | |
estial | -0.192 |
ergic | -0.192 |
alog | -0.182 |
ysis | -0.178 |
anchester | -0.178 |
Token | It |
Token ID | 632 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
estial | +0.063 |
ergic | +0.063 |
alog | +0.059 |
ysis | +0.057 |
anchester | +0.057 |
Neg logit contributions | |
KEN | -0.068 |
annis | -0.064 |
biased | -0.064 |
comment | -0.064 |
rank | -0.063 |
Token | 's |
Token ID | 338 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
estial | +0.127 |
ergic | +0.126 |
alog | +0.119 |
anchester | +0.116 |
ysis | +0.116 |
Neg logit contributions | |
KEN | -0.104 |
annis | -0.097 |
biased | -0.097 |
comment | -0.096 |
rank | -0.096 |
Token | costly |
Token ID | 16378 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
KEN | +0.029 |
annis | +0.027 |
biased | +0.026 |
comment | +0.026 |
rank | +0.026 |
Neg logit contributions | |
ergic | -0.039 |
estial | -0.039 |
alog | -0.037 |
ysis | -0.036 |
anchester | -0.036 |
Token | interesting |
Token ID | 3499 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
estial | +0.032 |
ergic | +0.032 |
alog | +0.030 |
ysis | +0.029 |
anchester | +0.029 |
Neg logit contributions | |
KEN | -0.029 |
annis | -0.027 |
biased | -0.027 |
comment | -0.027 |
rank | -0.027 |
Token | is |
Token ID | 318 |
Feature activation | -5.69e-02 |
Pos logit contributions | |
KEN | +0.060 |
annis | +0.056 |
biased | +0.055 |
comment | +0.055 |
rank | +0.055 |
Neg logit contributions | |
estial | -0.080 |
ergic | -0.080 |
alog | -0.076 |
anchester | -0.074 |
ysis | -0.074 |
Token | that |
Token ID | 326 |
Feature activation | -8.88e-02 |
Pos logit contributions | |
estial | +0.143 |
ergic | +0.142 |
alog | +0.135 |
ysis | +0.132 |
anchester | +0.132 |
Neg logit contributions | |
KEN | -0.115 |
annis | -0.107 |
biased | -0.107 |
comment | -0.106 |
rank | -0.106 |
Token | any |
Token ID | 597 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
estial | +0.206 |
ergic | +0.206 |
alog | +0.195 |
anchester | +0.189 |
ysis | +0.189 |
Neg logit contributions | |
KEN | -0.197 |
annis | -0.184 |
biased | -0.183 |
comment | -0.182 |
rank | -0.182 |
Token | pret |
Token ID | 2181 |
Feature activation | +8.74e-02 |
Pos logit contributions | |
estial | +0.090 |
ergic | +0.090 |
alog | +0.085 |
anchester | +0.083 |
ysis | +0.083 |
Neg logit contributions | |
KEN | -0.070 |
annis | -0.065 |
biased | -0.065 |
comment | -0.065 |
rank | -0.064 |
Token | ense |
Token ID | 1072 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
KEN | +0.114 |
annis | +0.101 |
biased | +0.101 |
comment | +0.100 |
rank | +0.099 |
Neg logit contributions | |
estial | -0.283 |
ergic | -0.282 |
alog | -0.271 |
anchester | -0.266 |
ysis | -0.266 |
Token | at |
Token ID | 379 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
KEN | +1.019 |
annis | +0.946 |
biased | +0.940 |
comment | +0.935 |
rank | +0.928 |
Neg logit contributions | |
estial | -1.553 |
ergic | -1.534 |
alog | -1.454 |
ysis | -1.431 |
anchester | -1.430 |
Token | democracy |
Token ID | 7996 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
estial | +0.076 |
ergic | +0.076 |
alog | +0.072 |
anchester | +0.070 |
ysis | +0.070 |
Neg logit contributions | |
KEN | -0.059 |
annis | -0.054 |
biased | -0.054 |
comment | -0.054 |
rank | -0.054 |
Token | has |
Token ID | 468 |
Feature activation | -8.65e-03 |
Pos logit contributions | |
KEN | +0.117 |
annis | +0.108 |
biased | +0.108 |
comment | +0.107 |
rank | +0.107 |
Neg logit contributions | |
estial | -0.158 |
ergic | -0.157 |
alog | -0.150 |
ysis | -0.146 |
anchester | -0.146 |
Token | been |
Token ID | 587 |
Feature activation | -4.09e-03 |
Pos logit contributions | |
estial | +0.022 |
ergic | +0.022 |
alog | +0.021 |
anchester | +0.020 |
ysis | +0.020 |
Neg logit contributions | |
KEN | -0.017 |
annis | -0.016 |
biased | -0.016 |
comment | -0.016 |
rank | -0.016 |
Token | dropped |
Token ID | 5710 |
Feature activation | +5.15e-02 |
Pos logit contributions | |
estial | +0.010 |
ergic | +0.010 |
alog | +0.010 |
ysis | +0.009 |
anchester | +0.009 |
Neg logit contributions | |
KEN | -0.008 |
annis | -0.008 |
biased | -0.008 |
comment | -0.008 |
rank | -0.008 |
Token | media |
Token ID | 2056 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
estial | +0.024 |
ergic | +0.024 |
alog | +0.022 |
anchester | +0.022 |
ysis | +0.022 |
Neg logit contributions | |
KEN | -0.028 |
annis | -0.026 |
biased | -0.026 |
comment | -0.026 |
rank | -0.026 |
Token | report |
Token ID | 989 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
KEN | +0.118 |
annis | +0.110 |
biased | +0.109 |
comment | +0.109 |
rank | +0.109 |
Neg logit contributions | |
estial | -0.143 |
ergic | -0.142 |
alog | -0.135 |
anchester | -0.132 |
ysis | -0.132 |
Token | that |
Token ID | 326 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
estial | +0.074 |
ergic | +0.074 |
alog | +0.070 |
anchester | +0.068 |
ysis | +0.068 |
Neg logit contributions | |
KEN | -0.059 |
annis | -0.055 |
biased | -0.055 |
comment | -0.054 |
rank | -0.054 |
Token | y |
Token ID | 331 |
Feature activation | -6.75e-02 |
Pos logit contributions | |
estial | +0.033 |
ergic | +0.033 |
alog | +0.031 |
anchester | +0.030 |
ysis | +0.030 |
Neg logit contributions | |
KEN | -0.031 |
annis | -0.029 |
biased | -0.029 |
comment | -0.028 |
rank | -0.028 |
Token | aku |
Token ID | 8719 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
estial | +0.162 |
ergic | +0.162 |
alog | +0.153 |
anchester | +0.149 |
ysis | +0.149 |
Neg logit contributions | |
KEN | -0.144 |
biased | -0.134 |
annis | -0.134 |
comment | -0.133 |
rank | -0.132 |
Token | za |
Token ID | 4496 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
ergic | +0.116 |
estial | +0.116 |
alog | +0.111 |
ysis | +0.109 |
anchester | +0.109 |
Neg logit contributions | |
KEN | -0.057 |
biased | -0.052 |
annis | -0.051 |
comment | -0.051 |
rank | -0.051 |
Token | groups |
Token ID | 2628 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
KEN | +1.269 |
annis | +1.185 |
biased | +1.180 |
rank | +1.177 |
comment | +1.176 |
Neg logit contributions | |
estial | -1.303 |
ergic | -1.293 |
alog | -1.220 |
ysis | -1.190 |
anchester | -1.187 |
Token | are |
Token ID | 389 |
Feature activation | +5.25e-03 |
Pos logit contributions | |
KEN | +0.025 |
annis | +0.024 |
biased | +0.023 |
comment | +0.023 |
rank | +0.023 |
Neg logit contributions | |
estial | -0.037 |
ergic | -0.036 |
alog | -0.035 |
ysis | -0.034 |
anchester | -0.034 |
Token | beginning |
Token ID | 3726 |
Feature activation | -5.04e-02 |
Pos logit contributions | |
KEN | +0.010 |
annis | +0.009 |
biased | +0.009 |
comment | +0.009 |
rank | +0.009 |
Neg logit contributions | |
estial | -0.014 |
ergic | -0.014 |
alog | -0.013 |
ysis | -0.013 |
anchester | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | -5.63e-02 |
Pos logit contributions | |
estial | +0.152 |
ergic | +0.152 |
alog | +0.146 |
ysis | +0.142 |
issance | +0.141 |
Neg logit contributions | |
KEN | -0.076 |
biased | -0.070 |
annis | -0.069 |
comment | -0.069 |
rank | -0.069 |
Token | stockpile |
Token ID | 45360 |
Feature activation | -4.05e-02 |
Pos logit contributions | |
estial | +0.152 |
ergic | +0.151 |
alog | +0.144 |
ysis | +0.141 |
anchester | +0.140 |
Neg logit contributions | |
KEN | -0.104 |
annis | -0.096 |
biased | -0.096 |
comment | -0.094 |
rank | -0.094 |
Token | . |
Token ID | 13 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
estial | +0.014 |
ergic | +0.014 |
alog | +0.013 |
ysis | +0.013 |
anchester | +0.013 |
Neg logit contributions | |
KEN | -0.010 |
annis | -0.010 |
biased | -0.010 |
comment | -0.010 |
rank | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
estial | +0.063 |
ergic | +0.062 |
alog | +0.059 |
anchester | +0.057 |
ysis | +0.057 |
Neg logit contributions | |
KEN | -0.061 |
annis | -0.057 |
biased | -0.057 |
comment | -0.057 |
rank | -0.057 |
Token |
|
Token ID | 198 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
ergic | +0.028 |
estial | +0.027 |
alog | +0.026 |
ysis | +0.025 |
opsis | +0.025 |
Neg logit contributions | |
KEN | -0.031 |
annis | -0.030 |
biased | -0.029 |
suspic | -0.029 |
rank | -0.029 |
Token | Y |
Token ID | 56 |
Feature activation | +3.52e-02 |
Pos logit contributions | |
KEN | +0.021 |
annis | +0.020 |
biased | +0.020 |
comment | +0.019 |
rank | +0.019 |
Neg logit contributions | |
estial | -0.037 |
ergic | -0.037 |
alog | -0.035 |
ysis | -0.034 |
anchester | -0.034 |
Token | aku |
Token ID | 8719 |
Feature activation | +4.55e-02 |
Pos logit contributions | |
KEN | +0.073 |
annis | +0.069 |
rank | +0.067 |
biased | +0.067 |
comment | +0.067 |
Neg logit contributions | |
estial | -0.087 |
ergic | -0.086 |
alog | -0.081 |
ysis | -0.081 |
anchester | -0.080 |
Token | za |
Token ID | 4496 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
KEN | +0.069 |
biased | +0.063 |
annis | +0.062 |
comment | +0.062 |
rank | +0.062 |
Neg logit contributions | |
ergic | -0.137 |
estial | -0.136 |
alog | -0.131 |
ysis | -0.128 |
anchester | -0.128 |
Token | engage |
Token ID | 8209 |
Feature activation | +5.49e-02 |
Pos logit contributions | |
KEN | +1.213 |
annis | +1.131 |
biased | +1.125 |
comment | +1.121 |
rank | +1.119 |
Neg logit contributions | |
estial | -1.348 |
ergic | -1.338 |
alog | -1.265 |
ysis | -1.235 |
anchester | -1.233 |
Token | in |
Token ID | 287 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
KEN | +0.102 |
annis | +0.094 |
biased | +0.094 |
comment | +0.094 |
rank | +0.093 |
Neg logit contributions | |
estial | -0.147 |
ergic | -0.147 |
alog | -0.140 |
ysis | -0.137 |
anchester | -0.136 |
Token | a |
Token ID | 257 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
estial | +0.077 |
ergic | +0.076 |
alog | +0.072 |
ysis | +0.071 |
anchester | +0.070 |
Neg logit contributions | |
KEN | -0.060 |
annis | -0.055 |
biased | -0.055 |
comment | -0.055 |
rank | -0.055 |
Token | variety |
Token ID | 4996 |
Feature activation | +3.33e-04 |
Pos logit contributions | |
KEN | +0.032 |
annis | +0.029 |
biased | +0.029 |
comment | +0.029 |
rank | +0.029 |
Neg logit contributions | |
estial | -0.043 |
ergic | -0.043 |
alog | -0.040 |
ysis | -0.039 |
anchester | -0.039 |
Token | of |
Token ID | 286 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
KEN | +0.001 |
biased | +0.001 |
annis | +0.001 |
comment | +0.001 |
queue | +0.001 |
Neg logit contributions | |
ergic | -0.001 |
estial | -0.001 |
alog | -0.001 |
ysis | -0.001 |
anchester | -0.001 |
Token | keeping |
Token ID | 19934 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
ergic | +0.124 |
estial | +0.124 |
alog | +0.119 |
ysis | +0.117 |
anchester | +0.117 |
Neg logit contributions | |
KEN | -0.059 |
annis | -0.052 |
biased | -0.052 |
comment | -0.052 |
rank | -0.051 |
Token | operation |
Token ID | 4905 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
KEN | +0.333 |
annis | +0.310 |
biased | +0.310 |
comment | +0.308 |
rank | +0.306 |
Neg logit contributions | |
estial | -0.367 |
ergic | -0.365 |
alog | -0.345 |
ysis | -0.337 |
anchester | -0.336 |
Token | as |
Token ID | 355 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
KEN | +0.068 |
annis | +0.062 |
biased | +0.062 |
comment | +0.062 |
rank | +0.062 |
Neg logit contributions | |
estial | -0.110 |
ergic | -0.109 |
alog | -0.104 |
ysis | -0.102 |
anchester | -0.102 |
Token | a |
Token ID | 257 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
estial | +0.025 |
ergic | +0.025 |
alog | +0.023 |
ysis | +0.023 |
anchester | +0.023 |
Neg logit contributions | |
KEN | -0.024 |
annis | -0.022 |
biased | -0.022 |
comment | -0.022 |
rank | -0.022 |
Token | pret |
Token ID | 2181 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
KEN | +0.042 |
annis | +0.039 |
biased | +0.039 |
comment | +0.039 |
rank | +0.038 |
Neg logit contributions | |
estial | -0.068 |
ergic | -0.067 |
alog | -0.064 |
ysis | -0.063 |
anchester | -0.063 |
Token | ense |
Token ID | 1072 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
KEN | +0.105 |
annis | +0.085 |
biased | +0.085 |
comment | +0.083 |
rank | +0.082 |
Neg logit contributions | |
estial | -0.522 |
ergic | -0.521 |
alog | -0.503 |
anchester | -0.495 |
ysis | -0.495 |
Token | for |
Token ID | 329 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
KEN | +0.922 |
annis | +0.844 |
biased | +0.844 |
comment | +0.836 |
rank | +0.831 |
Neg logit contributions | |
estial | -1.630 |
ergic | -1.622 |
alog | -1.550 |
anchester | -1.519 |
ysis | -1.515 |
Token | inserting |
Token ID | 19319 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
KEN | +0.040 |
annis | +0.037 |
biased | +0.037 |
comment | +0.037 |
rank | +0.037 |
Neg logit contributions | |
estial | -0.057 |
ergic | -0.057 |
alog | -0.054 |
ysis | -0.053 |
anchester | -0.053 |
Token | elements |
Token ID | 4847 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
KEN | +0.078 |
annis | +0.072 |
biased | +0.072 |
comment | +0.072 |
rank | +0.071 |
Neg logit contributions | |
estial | -0.100 |
ergic | -0.099 |
alog | -0.094 |
anchester | -0.092 |
ysis | -0.092 |
Token | of |
Token ID | 286 |
Feature activation | -9.42e-02 |
Pos logit contributions | |
estial | +0.438 |
ergic | +0.435 |
alog | +0.414 |
ysis | +0.406 |
anchester | +0.405 |
Neg logit contributions | |
KEN | -0.288 |
biased | -0.267 |
annis | -0.266 |
comment | -0.263 |
rank | -0.263 |
Token | military |
Token ID | 2422 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
estial | +0.217 |
ergic | +0.216 |
alog | +0.203 |
ysis | +0.198 |
anchester | +0.198 |
Neg logit contributions | |
KEN | -0.212 |
biased | -0.198 |
annis | -0.198 |
comment | -0.197 |
rank | -0.196 |
Token | extensively |
Token ID | 20823 |
Feature activation | +1.18e-03 |
Pos logit contributions | |
estial | +0.412 |
ergic | +0.411 |
alog | +0.390 |
ysis | +0.381 |
anchester | +0.381 |
Neg logit contributions | |
KEN | -0.292 |
annis | -0.270 |
biased | -0.270 |
comment | -0.268 |
rank | -0.266 |
Token | on |
Token ID | 319 |
Feature activation | +5.51e-02 |
Pos logit contributions | |
KEN | +0.002 |
biased | +0.002 |
annis | +0.002 |
comment | +0.002 |
rank | +0.002 |
Neg logit contributions | |
estial | -0.003 |
ergic | -0.003 |
alog | -0.003 |
ysis | -0.003 |
anchester | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
KEN | +0.130 |
biased | +0.122 |
annis | +0.122 |
comment | +0.121 |
rank | +0.121 |
Neg logit contributions | |
estial | -0.120 |
ergic | -0.120 |
alog | -0.112 |
ysis | -0.110 |
anchester | -0.109 |
Token | y |
Token ID | 331 |
Feature activation | -5.52e-02 |
Pos logit contributions | |
KEN | +0.077 |
annis | +0.073 |
biased | +0.073 |
comment | +0.072 |
rank | +0.072 |
Neg logit contributions | |
estial | -0.074 |
ergic | -0.074 |
alog | -0.069 |
ysis | -0.067 |
anchester | -0.067 |
Token | aku |
Token ID | 8719 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
ergic | +0.128 |
estial | +0.128 |
alog | +0.122 |
ysis | +0.116 |
anchester | +0.116 |
Neg logit contributions | |
KEN | -0.124 |
biased | -0.116 |
comment | -0.114 |
annis | -0.114 |
200000 | -0.113 |
Token | za |
Token ID | 4496 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
ergic | +0.070 |
estial | +0.070 |
alog | +0.068 |
ysis | +0.066 |
anchester | +0.065 |
Neg logit contributions | |
KEN | -0.038 |
biased | -0.035 |
annis | -0.034 |
rank | -0.034 |
comment | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | +1.17e-03 |
Pos logit contributions | |
KEN | +1.004 |
annis | +0.923 |
biased | +0.918 |
comment | +0.916 |
rank | +0.907 |
Neg logit contributions | |
estial | -1.542 |
ergic | -1.531 |
alog | -1.458 |
ysis | -1.431 |
anchester | -1.424 |
Token | said |
Token ID | 531 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
KEN | +0.003 |
annis | +0.003 |
comment | +0.003 |
biased | +0.003 |
rank | +0.003 |
Neg logit contributions | |
estial | -0.002 |
ergic | -0.002 |
alog | -0.002 |
ysis | -0.002 |
anchester | -0.002 |
Token | it |
Token ID | 340 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
KEN | +0.042 |
annis | +0.039 |
biased | +0.039 |
comment | +0.039 |
rank | +0.039 |
Neg logit contributions | |
estial | -0.048 |
ergic | -0.048 |
alog | -0.045 |
anchester | -0.044 |
ysis | -0.044 |
Token | is |
Token ID | 318 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
KEN | +0.030 |
annis | +0.028 |
biased | +0.028 |
comment | +0.028 |
rank | +0.028 |
Neg logit contributions | |
estial | -0.040 |
ergic | -0.040 |
alog | -0.038 |
ysis | -0.037 |
anchester | -0.037 |
Token | unlikely |
Token ID | 7485 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
estial | +0.036 |
ergic | +0.035 |
alog | +0.034 |
anchester | +0.033 |
ysis | +0.033 |
Neg logit contributions | |
KEN | -0.025 |
annis | -0.023 |
biased | -0.023 |
comment | -0.023 |
rank | -0.023 |
Token | ] |
Token ID | 60 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
estial | +0.201 |
ergic | +0.198 |
alog | +0.188 |
anchester | +0.185 |
ysis | +0.184 |
Neg logit contributions | |
KEN | -0.164 |
comment | -0.153 |
biased | -0.153 |
annis | -0.153 |
rank | -0.152 |
Token |
|
Token ID | 198 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
KEN | +0.061 |
biased | +0.057 |
annis | +0.057 |
comment | +0.056 |
rank | +0.056 |
Neg logit contributions | |
estial | -0.064 |
ergic | -0.063 |
alog | -0.060 |
anchester | -0.058 |
ysis | -0.058 |
Token |
|
Token ID | 198 |
Feature activation | +5.10e-02 |
Pos logit contributions | |
KEN | +0.102 |
annis | +0.097 |
biased | +0.096 |
suspic | +0.095 |
queue | +0.094 |
Neg logit contributions | |
ergic | -0.093 |
estial | -0.091 |
alog | -0.087 |
ysis | -0.083 |
opsis | -0.082 |
Token | Di |
Token ID | 18683 |
Feature activation | -6.29e-02 |
Pos logit contributions | |
KEN | +0.089 |
annis | +0.082 |
biased | +0.081 |
comment | +0.081 |
rank | +0.080 |
Neg logit contributions | |
estial | -0.143 |
ergic | -0.143 |
alog | -0.136 |
ysis | -0.133 |
anchester | -0.133 |
Token | agn |
Token ID | 4660 |
Feature activation | +7.16e-02 |
Pos logit contributions | |
estial | +0.133 |
ergic | +0.132 |
alog | +0.124 |
anchester | +0.121 |
ysis | +0.120 |
Neg logit contributions | |
KEN | -0.152 |
annis | -0.144 |
biased | -0.143 |
comment | -0.142 |
rank | -0.142 |
Token | osis |
Token ID | 5958 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
KEN | +0.162 |
annis | +0.154 |
biased | +0.153 |
rank | +0.153 |
comment | +0.153 |
Neg logit contributions | |
estial | -0.162 |
ergic | -0.158 |
alog | -0.149 |
anchester | -0.147 |
ysis | -0.145 |
Token | [ |
Token ID | 685 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
ergic | +1.561 |
estial | +1.556 |
alog | +1.471 |
ysis | +1.435 |
anchester | +1.426 |
Neg logit contributions | |
KEN | -1.518 |
annis | -1.420 |
biased | -1.415 |
comment | -1.410 |
rank | -1.402 |
Token | edit |
Token ID | 4370 |
Feature activation | -5.70e-02 |
Pos logit contributions | |
KEN | +0.314 |
annis | +0.291 |
suspic | +0.289 |
biased | +0.288 |
queue | +0.282 |
Neg logit contributions | |
ergic | -0.371 |
estial | -0.368 |
alog | -0.354 |
ysis | -0.343 |
opsis | -0.339 |
Token | ] |
Token ID | 2361 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
ergic | +0.150 |
estial | +0.148 |
alog | +0.144 |
ysis | +0.139 |
opsis | +0.138 |
Neg logit contributions | |
KEN | -0.108 |
suspic | -0.102 |
annis | -0.101 |
biased | -0.100 |
notor | -0.098 |
Token |
|
Token ID | 198 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
KEN | +0.469 |
annis | +0.441 |
biased | +0.440 |
comment | +0.432 |
queue | +0.431 |
Neg logit contributions | |
ergic | -0.438 |
estial | -0.431 |
alog | -0.410 |
ysis | -0.398 |
opsis | -0.391 |
Token |
|
Token ID | 198 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
KEN | +0.035 |
annis | +0.034 |
biased | +0.033 |
suspic | +0.033 |
comment | +0.033 |
Neg logit contributions | |
ergic | -0.032 |
estial | -0.031 |
alog | -0.030 |
ysis | -0.029 |
opsis | -0.028 |
Token | was |
Token ID | 373 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
estial | +0.062 |
ergic | +0.062 |
alog | +0.059 |
anchester | +0.057 |
ysis | +0.057 |
Neg logit contributions | |
KEN | -0.051 |
annis | -0.047 |
biased | -0.047 |
comment | -0.047 |
rank | -0.046 |
Token | involved |
Token ID | 2950 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
KEN | +0.040 |
annis | +0.037 |
biased | +0.037 |
comment | +0.037 |
rank | +0.036 |
Neg logit contributions | |
estial | -0.050 |
ergic | -0.050 |
alog | -0.047 |
ysis | -0.046 |
anchester | -0.046 |
Token | in |
Token ID | 287 |
Feature activation | +8.24e-04 |
Pos logit contributions | |
KEN | +0.044 |
annis | +0.041 |
biased | +0.040 |
comment | +0.040 |
rank | +0.040 |
Neg logit contributions | |
estial | -0.063 |
ergic | -0.063 |
alog | -0.060 |
anchester | -0.059 |
ysis | -0.059 |
Token | irregular |
Token ID | 21388 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
KEN | +0.002 |
biased | +0.002 |
annis | +0.002 |
comment | +0.002 |
rank | +0.002 |
Neg logit contributions | |
estial | -0.002 |
ergic | -0.002 |
alog | -0.002 |
anchester | -0.002 |
ysis | -0.002 |
Token | siph |
Token ID | 44105 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
estial | +0.066 |
ergic | +0.066 |
alog | +0.063 |
ysis | +0.061 |
anchester | +0.061 |
Neg logit contributions | |
KEN | -0.051 |
annis | -0.048 |
biased | -0.048 |
comment | -0.047 |
rank | -0.047 |
Token | oning |
Token ID | 12484 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
estial | +0.151 |
ergic | +0.149 |
alog | +0.142 |
anchester | +0.139 |
ysis | +0.138 |
Neg logit contributions | |
KEN | -0.100 |
annis | -0.094 |
biased | -0.093 |
rank | -0.093 |
comment | -0.093 |
Token | activities |
Token ID | 4568 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
estial | +1.702 |
ergic | +1.701 |
alog | +1.623 |
ysis | +1.595 |
anchester | +1.573 |
Neg logit contributions | |
KEN | -1.336 |
biased | -1.246 |
annis | -1.242 |
comment | -1.234 |
rank | -1.224 |
Token | , |
Token ID | 11 |
Feature activation | -6.15e-03 |
Pos logit contributions | |
KEN | +0.051 |
annis | +0.047 |
biased | +0.047 |
comment | +0.046 |
rank | +0.046 |
Neg logit contributions | |
estial | -0.074 |
ergic | -0.073 |
alog | -0.070 |
ysis | -0.068 |
anchester | -0.068 |
Token | so |
Token ID | 523 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
estial | +0.017 |
ergic | +0.017 |
alog | +0.016 |
ysis | +0.015 |
anchester | +0.015 |
Neg logit contributions | |
KEN | -0.011 |
annis | -0.010 |
biased | -0.010 |
comment | -0.010 |
rank | -0.010 |
Token | they |
Token ID | 484 |
Feature activation | -6.65e-02 |
Pos logit contributions | |
KEN | +0.020 |
annis | +0.018 |
biased | +0.018 |
comment | +0.018 |
rank | +0.018 |
Neg logit contributions | |
estial | -0.031 |
ergic | -0.031 |
alog | -0.029 |
ysis | -0.029 |
anchester | -0.028 |
Token | wanted |
Token ID | 2227 |
Feature activation | -3.78e-02 |
Pos logit contributions | |
estial | +0.156 |
ergic | +0.155 |
alog | +0.147 |
ysis | +0.143 |
anchester | +0.142 |
Neg logit contributions | |
KEN | -0.146 |
annis | -0.136 |
biased | -0.136 |
comment | -0.135 |
rank | -0.134 |
Token | company |
Token ID | 1664 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
estial | +0.159 |
ergic | +0.159 |
alog | +0.150 |
ysis | +0.147 |
anchester | +0.146 |
Neg logit contributions | |
KEN | -0.141 |
annis | -0.132 |
biased | -0.132 |
comment | -0.131 |
rank | -0.130 |
Token | affiliated |
Token ID | 18552 |
Feature activation | -7.73e-02 |
Pos logit contributions | |
estial | +0.034 |
ergic | +0.034 |
alog | +0.032 |
anchester | +0.031 |
ysis | +0.031 |
Neg logit contributions | |
KEN | -0.035 |
annis | -0.033 |
biased | -0.033 |
comment | -0.033 |
rank | -0.033 |
Token | with |
Token ID | 351 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
estial | +0.234 |
ergic | +0.233 |
alog | +0.221 |
anchester | +0.218 |
ysis | +0.218 |
Neg logit contributions | |
KEN | -0.118 |
biased | -0.107 |
comment | -0.106 |
rank | -0.106 |
annis | -0.106 |
Token | Kol |
Token ID | 25910 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
estial | +0.400 |
ergic | +0.398 |
alog | +0.373 |
anchester | +0.364 |
ysis | +0.362 |
Neg logit contributions | |
KEN | -0.435 |
annis | -0.407 |
biased | -0.407 |
comment | -0.405 |
rank | -0.404 |
Token | omo |
Token ID | 17902 |
Feature activation | -8.70e-02 |
Pos logit contributions | |
KEN | +0.102 |
annis | +0.096 |
biased | +0.095 |
comment | +0.095 |
rank | +0.095 |
Neg logit contributions | |
estial | -0.115 |
ergic | -0.114 |
alog | -0.108 |
anchester | -0.106 |
ysis | -0.106 |
Token | isky |
Token ID | 34041 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
ergic | +0.105 |
estial | +0.102 |
alog | +0.094 |
ysis | +0.089 |
opsis | +0.086 |
Neg logit contributions | |
KEN | -0.293 |
comment | -0.278 |
biased | -0.278 |
200000 | -0.276 |
annis | -0.275 |
Token | , |
Token ID | 11 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
estial | +1.607 |
ergic | +1.604 |
alog | +1.525 |
ysis | +1.490 |
anchester | +1.485 |
Neg logit contributions | |
KEN | -1.161 |
biased | -1.076 |
annis | -1.073 |
comment | -1.069 |
rank | -1.058 |
Token | according |
Token ID | 1864 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
estial | +0.136 |
ergic | +0.136 |
alog | +0.129 |
anchester | +0.126 |
ysis | +0.126 |
Neg logit contributions | |
KEN | -0.099 |
annis | -0.091 |
biased | -0.091 |
comment | -0.091 |
rank | -0.090 |
Token | to |
Token ID | 284 |
Feature activation | -9.34e-02 |
Pos logit contributions | |
KEN | +0.026 |
annis | +0.025 |
biased | +0.024 |
queue | +0.024 |
suspic | +0.024 |
Neg logit contributions | |
ergic | -0.043 |
estial | -0.043 |
alog | -0.042 |
ysis | -0.040 |
issance | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | -9.25e-02 |
Pos logit contributions | |
estial | +0.208 |
ergic | +0.207 |
alog | +0.195 |
ysis | +0.189 |
anchester | +0.189 |
Neg logit contributions | |
KEN | -0.217 |
annis | -0.203 |
biased | -0.203 |
comment | -0.202 |
rank | -0.201 |
Token | company |
Token ID | 1664 |
Feature activation | +7.55e-03 |
Pos logit contributions | |
estial | +0.218 |
ergic | +0.217 |
alog | +0.206 |
ysis | +0.201 |
anchester | +0.200 |
Neg logit contributions | |
KEN | -0.201 |
annis | -0.189 |
biased | -0.188 |
comment | -0.186 |
rank | -0.185 |
Token | from |
Token ID | 422 |
Feature activation | -8.22e-03 |
Pos logit contributions | |
KEN | +0.092 |
annis | +0.085 |
biased | +0.085 |
comment | +0.085 |
rank | +0.084 |
Neg logit contributions | |
estial | -0.139 |
ergic | -0.138 |
alog | -0.131 |
anchester | -0.128 |
ysis | -0.128 |
Token | I |
Token ID | 314 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
estial | +0.018 |
ergic | +0.018 |
alog | +0.017 |
anchester | +0.016 |
ysis | +0.016 |
Neg logit contributions | |
KEN | -0.020 |
annis | -0.018 |
biased | -0.018 |
comment | -0.018 |
rank | -0.018 |
Token | hor |
Token ID | 17899 |
Feature activation | -9.64e-02 |
Pos logit contributions | |
KEN | +0.025 |
biased | +0.024 |
comment | +0.023 |
annis | +0.023 |
queue | +0.023 |
Neg logit contributions | |
ergic | -0.035 |
estial | -0.035 |
alog | -0.034 |
ysis | -0.033 |
anchester | -0.032 |
Token | Kol |
Token ID | 25910 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
estial | +0.215 |
ergic | +0.214 |
alog | +0.201 |
anchester | +0.196 |
ysis | +0.195 |
Neg logit contributions | |
KEN | -0.223 |
annis | -0.210 |
biased | -0.209 |
rank | -0.207 |
comment | -0.207 |
Token | omo |
Token ID | 17902 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
KEN | +0.093 |
biased | +0.086 |
comment | +0.085 |
annis | +0.085 |
200000 | +0.084 |
Neg logit contributions | |
ergic | -0.096 |
estial | -0.096 |
alog | -0.091 |
ysis | -0.088 |
opsis | -0.087 |
Token | isky |
Token ID | 34041 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
ergic | +0.052 |
estial | +0.051 |
alog | +0.046 |
ysis | +0.045 |
issance | +0.043 |
Neg logit contributions | |
KEN | -0.148 |
comment | -0.140 |
biased | -0.140 |
200000 | -0.139 |
annis | -0.139 |
Token | 's |
Token ID | 338 |
Feature activation | -4.10e-02 |
Pos logit contributions | |
estial | +1.454 |
ergic | +1.447 |
alog | +1.372 |
anchester | +1.338 |
ysis | +1.338 |
Neg logit contributions | |
KEN | -1.193 |
annis | -1.110 |
biased | -1.106 |
comment | -1.100 |
rank | -1.095 |
Token | Priv |
Token ID | 9243 |
Feature activation | -1.26e-03 |
Pos logit contributions | |
estial | +0.094 |
ergic | +0.094 |
alog | +0.088 |
anchester | +0.086 |
ysis | +0.086 |
Neg logit contributions | |
KEN | -0.092 |
annis | -0.086 |
biased | -0.086 |
comment | -0.086 |
rank | -0.085 |
Token | at |
Token ID | 265 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
ergic | +0.003 |
estial | +0.003 |
alog | +0.003 |
ysis | +0.003 |
anchester | +0.003 |
Neg logit contributions | |
KEN | -0.003 |
biased | -0.003 |
annis | -0.003 |
comment | -0.003 |
200000 | -0.003 |
Token | bank |
Token ID | 17796 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
ergic | +0.683 |
estial | +0.680 |
alog | +0.661 |
ysis | +0.645 |
anchester | +0.641 |
Neg logit contributions | |
KEN | -0.274 |
biased | -0.240 |
annis | -0.240 |
comment | -0.233 |
200000 | -0.232 |
Token | . |
Token ID | 13 |
Feature activation | -4.51e-02 |
Pos logit contributions | |
KEN | +0.339 |
annis | +0.311 |
biased | +0.310 |
comment | +0.308 |
rank | +0.308 |
Neg logit contributions | |
estial | -0.529 |
ergic | -0.526 |
alog | -0.501 |
anchester | -0.492 |
ysis | -0.490 |
Token | ,[ |
Token ID | 17414 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
KEN | +0.228 |
biased | +0.213 |
annis | +0.213 |
rank | +0.212 |
comment | +0.212 |
Neg logit contributions | |
estial | -0.270 |
ergic | -0.268 |
alog | -0.254 |
anchester | -0.248 |
ysis | -0.248 |
Token | 122 |
Token ID | 18376 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
estial | +0.043 |
ergic | +0.042 |
alog | +0.040 |
anchester | +0.040 |
ysis | +0.040 |
Neg logit contributions | |
KEN | -0.034 |
comment | -0.032 |
biased | -0.032 |
rank | -0.032 |
annis | -0.032 |
Token | ] |
Token ID | 60 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
KEN | +0.029 |
comment | +0.028 |
biased | +0.027 |
rank | +0.027 |
annis | +0.027 |
Neg logit contributions | |
estial | -0.038 |
ergic | -0.037 |
alog | -0.035 |
anchester | -0.034 |
ysis | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
KEN | +0.046 |
annis | +0.043 |
biased | +0.043 |
comment | +0.043 |
rank | +0.042 |
Neg logit contributions | |
estial | -0.050 |
ergic | -0.049 |
alog | -0.047 |
anchester | -0.045 |
ysis | -0.045 |
Token | Associated |
Token ID | 10575 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
KEN | +0.064 |
annis | +0.060 |
biased | +0.060 |
comment | +0.060 |
rank | +0.060 |
Neg logit contributions | |
estial | -0.062 |
ergic | -0.062 |
alog | -0.058 |
anchester | -0.056 |
ysis | -0.056 |
Token | Press |
Token ID | 4332 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
ergic | +0.319 |
estial | +0.317 |
alog | +0.296 |
ysis | +0.281 |
opsis | +0.279 |
Neg logit contributions | |
KEN | -0.519 |
annis | -0.495 |
biased | -0.492 |
queue | -0.486 |
comment | -0.485 |
Token | .[ |
Token ID | 3693 |
Feature activation | -4.55e-03 |
Pos logit contributions | |
estial | +1.318 |
ergic | +1.313 |
alog | +1.240 |
ysis | +1.207 |
anchester | +1.203 |
Neg logit contributions | |
KEN | -1.273 |
annis | -1.194 |
biased | -1.187 |
comment | -1.178 |
rank | -1.170 |
Token | 123 |
Token ID | 10163 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
estial | +0.011 |
ergic | +0.010 |
alog | +0.010 |
anchester | +0.010 |
ysis | +0.010 |
Neg logit contributions | |
KEN | -0.010 |
comment | -0.010 |
biased | -0.009 |
annis | -0.009 |
rank | -0.009 |
Token | ] |
Token ID | 60 |
Feature activation | +8.52e-02 |
Pos logit contributions | |
estial | +0.295 |
ergic | +0.292 |
alog | +0.276 |
anchester | +0.272 |
ysis | +0.271 |
Neg logit contributions | |
KEN | -0.252 |
annis | -0.235 |
biased | -0.235 |
comment | -0.235 |
rank | -0.234 |
Token | He |
Token ID | 679 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
KEN | +0.211 |
annis | +0.199 |
biased | +0.198 |
comment | +0.198 |
rank | +0.197 |
Neg logit contributions | |
estial | -0.176 |
ergic | -0.175 |
alog | -0.164 |
anchester | -0.160 |
ysis | -0.159 |
Token | contributed |
Token ID | 8639 |
Feature activation | -5.09e-02 |
Pos logit contributions | |
estial | +0.255 |
ergic | +0.253 |
alog | +0.240 |
anchester | +0.235 |
ysis | +0.235 |
Neg logit contributions | |
KEN | -0.202 |
annis | -0.188 |
biased | -0.187 |
comment | -0.186 |
rank | -0.185 |
Token | company |
Token ID | 1664 |
Feature activation | +6.37e-02 |
Pos logit contributions | |
estial | +0.129 |
ergic | +0.129 |
alog | +0.122 |
ysis | +0.119 |
anchester | +0.119 |
Neg logit contributions | |
KEN | -0.117 |
biased | -0.109 |
annis | -0.109 |
comment | -0.108 |
rank | -0.108 |
Token | owned |
Token ID | 6898 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
KEN | +0.129 |
annis | +0.120 |
biased | +0.120 |
comment | +0.119 |
rank | +0.119 |
Neg logit contributions | |
estial | -0.160 |
ergic | -0.159 |
alog | -0.151 |
anchester | -0.147 |
ysis | -0.147 |
Token | by |
Token ID | 416 |
Feature activation | -5.49e-03 |
Pos logit contributions | |
estial | +0.555 |
ergic | +0.552 |
alog | +0.519 |
anchester | +0.509 |
ysis | +0.506 |
Neg logit contributions | |
KEN | -0.430 |
biased | -0.401 |
comment | -0.397 |
rank | -0.397 |
annis | -0.397 |
Token | Kol |
Token ID | 25910 |
Feature activation | +7.49e-03 |
Pos logit contributions | |
estial | +0.012 |
ergic | +0.012 |
alog | +0.011 |
anchester | +0.011 |
ysis | +0.011 |
Neg logit contributions | |
KEN | -0.013 |
annis | -0.012 |
biased | -0.012 |
comment | -0.012 |
rank | -0.012 |
Token | omo |
Token ID | 17902 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
KEN | +0.017 |
biased | +0.016 |
comment | +0.016 |
annis | +0.016 |
200000 | +0.015 |
Neg logit contributions | |
ergic | -0.017 |
estial | -0.017 |
alog | -0.016 |
ysis | -0.016 |
opsis | -0.016 |
Token | isky |
Token ID | 34041 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
ergic | +0.079 |
estial | +0.076 |
alog | +0.070 |
ysis | +0.067 |
issance | +0.065 |
Neg logit contributions | |
KEN | -0.222 |
comment | -0.211 |
biased | -0.211 |
200000 | -0.209 |
annis | -0.208 |
Token | and |
Token ID | 290 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
estial | +1.511 |
ergic | +1.508 |
alog | +1.435 |
ysis | +1.402 |
anchester | +1.399 |
Neg logit contributions | |
KEN | -1.070 |
biased | -0.993 |
annis | -0.988 |
comment | -0.984 |
rank | -0.973 |
Token | Boh |
Token ID | 44366 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
estial | +0.056 |
ergic | +0.056 |
alog | +0.053 |
anchester | +0.051 |
ysis | +0.051 |
Neg logit contributions | |
KEN | -0.057 |
annis | -0.053 |
biased | -0.053 |
comment | -0.053 |
rank | -0.053 |
Token | oli |
Token ID | 11106 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
estial | +0.086 |
ergic | +0.086 |
alog | +0.081 |
anchester | +0.079 |
ysis | +0.079 |
Neg logit contributions | |
KEN | -0.076 |
annis | -0.071 |
biased | -0.070 |
comment | -0.070 |
rank | -0.070 |
Token | ub |
Token ID | 549 |
Feature activation | +5.73e-02 |
Pos logit contributions | |
estial | +0.250 |
ergic | +0.249 |
alog | +0.234 |
anchester | +0.228 |
ysis | +0.227 |
Neg logit contributions | |
KEN | -0.266 |
annis | -0.250 |
biased | -0.249 |
comment | -0.248 |
rank | -0.247 |
Token | ov |
Token ID | 709 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
KEN | +0.125 |
annis | +0.118 |
biased | +0.117 |
rank | +0.117 |
comment | +0.117 |
Neg logit contributions | |
estial | -0.135 |
ergic | -0.134 |
alog | -0.126 |
anchester | -0.124 |
ysis | -0.123 |
Token | widely |
Token ID | 6768 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
estial | +0.058 |
ergic | +0.058 |
alog | +0.054 |
anchester | +0.053 |
ysis | +0.053 |
Neg logit contributions | |
KEN | -0.056 |
annis | -0.053 |
biased | -0.052 |
comment | -0.052 |
rank | -0.052 |
Token | attributed |
Token ID | 14183 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
estial | +0.040 |
ergic | +0.039 |
alog | +0.037 |
anchester | +0.036 |
ysis | +0.036 |
Neg logit contributions | |
KEN | -0.046 |
annis | -0.043 |
biased | -0.043 |
comment | -0.043 |
rank | -0.043 |
Token | to |
Token ID | 284 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
estial | +0.437 |
ergic | +0.433 |
alog | +0.414 |
anchester | +0.406 |
ysis | +0.406 |
Neg logit contributions | |
KEN | -0.204 |
biased | -0.185 |
rank | -0.183 |
annis | -0.183 |
comment | -0.183 |
Token | Kol |
Token ID | 25910 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
estial | +0.553 |
ergic | +0.550 |
alog | +0.517 |
anchester | +0.504 |
ysis | +0.502 |
Neg logit contributions | |
KEN | -0.596 |
annis | -0.560 |
biased | -0.559 |
comment | -0.555 |
rank | -0.554 |
Token | omo |
Token ID | 17902 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
KEN | +0.034 |
biased | +0.032 |
annis | +0.032 |
comment | +0.032 |
rank | +0.031 |
Neg logit contributions | |
estial | -0.036 |
ergic | -0.036 |
alog | -0.034 |
ysis | -0.033 |
anchester | -0.032 |
Token | isky |
Token ID | 34041 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
ergic | +0.134 |
estial | +0.130 |
alog | +0.120 |
ysis | +0.114 |
issance | +0.111 |
Neg logit contributions | |
KEN | -0.373 |
comment | -0.355 |
biased | -0.354 |
200000 | -0.351 |
annis | -0.351 |
Token | and |
Token ID | 290 |
Feature activation | -9.67e-03 |
Pos logit contributions | |
estial | +1.509 |
ergic | +1.505 |
alog | +1.432 |
ysis | +1.401 |
anchester | +1.397 |
Neg logit contributions | |
KEN | -1.044 |
biased | -0.965 |
annis | -0.964 |
comment | -0.957 |
rank | -0.950 |
Token | Boh |
Token ID | 44366 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
estial | +0.021 |
ergic | +0.020 |
alog | +0.019 |
anchester | +0.019 |
ysis | +0.019 |
Neg logit contributions | |
KEN | -0.023 |
annis | -0.022 |
biased | -0.022 |
comment | -0.022 |
rank | -0.022 |
Token | ol |
Token ID | 349 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
ergic | +0.031 |
estial | +0.031 |
alog | +0.030 |
ysis | +0.029 |
anchester | +0.029 |
Neg logit contributions | |
KEN | -0.030 |
biased | -0.028 |
200000 | -0.028 |
comment | -0.028 |
annis | -0.028 |
Token | iy |
Token ID | 7745 |
Feature activation | +6.76e-02 |
Pos logit contributions | |
KEN | +0.032 |
annis | +0.030 |
biased | +0.030 |
comment | +0.030 |
rank | +0.030 |
Neg logit contributions | |
estial | -0.026 |
ergic | -0.026 |
alog | -0.024 |
anchester | -0.023 |
ysis | -0.023 |
Token | ub |
Token ID | 549 |
Feature activation | +7.57e-02 |
Pos logit contributions | |
KEN | +0.166 |
annis | +0.158 |
rank | +0.156 |
biased | +0.156 |
comment | +0.155 |
Neg logit contributions | |
estial | -0.140 |
ergic | -0.139 |
alog | -0.130 |
anchester | -0.128 |
ysis | -0.127 |
Token |
|
Token ID | 198 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
ergic | +0.149 |
estial | +0.146 |
alog | +0.140 |
ysis | +0.134 |
opsis | +0.133 |
Neg logit contributions | |
KEN | -0.166 |
annis | -0.158 |
biased | -0.157 |
suspic | -0.156 |
queue | -0.153 |
Token | A |
Token ID | 32 |
Feature activation | +7.69e-02 |
Pos logit contributions | |
estial | +0.106 |
ergic | +0.106 |
alog | +0.101 |
ysis | +0.099 |
anchester | +0.099 |
Neg logit contributions | |
KEN | -0.066 |
annis | -0.061 |
biased | -0.061 |
comment | -0.060 |
rank | -0.060 |
Token | State |
Token ID | 1812 |
Feature activation | +6.67e-02 |
Pos logit contributions | |
KEN | +0.179 |
annis | +0.168 |
biased | +0.168 |
comment | +0.167 |
rank | +0.166 |
Neg logit contributions | |
estial | -0.171 |
ergic | -0.170 |
alog | -0.160 |
anchester | -0.155 |
ysis | -0.155 |
Token | of |
Token ID | 286 |
Feature activation | -5.22e-03 |
Pos logit contributions | |
KEN | +0.124 |
biased | +0.116 |
comment | +0.115 |
annis | +0.115 |
rank | +0.114 |
Neg logit contributions | |
estial | -0.179 |
ergic | -0.177 |
alog | -0.169 |
ysis | -0.165 |
anchester | -0.165 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
estial | +0.011 |
ergic | +0.011 |
alog | +0.010 |
ysis | +0.010 |
anchester | +0.010 |
Neg logit contributions | |
KEN | -0.013 |
annis | -0.012 |
biased | -0.012 |
comment | -0.012 |
rank | -0.012 |
Token | eless |
Token ID | 5321 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
estial | +0.260 |
ergic | +0.256 |
alog | +0.237 |
ysis | +0.231 |
anchester | +0.230 |
Neg logit contributions | |
KEN | -0.399 |
biased | -0.379 |
annis | -0.378 |
comment | -0.376 |
rank | -0.375 |
Token | ness |
Token ID | 1108 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
estial | +1.475 |
ergic | +1.474 |
alog | +1.402 |
ysis | +1.365 |
anchester | +1.363 |
Neg logit contributions | |
KEN | -1.076 |
annis | -0.996 |
biased | -0.994 |
comment | -0.980 |
rank | -0.978 |
Token | : |
Token ID | 25 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
KEN | +0.360 |
biased | +0.334 |
annis | +0.334 |
comment | +0.331 |
rank | +0.329 |
Neg logit contributions | |
estial | -0.524 |
ergic | -0.521 |
alog | -0.496 |
ysis | -0.486 |
anchester | -0.484 |
Token | A |
Token ID | 317 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
estial | +0.073 |
ergic | +0.072 |
alog | +0.068 |
ysis | +0.066 |
anchester | +0.066 |
Neg logit contributions | |
KEN | -0.081 |
annis | -0.076 |
biased | -0.076 |
comment | -0.076 |
rank | -0.076 |
Token | Brief |
Token ID | 22821 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
estial | +0.150 |
ergic | +0.149 |
alog | +0.140 |
anchester | +0.136 |
ysis | +0.136 |
Neg logit contributions | |
KEN | -0.170 |
annis | -0.160 |
biased | -0.159 |
comment | -0.158 |
rank | -0.158 |
Token | Collection |
Token ID | 12251 |
Feature activation | -9.85e-02 |
Pos logit contributions | |
estial | +0.083 |
ergic | +0.082 |
alog | +0.077 |
ysis | +0.075 |
anchester | +0.075 |
Neg logit contributions | |
KEN | -0.084 |
annis | -0.078 |
biased | -0.078 |
comment | -0.078 |
rank | -0.078 |
Token | 100 |
Token ID | 3064 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
estial | +0.090 |
ergic | +0.089 |
alog | +0.086 |
ysis | +0.084 |
anchester | +0.084 |
Neg logit contributions | |
KEN | -0.043 |
annis | -0.039 |
biased | -0.039 |
comment | -0.039 |
rank | -0.038 |
Token | ] |
Token ID | 60 |
Feature activation | +1.01e-03 |
Pos logit contributions | |
KEN | +0.044 |
biased | +0.041 |
annis | +0.041 |
comment | +0.041 |
rank | +0.041 |
Neg logit contributions | |
estial | -0.055 |
ergic | -0.055 |
alog | -0.052 |
anchester | -0.051 |
ysis | -0.051 |
Token | and |
Token ID | 290 |
Feature activation | +3.64e-02 |
Pos logit contributions | |
KEN | +0.002 |
annis | +0.002 |
biased | +0.002 |
comment | +0.002 |
rank | +0.002 |
Neg logit contributions | |
estial | -0.002 |
ergic | -0.002 |
alog | -0.002 |
anchester | -0.002 |
ysis | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +4.50e-03 |
Pos logit contributions | |
KEN | +0.082 |
annis | +0.077 |
biased | +0.077 |
comment | +0.076 |
rank | +0.076 |
Neg logit contributions | |
estial | -0.083 |
ergic | -0.083 |
alog | -0.078 |
anchester | -0.076 |
ysis | -0.076 |
Token | Associated |
Token ID | 10575 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
KEN | +0.011 |
annis | +0.010 |
biased | +0.010 |
comment | +0.010 |
rank | +0.010 |
Neg logit contributions | |
estial | -0.010 |
ergic | -0.010 |
alog | -0.009 |
ysis | -0.009 |
anchester | -0.009 |
Token | Press |
Token ID | 4332 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
ergic | +0.262 |
estial | +0.261 |
alog | +0.243 |
ysis | +0.231 |
opsis | +0.230 |
Neg logit contributions | |
KEN | -0.427 |
annis | -0.407 |
biased | -0.405 |
queue | -0.400 |
comment | -0.400 |
Token | .[ |
Token ID | 3693 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
estial | +1.305 |
ergic | +1.297 |
alog | +1.229 |
ysis | +1.196 |
anchester | +1.189 |
Neg logit contributions | |
KEN | -1.237 |
annis | -1.158 |
biased | -1.152 |
comment | -1.143 |
queue | -1.136 |
Token | 101 |
Token ID | 8784 |
Feature activation | -8.13e-03 |
Pos logit contributions | |
estial | +0.110 |
ergic | +0.109 |
alog | +0.103 |
anchester | +0.100 |
ysis | +0.100 |
Neg logit contributions | |
KEN | -0.109 |
annis | -0.102 |
biased | -0.102 |
comment | -0.102 |
rank | -0.101 |
Token | ] |
Token ID | 60 |
Feature activation | +7.81e-02 |
Pos logit contributions | |
estial | +0.021 |
ergic | +0.020 |
alog | +0.019 |
anchester | +0.019 |
ysis | +0.019 |
Neg logit contributions | |
KEN | -0.016 |
biased | -0.015 |
comment | -0.015 |
annis | -0.015 |
rank | -0.015 |
Token | In |
Token ID | 554 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
KEN | +0.192 |
annis | +0.181 |
biased | +0.181 |
comment | +0.180 |
rank | +0.179 |
Neg logit contributions | |
estial | -0.163 |
ergic | -0.162 |
alog | -0.152 |
anchester | -0.148 |
ysis | -0.147 |
Token | its |
Token ID | 663 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
KEN | +0.058 |
annis | +0.055 |
biased | +0.055 |
comment | +0.054 |
rank | +0.054 |
Neg logit contributions | |
estial | -0.059 |
ergic | -0.059 |
alog | -0.056 |
ysis | -0.054 |
anchester | -0.054 |
Token | at |
Token ID | 265 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
KEN | +0.135 |
biased | +0.124 |
annis | +0.124 |
suspic | +0.123 |
200000 | +0.122 |
Neg logit contributions | |
ergic | -0.138 |
estial | -0.137 |
alog | -0.132 |
opsis | -0.125 |
ysis | -0.125 |
Token | otic |
Token ID | 6210 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
ergic | +0.545 |
estial | +0.541 |
alog | +0.517 |
ysis | +0.507 |
opsis | +0.504 |
Neg logit contributions | |
KEN | -0.358 |
comment | -0.320 |
biased | -0.320 |
rank | -0.318 |
annis | -0.316 |
Token | plugs |
Token ID | 37008 |
Feature activation | -5.05e-02 |
Pos logit contributions | |
ergic | +0.189 |
estial | +0.182 |
alog | +0.173 |
ysis | +0.166 |
opsis | +0.161 |
Neg logit contributions | |
KEN | -0.353 |
annis | -0.336 |
biased | -0.335 |
comment | -0.334 |
rank | -0.334 |
Token | , |
Token ID | 11 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
ergic | +0.131 |
estial | +0.128 |
alog | +0.124 |
ysis | +0.120 |
opsis | +0.119 |
Neg logit contributions | |
KEN | -0.098 |
suspic | -0.094 |
biased | -0.093 |
annis | -0.092 |
rank | -0.090 |
Token | mim |
Token ID | 17007 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
KEN | +0.035 |
rank | +0.033 |
comment | +0.033 |
biased | +0.033 |
annis | +0.033 |
Neg logit contributions | |
ergic | -0.034 |
estial | -0.033 |
alog | -0.032 |
ysis | -0.030 |
anchester | -0.030 |
Token | icking |
Token ID | 7958 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
KEN | +0.112 |
biased | +0.104 |
rank | +0.104 |
annis | +0.103 |
comment | +0.103 |
Neg logit contributions | |
ergic | -0.145 |
estial | -0.144 |
alog | -0.137 |
ysis | -0.134 |
anchester | -0.133 |
Token | the |
Token ID | 262 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
ergic | +1.044 |
estial | +1.022 |
alog | +0.980 |
ysis | +0.937 |
opsis | +0.927 |
Neg logit contributions | |
KEN | -1.473 |
annis | -1.407 |
biased | -1.407 |
suspic | -1.388 |
queue | -1.377 |
Token | sp |
Token ID | 599 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
ergic | +0.069 |
estial | +0.069 |
alog | +0.066 |
ysis | +0.064 |
opsis | +0.064 |
Neg logit contributions | |
KEN | -0.060 |
biased | -0.055 |
annis | -0.055 |
comment | -0.055 |
rank | -0.054 |
Token | ines |
Token ID | 1127 |
Feature activation | +9.59e-02 |
Pos logit contributions | |
KEN | +0.028 |
biased | +0.024 |
suspic | +0.023 |
comment | +0.023 |
queue | +0.023 |
Neg logit contributions | |
ergic | -0.072 |
estial | -0.071 |
alog | -0.069 |
ysis | -0.068 |
opsis | -0.067 |
Token | on |
Token ID | 319 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
KEN | +0.212 |
biased | +0.199 |
annis | +0.198 |
comment | +0.195 |
rank | +0.194 |
Neg logit contributions | |
ergic | -0.224 |
estial | -0.222 |
alog | -0.211 |
ysis | -0.205 |
opsis | -0.201 |
Token | a |
Token ID | 257 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
KEN | +0.041 |
annis | +0.039 |
biased | +0.039 |
comment | +0.038 |
rank | +0.038 |
Neg logit contributions | |
ergic | -0.037 |
estial | -0.037 |
alog | -0.035 |
ysis | -0.034 |
opsis | -0.033 |
Token | top |
Token ID | 1353 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
KEN | +0.113 |
annis | +0.106 |
biased | +0.106 |
comment | +0.105 |
rank | +0.105 |
Neg logit contributions | |
estial | -0.121 |
ergic | -0.121 |
alog | -0.114 |
ysis | -0.111 |
anchester | -0.111 |
Token | manager |
Token ID | 4706 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
estial | +0.238 |
ergic | +0.237 |
alog | +0.224 |
ysis | +0.218 |
anchester | +0.217 |
Neg logit contributions | |
KEN | -0.236 |
biased | -0.222 |
annis | -0.222 |
comment | -0.220 |
rank | -0.218 |
Token | in |
Token ID | 287 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
estial | +0.093 |
ergic | +0.092 |
alog | +0.087 |
ysis | +0.086 |
anchester | +0.085 |
Neg logit contributions | |
KEN | -0.066 |
annis | -0.061 |
biased | -0.061 |
rank | -0.060 |
comment | -0.060 |
Token | Kol |
Token ID | 25910 |
Feature activation | +6.03e-02 |
Pos logit contributions | |
estial | +0.083 |
ergic | +0.083 |
alog | +0.077 |
anchester | +0.076 |
ysis | +0.075 |
Neg logit contributions | |
KEN | -0.091 |
annis | -0.086 |
biased | -0.085 |
comment | -0.085 |
rank | -0.085 |
Token | omo |
Token ID | 17902 |
Feature activation | -7.57e-02 |
Pos logit contributions | |
KEN | +0.137 |
annis | +0.130 |
biased | +0.129 |
rank | +0.128 |
comment | +0.128 |
Neg logit contributions | |
estial | -0.135 |
ergic | -0.135 |
alog | -0.127 |
anchester | -0.124 |
ysis | -0.124 |
Token | isky |
Token ID | 34041 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
ergic | +0.091 |
estial | +0.089 |
alog | +0.082 |
ysis | +0.078 |
issance | +0.075 |
Neg logit contributions | |
KEN | -0.254 |
comment | -0.242 |
biased | -0.241 |
200000 | -0.240 |
annis | -0.240 |
Token | � |
Token ID | 447 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
estial | +1.397 |
ergic | +1.394 |
alog | +1.320 |
ysis | +1.291 |
anchester | +1.287 |
Neg logit contributions | |
KEN | -1.128 |
biased | -1.051 |
annis | -1.047 |
comment | -1.041 |
rank | -1.035 |
Token | � |
Token ID | 247 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
estial | +0.030 |
ergic | +0.030 |
alog | +0.027 |
anchester | +0.026 |
ysis | +0.026 |
Neg logit contributions | |
KEN | -0.055 |
annis | -0.052 |
comment | -0.052 |
biased | -0.052 |
rank | -0.052 |
Token | s |
Token ID | 82 |
Feature activation | -4.19e-02 |
Pos logit contributions | |
estial | +0.078 |
ergic | +0.078 |
alog | +0.074 |
anchester | +0.072 |
ysis | +0.072 |
Neg logit contributions | |
KEN | -0.061 |
annis | -0.057 |
biased | -0.057 |
comment | -0.056 |
rank | -0.056 |
Token | refinery |
Token ID | 44133 |
Feature activation | +8.75e-02 |
Pos logit contributions | |
estial | +0.094 |
ergic | +0.094 |
alog | +0.088 |
ysis | +0.086 |
anchester | +0.086 |
Neg logit contributions | |
KEN | -0.096 |
annis | -0.090 |
biased | -0.090 |
comment | -0.089 |
rank | -0.089 |
Token | business |
Token ID | 1597 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
KEN | +0.173 |
annis | +0.160 |
biased | +0.159 |
comment | +0.159 |
rank | +0.158 |
Neg logit contributions | |
estial | -0.225 |
ergic | -0.224 |
alog | -0.213 |
anchester | -0.208 |
ysis | -0.207 |
Token | from |
Token ID | 422 |
Feature activation | +4.52e-03 |
Pos logit contributions | |
KEN | +0.024 |
annis | +0.022 |
biased | +0.022 |
comment | +0.022 |
rank | +0.022 |
Neg logit contributions | |
estial | -0.033 |
ergic | -0.033 |
alog | -0.031 |
ysis | -0.031 |
anchester | -0.031 |
Token | I |
Token ID | 314 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
KEN | +0.010 |
annis | +0.010 |
biased | +0.010 |
comment | +0.010 |
rank | +0.010 |
Neg logit contributions | |
estial | -0.010 |
ergic | -0.010 |
alog | -0.009 |
anchester | -0.009 |
ysis | -0.009 |
Token | hor |
Token ID | 17899 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
KEN | +0.039 |
annis | +0.036 |
biased | +0.036 |
comment | +0.036 |
rank | +0.036 |
Neg logit contributions | |
estial | -0.058 |
ergic | -0.057 |
alog | -0.055 |
ysis | -0.054 |
anchester | -0.053 |
Token | Kol |
Token ID | 25910 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
estial | +0.226 |
ergic | +0.225 |
alog | +0.210 |
anchester | +0.205 |
ysis | +0.205 |
Neg logit contributions | |
KEN | -0.251 |
annis | -0.237 |
biased | -0.235 |
comment | -0.234 |
rank | -0.234 |
Token | omo |
Token ID | 17902 |
Feature activation | -5.36e-02 |
Pos logit contributions | |
KEN | +0.059 |
annis | +0.056 |
biased | +0.055 |
rank | +0.055 |
comment | +0.055 |
Neg logit contributions | |
estial | -0.059 |
ergic | -0.059 |
alog | -0.056 |
anchester | -0.054 |
ysis | -0.054 |
Token | isky |
Token ID | 34041 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
estial | +0.127 |
ergic | +0.127 |
alog | +0.120 |
ysis | +0.116 |
anchester | +0.116 |
Neg logit contributions | |
KEN | -0.117 |
annis | -0.109 |
biased | -0.109 |
comment | -0.108 |
rank | -0.108 |
Token | 's |
Token ID | 338 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
ergic | +1.435 |
estial | +1.434 |
alog | +1.365 |
ysis | +1.333 |
anchester | +1.325 |
Neg logit contributions | |
KEN | -1.079 |
biased | -1.007 |
comment | -0.996 |
annis | -0.992 |
rank | -0.980 |
Token | Priv |
Token ID | 9243 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
estial | +0.040 |
ergic | +0.040 |
alog | +0.037 |
ysis | +0.036 |
anchester | +0.036 |
Neg logit contributions | |
KEN | -0.042 |
annis | -0.039 |
biased | -0.039 |
comment | -0.039 |
rank | -0.039 |
Token | at |
Token ID | 265 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
KEN | +0.029 |
annis | +0.027 |
biased | +0.027 |
comment | +0.027 |
rank | +0.027 |
Neg logit contributions | |
estial | -0.035 |
ergic | -0.035 |
alog | -0.033 |
anchester | -0.032 |
ysis | -0.032 |
Token | bank |
Token ID | 17796 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
estial | +0.546 |
ergic | +0.543 |
alog | +0.511 |
anchester | +0.500 |
ysis | +0.498 |
Neg logit contributions | |
KEN | -0.530 |
annis | -0.498 |
biased | -0.495 |
comment | -0.493 |
rank | -0.492 |
Token | . |
Token ID | 13 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
KEN | +0.385 |
annis | +0.358 |
biased | +0.356 |
comment | +0.354 |
rank | +0.353 |
Neg logit contributions | |
estial | -0.499 |
ergic | -0.497 |
alog | -0.472 |
anchester | -0.461 |
ysis | -0.460 |
Token | � |
Token ID | 247 |
Feature activation | -4.35e-02 |
Pos logit contributions | |
KEN | +0.073 |
annis | +0.070 |
biased | +0.070 |
comment | +0.069 |
rank | +0.069 |
Neg logit contributions | |
estial | -0.030 |
ergic | -0.030 |
alog | -0.027 |
ysis | -0.026 |
anchester | -0.025 |
Token | s |
Token ID | 82 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
estial | +0.100 |
ergic | +0.100 |
alog | +0.094 |
ysis | +0.091 |
anchester | +0.091 |
Neg logit contributions | |
KEN | -0.098 |
annis | -0.092 |
biased | -0.092 |
comment | -0.091 |
rank | -0.091 |
Token | also |
Token ID | 635 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
estial | +0.044 |
ergic | +0.044 |
alog | +0.042 |
ysis | +0.041 |
anchester | +0.041 |
Neg logit contributions | |
KEN | -0.034 |
annis | -0.031 |
biased | -0.031 |
comment | -0.031 |
rank | -0.031 |
Token | deeply |
Token ID | 7744 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
KEN | +0.044 |
annis | +0.041 |
biased | +0.041 |
comment | +0.041 |
rank | +0.041 |
Neg logit contributions | |
estial | -0.057 |
ergic | -0.057 |
alog | -0.054 |
ysis | -0.053 |
anchester | -0.053 |
Token | melanch |
Token ID | 40853 |
Feature activation | +4.94e-03 |
Pos logit contributions | |
KEN | +0.045 |
annis | +0.042 |
biased | +0.041 |
comment | +0.041 |
rank | +0.041 |
Neg logit contributions | |
estial | -0.063 |
ergic | -0.063 |
alog | -0.059 |
anchester | -0.058 |
ysis | -0.058 |
Token | olic |
Token ID | 4160 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
KEN | +0.016 |
comment | +0.015 |
biased | +0.015 |
annis | +0.015 |
rank | +0.015 |
Neg logit contributions | |
estial | -0.007 |
ergic | -0.006 |
alog | -0.006 |
anchester | -0.006 |
ysis | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +3.07e-03 |
Pos logit contributions | |
estial | +1.494 |
ergic | +1.491 |
alog | +1.419 |
ysis | +1.387 |
anchester | +1.387 |
Neg logit contributions | |
KEN | -1.019 |
annis | -0.939 |
biased | -0.936 |
comment | -0.926 |
rank | -0.925 |
Token | That |
Token ID | 1320 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
KEN | +0.007 |
annis | +0.007 |
biased | +0.007 |
comment | +0.007 |
rank | +0.007 |
Neg logit contributions | |
estial | -0.007 |
ergic | -0.007 |
alog | -0.006 |
anchester | -0.006 |
ysis | -0.006 |
Token | � |
Token ID | 447 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
KEN | +0.098 |
annis | +0.091 |
biased | +0.091 |
comment | +0.091 |
rank | +0.090 |
Neg logit contributions | |
estial | -0.111 |
ergic | -0.111 |
alog | -0.105 |
ysis | -0.102 |
anchester | -0.102 |
Token | � |
Token ID | 247 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
KEN | +0.090 |
annis | +0.087 |
biased | +0.087 |
comment | +0.086 |
rank | +0.085 |
Neg logit contributions | |
estial | -0.036 |
ergic | -0.036 |
alog | -0.033 |
ysis | -0.031 |
anchester | -0.031 |
Token | s |
Token ID | 82 |
Feature activation | +5.98e-02 |
Pos logit contributions | |
estial | +0.117 |
ergic | +0.116 |
alog | +0.110 |
ysis | +0.107 |
anchester | +0.107 |
Neg logit contributions | |
KEN | -0.109 |
annis | -0.102 |
biased | -0.102 |
comment | -0.101 |
rank | -0.101 |
Token | in |
Token ID | 287 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
estial | +0.037 |
ergic | +0.037 |
alog | +0.035 |
ysis | +0.035 |
anchester | +0.035 |
Neg logit contributions | |
KEN | -0.025 |
annis | -0.023 |
biased | -0.023 |
comment | -0.023 |
rank | -0.023 |
Token | modern |
Token ID | 3660 |
Feature activation | +5.87e-02 |
Pos logit contributions | |
estial | +0.061 |
ergic | +0.060 |
alog | +0.057 |
ysis | +0.056 |
anchester | +0.055 |
Neg logit contributions | |
KEN | -0.060 |
comment | -0.056 |
biased | -0.056 |
annis | -0.056 |
rank | -0.056 |
Token | times |
Token ID | 1661 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
KEN | +0.146 |
biased | +0.138 |
annis | +0.137 |
comment | +0.137 |
rank | +0.136 |
Neg logit contributions | |
estial | -0.121 |
ergic | -0.120 |
alog | -0.112 |
anchester | -0.109 |
ysis | -0.109 |
Token | . |
Token ID | 13 |
Feature activation | -4.98e-03 |
Pos logit contributions | |
KEN | +0.087 |
annis | +0.081 |
biased | +0.081 |
comment | +0.080 |
rank | +0.080 |
Neg logit contributions | |
estial | -0.130 |
ergic | -0.129 |
alog | -0.123 |
ysis | -0.120 |
anchester | -0.120 |
Token | Symb |
Token ID | 41327 |
Feature activation | -6.20e-02 |
Pos logit contributions | |
estial | +0.011 |
ergic | +0.011 |
alog | +0.010 |
anchester | +0.010 |
ysis | +0.010 |
Neg logit contributions | |
KEN | -0.011 |
annis | -0.011 |
biased | -0.011 |
comment | -0.011 |
rank | -0.011 |
Token | olic |
Token ID | 4160 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
estial | +0.120 |
ergic | +0.120 |
alog | +0.111 |
anchester | +0.108 |
ysis | +0.107 |
Neg logit contributions | |
KEN | -0.160 |
annis | -0.153 |
biased | -0.152 |
comment | -0.151 |
rank | -0.151 |
Token | names |
Token ID | 3891 |
Feature activation | -7.94e-02 |
Pos logit contributions | |
estial | +1.205 |
ergic | +1.199 |
alog | +1.130 |
ysis | +1.096 |
anchester | +1.093 |
Neg logit contributions | |
KEN | -1.299 |
annis | -1.220 |
biased | -1.219 |
comment | -1.209 |
rank | -1.202 |
Token | that |
Token ID | 326 |
Feature activation | +3.85e-04 |
Pos logit contributions | |
estial | +0.200 |
ergic | +0.199 |
alog | +0.189 |
ysis | +0.184 |
anchester | +0.184 |
Neg logit contributions | |
KEN | -0.161 |
annis | -0.150 |
biased | -0.149 |
comment | -0.149 |
rank | -0.148 |
Token | express |
Token ID | 4911 |
Feature activation | +9.05e-02 |
Pos logit contributions | |
KEN | +0.001 |
annis | +0.001 |
biased | +0.001 |
comment | +0.001 |
rank | +0.001 |
Neg logit contributions | |
estial | -0.001 |
ergic | -0.001 |
alog | -0.001 |
ysis | -0.001 |
anchester | -0.001 |
Token | frustration |
Token ID | 14285 |
Feature activation | -5.27e-02 |
Pos logit contributions | |
KEN | +0.191 |
annis | +0.178 |
biased | +0.178 |
comment | +0.177 |
rank | +0.177 |
Neg logit contributions | |
estial | -0.220 |
ergic | -0.218 |
alog | -0.207 |
anchester | -0.202 |
ysis | -0.202 |
Token | can |
Token ID | 460 |
Feature activation | +3.83e-04 |
Pos logit contributions | |
estial | +0.140 |
ergic | +0.139 |
alog | +0.132 |
ysis | +0.129 |
anchester | +0.129 |
Neg logit contributions | |
KEN | -0.100 |
annis | -0.092 |
biased | -0.092 |
comment | -0.092 |
rank | -0.091 |
Token | Russian |
Token ID | 3394 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
estial | +0.038 |
ergic | +0.038 |
alog | +0.035 |
anchester | +0.034 |
ysis | +0.034 |
Neg logit contributions | |
KEN | -0.046 |
annis | -0.043 |
biased | -0.043 |
comment | -0.043 |
rank | -0.043 |
Token | Mars |
Token ID | 8706 |
Feature activation | -6.63e-02 |
Pos logit contributions | |
estial | +0.256 |
ergic | +0.254 |
alog | +0.239 |
anchester | +0.232 |
ysis | +0.231 |
Neg logit contributions | |
KEN | -0.296 |
annis | -0.279 |
biased | -0.278 |
comment | -0.277 |
rank | -0.276 |
Token | probe |
Token ID | 12774 |
Feature activation | -5.63e-02 |
Pos logit contributions | |
estial | +0.148 |
ergic | +0.147 |
alog | +0.139 |
ysis | +0.135 |
anchester | +0.135 |
Neg logit contributions | |
KEN | -0.153 |
annis | -0.143 |
biased | -0.143 |
comment | -0.142 |
rank | -0.142 |
Token | , |
Token ID | 11 |
Feature activation | -3.75e-03 |
Pos logit contributions | |
estial | +0.140 |
ergic | +0.139 |
alog | +0.132 |
anchester | +0.129 |
ysis | +0.129 |
Neg logit contributions | |
KEN | -0.116 |
annis | -0.108 |
biased | -0.108 |
comment | -0.107 |
rank | -0.107 |
Token | Ph |
Token ID | 1380 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
estial | +0.009 |
ergic | +0.009 |
alog | +0.008 |
anchester | +0.008 |
ysis | +0.008 |
Neg logit contributions | |
KEN | -0.008 |
biased | -0.008 |
annis | -0.008 |
comment | -0.008 |
rank | -0.008 |
Token | obos |
Token ID | 49878 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
estial | +0.108 |
ergic | +0.106 |
alog | +0.088 |
anchester | +0.081 |
ysis | +0.080 |
Neg logit contributions | |
KEN | -0.512 |
annis | -0.493 |
biased | -0.492 |
comment | -0.491 |
rank | -0.491 |
Token | - |
Token ID | 12 |
Feature activation | -9.18e-02 |
Pos logit contributions | |
estial | +1.432 |
ergic | +1.426 |
alog | +1.354 |
ysis | +1.331 |
opsis | +1.312 |
Neg logit contributions | |
KEN | -1.049 |
annis | -0.968 |
biased | -0.967 |
comment | -0.958 |
rank | -0.951 |
Token | Gr |
Token ID | 8642 |
Feature activation | +1.75e-03 |
Pos logit contributions | |
estial | +0.259 |
ergic | +0.257 |
alog | +0.245 |
ysis | +0.240 |
anchester | +0.240 |
Neg logit contributions | |
KEN | -0.159 |
annis | -0.146 |
biased | -0.145 |
comment | -0.144 |
rank | -0.143 |
Token | unt |
Token ID | 2797 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
KEN | +0.003 |
biased | +0.002 |
200000 | +0.002 |
comment | +0.002 |
queue | +0.002 |
Neg logit contributions | |
estial | -0.005 |
ergic | -0.005 |
alog | -0.005 |
ysis | -0.005 |
anchester | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
estial | +0.483 |
ergic | +0.480 |
alog | +0.457 |
ysis | +0.447 |
anchester | +0.446 |
Neg logit contributions | |
KEN | -0.342 |
annis | -0.316 |
biased | -0.316 |
comment | -0.313 |
rank | -0.312 |
Token | last |
Token ID | 938 |
Feature activation | -4.72e-02 |
Pos logit contributions | |
KEN | +0.038 |
annis | +0.035 |
biased | +0.035 |
comment | +0.035 |
rank | +0.035 |
Neg logit contributions | |
estial | -0.055 |
ergic | -0.055 |
alog | -0.052 |
anchester | -0.051 |
ysis | -0.051 |
Token | Though |
Token ID | 7486 |
Feature activation | +5.63e-03 |
Pos logit contributions | |
KEN | +0.017 |
annis | +0.016 |
biased | +0.016 |
comment | +0.016 |
rank | +0.016 |
Neg logit contributions | |
estial | -0.016 |
ergic | -0.016 |
alog | -0.015 |
ysis | -0.015 |
anchester | -0.015 |
Token | pension |
Token ID | 13553 |
Feature activation | +7.97e-02 |
Pos logit contributions | |
KEN | +0.012 |
annis | +0.011 |
biased | +0.011 |
comment | +0.011 |
rank | +0.011 |
Neg logit contributions | |
estial | -0.014 |
ergic | -0.014 |
alog | -0.013 |
anchester | -0.013 |
ysis | -0.013 |
Token | critics |
Token ID | 9188 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
KEN | +0.170 |
annis | +0.159 |
biased | +0.159 |
comment | +0.158 |
rank | +0.157 |
Neg logit contributions | |
estial | -0.192 |
ergic | -0.191 |
alog | -0.181 |
ysis | -0.176 |
anchester | -0.176 |
Token | often |
Token ID | 1690 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
KEN | +0.050 |
annis | +0.046 |
biased | +0.046 |
comment | +0.045 |
rank | +0.045 |
Neg logit contributions | |
estial | -0.077 |
ergic | -0.076 |
alog | -0.073 |
ysis | -0.071 |
anchester | -0.071 |
Token | mislead |
Token ID | 42154 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
KEN | +0.022 |
annis | +0.021 |
biased | +0.021 |
comment | +0.020 |
rank | +0.020 |
Neg logit contributions | |
estial | -0.034 |
ergic | -0.034 |
alog | -0.032 |
ysis | -0.032 |
anchester | -0.032 |
Token | ingly |
Token ID | 4420 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
estial | +0.596 |
ergic | +0.593 |
alog | +0.560 |
ysis | +0.546 |
anchester | +0.546 |
Neg logit contributions | |
KEN | -0.534 |
annis | -0.499 |
biased | -0.498 |
comment | -0.495 |
rank | -0.493 |
Token | suggest |
Token ID | 1950 |
Feature activation | -9.64e-03 |
Pos logit contributions | |
ergic | +1.466 |
estial | +1.465 |
alog | +1.399 |
anchester | +1.357 |
ysis | +1.355 |
Neg logit contributions | |
KEN | -1.003 |
biased | -0.919 |
annis | -0.913 |
comment | -0.901 |
200000 | -0.897 |
Token | that |
Token ID | 326 |
Feature activation | -5.80e-02 |
Pos logit contributions | |
estial | +0.025 |
ergic | +0.025 |
alog | +0.023 |
anchester | +0.023 |
ysis | +0.023 |
Neg logit contributions | |
KEN | -0.019 |
annis | -0.018 |
biased | -0.018 |
comment | -0.017 |
rank | -0.017 |
Token | teachers |
Token ID | 7799 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
estial | +0.141 |
ergic | +0.140 |
alog | +0.133 |
ysis | +0.129 |
anchester | +0.129 |
Neg logit contributions | |
KEN | -0.123 |
annis | -0.114 |
biased | -0.114 |
comment | -0.113 |
rank | -0.113 |
Token | who |
Token ID | 508 |
Feature activation | +7.91e-02 |
Pos logit contributions | |
KEN | +0.056 |
annis | +0.052 |
biased | +0.052 |
comment | +0.052 |
rank | +0.051 |
Neg logit contributions | |
estial | -0.073 |
ergic | -0.073 |
alog | -0.069 |
ysis | -0.067 |
anchester | -0.067 |
Token | work |
Token ID | 670 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
KEN | +0.148 |
annis | +0.136 |
biased | +0.136 |
comment | +0.135 |
rank | +0.134 |
Neg logit contributions | |
estial | -0.212 |
ergic | -0.211 |
alog | -0.201 |
ysis | -0.196 |
anchester | -0.196 |
Token | also |
Token ID | 635 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
estial | +0.019 |
ergic | +0.019 |
alog | +0.018 |
anchester | +0.017 |
ysis | +0.017 |
Neg logit contributions | |
KEN | -0.019 |
annis | -0.018 |
biased | -0.018 |
comment | -0.018 |
rank | -0.018 |
Token | controlled |
Token ID | 6856 |
Feature activation | +1.58e-03 |
Pos logit contributions | |
estial | +0.040 |
ergic | +0.040 |
alog | +0.038 |
anchester | +0.037 |
ysis | +0.037 |
Neg logit contributions | |
KEN | -0.043 |
annis | -0.041 |
biased | -0.040 |
comment | -0.040 |
rank | -0.040 |
Token | by |
Token ID | 416 |
Feature activation | +2.07e-03 |
Pos logit contributions | |
KEN | +0.003 |
biased | +0.003 |
comment | +0.003 |
annis | +0.003 |
rank | +0.003 |
Neg logit contributions | |
estial | -0.004 |
ergic | -0.004 |
alog | -0.004 |
anchester | -0.004 |
issance | -0.004 |
Token | Kol |
Token ID | 25910 |
Feature activation | +5.71e-04 |
Pos logit contributions | |
KEN | +0.005 |
annis | +0.005 |
biased | +0.005 |
comment | +0.005 |
rank | +0.005 |
Neg logit contributions | |
estial | -0.005 |
ergic | -0.005 |
alog | -0.004 |
anchester | -0.004 |
ysis | -0.004 |
Token | omo |
Token ID | 17902 |
Feature activation | -4.90e-02 |
Pos logit contributions | |
KEN | +0.001 |
biased | +0.001 |
comment | +0.001 |
annis | +0.001 |
200000 | +0.001 |
Neg logit contributions | |
ergic | -0.001 |
estial | -0.001 |
alog | -0.001 |
ysis | -0.001 |
opsis | -0.001 |
Token | isky |
Token ID | 34041 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
ergic | +0.059 |
estial | +0.057 |
alog | +0.052 |
ysis | +0.050 |
issance | +0.048 |
Neg logit contributions | |
KEN | -0.166 |
comment | -0.157 |
biased | -0.157 |
annis | -0.156 |
200000 | -0.156 |
Token | . |
Token ID | 13 |
Feature activation | +7.88e-03 |
Pos logit contributions | |
estial | +1.461 |
ergic | +1.457 |
alog | +1.387 |
ysis | +1.356 |
anchester | +1.354 |
Neg logit contributions | |
KEN | -1.000 |
biased | -0.925 |
annis | -0.924 |
comment | -0.916 |
rank | -0.909 |
Token |
|
Token ID | 198 |
Feature activation | +9.29e-03 |
Pos logit contributions | |
KEN | +0.019 |
annis | +0.018 |
biased | +0.018 |
comment | +0.018 |
rank | +0.018 |
Neg logit contributions | |
estial | -0.016 |
ergic | -0.016 |
alog | -0.015 |
anchester | -0.015 |
ysis | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
KEN | +0.022 |
annis | +0.021 |
biased | +0.021 |
suspic | +0.021 |
rank | +0.020 |
Neg logit contributions | |
ergic | -0.020 |
estial | -0.020 |
alog | -0.019 |
ysis | -0.018 |
opsis | -0.018 |
Token | I |
Token ID | 40 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
KEN | +0.034 |
annis | +0.031 |
biased | +0.031 |
comment | +0.031 |
rank | +0.031 |
Neg logit contributions | |
estial | -0.056 |
ergic | -0.056 |
alog | -0.054 |
ysis | -0.052 |
anchester | -0.052 |
Token | van |
Token ID | 10438 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
estial | +0.126 |
ergic | +0.125 |
alog | +0.117 |
anchester | +0.114 |
ysis | +0.114 |
Neg logit contributions | |
KEN | -0.155 |
annis | -0.146 |
biased | -0.145 |
comment | -0.145 |
rank | -0.144 |
Token | the |
Token ID | 262 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
estial | +0.022 |
ergic | +0.022 |
alog | +0.020 |
ysis | +0.020 |
anchester | +0.020 |
Neg logit contributions | |
KEN | -0.021 |
biased | -0.020 |
comment | -0.020 |
annis | -0.020 |
rank | -0.020 |
Token | stage |
Token ID | 3800 |
Feature activation | +8.18e-02 |
Pos logit contributions | |
estial | +0.027 |
ergic | +0.027 |
alog | +0.025 |
anchester | +0.025 |
ysis | +0.024 |
Neg logit contributions | |
KEN | -0.024 |
annis | -0.023 |
biased | -0.023 |
comment | -0.023 |
rank | -0.022 |
Token | at |
Token ID | 379 |
Feature activation | -4.96e-02 |
Pos logit contributions | |
KEN | +0.147 |
annis | +0.136 |
biased | +0.136 |
comment | +0.135 |
rank | +0.134 |
Neg logit contributions | |
estial | -0.224 |
ergic | -0.223 |
alog | -0.213 |
anchester | -0.208 |
ysis | -0.208 |
Token | the |
Token ID | 262 |
Feature activation | +2.09e-03 |
Pos logit contributions | |
estial | +0.114 |
ergic | +0.113 |
alog | +0.107 |
anchester | +0.104 |
ysis | +0.104 |
Neg logit contributions | |
KEN | -0.112 |
annis | -0.105 |
biased | -0.104 |
comment | -0.104 |
rank | -0.104 |
Token | Dol |
Token ID | 25143 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
KEN | +0.004 |
annis | +0.004 |
biased | +0.004 |
comment | +0.004 |
rank | +0.004 |
Neg logit contributions | |
estial | -0.005 |
ergic | -0.005 |
alog | -0.005 |
ysis | -0.005 |
anchester | -0.005 |
Token | by |
Token ID | 1525 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
KEN | +0.052 |
comment | +0.050 |
annis | +0.050 |
biased | +0.049 |
rank | +0.049 |
Neg logit contributions | |
estial | -0.036 |
ergic | -0.036 |
alog | -0.033 |
anchester | -0.032 |
ysis | -0.032 |
Token | Theatre |
Token ID | 15752 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
estial | +1.026 |
ergic | +1.012 |
alog | +0.941 |
anchester | +0.919 |
ysis | +0.914 |
Neg logit contributions | |
KEN | -1.432 |
biased | -1.355 |
annis | -1.352 |
comment | -1.349 |
rank | -1.347 |
Token | . |
Token ID | 13 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
estial | +0.448 |
ergic | +0.446 |
alog | +0.425 |
anchester | +0.416 |
ysis | +0.415 |
Neg logit contributions | |
KEN | -0.302 |
annis | -0.278 |
biased | -0.278 |
comment | -0.276 |
rank | -0.274 |
Token |
|
Token ID | 198 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
KEN | +0.036 |
annis | +0.033 |
comment | +0.033 |
biased | +0.033 |
rank | +0.033 |
Neg logit contributions | |
estial | -0.037 |
ergic | -0.037 |
alog | -0.035 |
ysis | -0.034 |
anchester | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | +4.77e-03 |
Pos logit contributions | |
ergic | +0.023 |
estial | +0.022 |
alog | +0.021 |
ysis | +0.020 |
opsis | +0.020 |
Neg logit contributions | |
KEN | -0.025 |
annis | -0.024 |
biased | -0.024 |
suspic | -0.023 |
rank | -0.023 |
Token | C |
Token ID | 34 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
KEN | +0.009 |
annis | +0.009 |
biased | +0.009 |
comment | +0.009 |
rank | +0.009 |
Neg logit contributions | |
estial | -0.012 |
ergic | -0.012 |
alog | -0.012 |
ysis | -0.011 |
anchester | -0.011 |
Token | at |
Token ID | 265 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
KEN | +0.117 |
annis | +0.111 |
biased | +0.110 |
comment | +0.109 |
rank | +0.109 |
Neg logit contributions | |
estial | -0.152 |
ergic | -0.151 |
alog | -0.143 |
ysis | -0.140 |
anchester | -0.140 |
Token | otic |
Token ID | 6210 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
estial | +0.490 |
ergic | +0.486 |
alog | +0.462 |
anchester | +0.452 |
ysis | +0.448 |
Neg logit contributions | |
KEN | -0.416 |
annis | -0.391 |
biased | -0.389 |
comment | -0.385 |
rank | -0.384 |
Token | plugs |
Token ID | 37008 |
Feature activation | -5.15e-02 |
Pos logit contributions | |
estial | +0.281 |
ergic | +0.280 |
alog | +0.264 |
ysis | +0.257 |
anchester | +0.257 |
Neg logit contributions | |
KEN | -0.275 |
annis | -0.258 |
biased | -0.257 |
comment | -0.256 |
rank | -0.255 |
Token | , |
Token ID | 11 |
Feature activation | -3.73e-03 |
Pos logit contributions | |
estial | +0.134 |
ergic | +0.134 |
alog | +0.127 |
ysis | +0.125 |
anchester | +0.124 |
Neg logit contributions | |
KEN | -0.100 |
biased | -0.092 |
annis | -0.092 |
comment | -0.091 |
rank | -0.091 |
Token | mim |
Token ID | 17007 |
Feature activation | +5.96e-02 |
Pos logit contributions | |
estial | +0.010 |
ergic | +0.010 |
alog | +0.009 |
ysis | +0.009 |
anchester | +0.009 |
Neg logit contributions | |
KEN | -0.007 |
annis | -0.007 |
biased | -0.007 |
comment | -0.007 |
rank | -0.007 |
Token | icking |
Token ID | 7958 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
KEN | +0.109 |
annis | +0.103 |
biased | +0.102 |
comment | +0.102 |
rank | +0.101 |
Neg logit contributions | |
estial | -0.160 |
ergic | -0.158 |
alog | -0.150 |
anchester | -0.148 |
ysis | -0.147 |
Token | the |
Token ID | 262 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
estial | +1.243 |
ergic | +1.241 |
alog | +1.170 |
ysis | +1.140 |
anchester | +1.136 |
Neg logit contributions | |
KEN | -1.208 |
annis | -1.131 |
biased | -1.128 |
comment | -1.122 |
rank | -1.118 |
Token | sp |
Token ID | 599 |
Feature activation | +6.19e-03 |
Pos logit contributions | |
estial | +0.097 |
ergic | +0.096 |
alog | +0.091 |
anchester | +0.089 |
ysis | +0.089 |
Neg logit contributions | |
KEN | -0.085 |
annis | -0.079 |
biased | -0.079 |
comment | -0.079 |
rank | -0.078 |
Token | ines |
Token ID | 1127 |
Feature activation | +8.93e-02 |
Pos logit contributions | |
KEN | +0.009 |
annis | +0.008 |
biased | +0.008 |
comment | +0.008 |
rank | +0.008 |
Neg logit contributions | |
estial | -0.019 |
ergic | -0.019 |
alog | -0.018 |
anchester | -0.018 |
ysis | -0.018 |
Token | on |
Token ID | 319 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
KEN | +0.165 |
annis | +0.153 |
biased | +0.153 |
comment | +0.151 |
rank | +0.151 |
Neg logit contributions | |
estial | -0.240 |
ergic | -0.238 |
alog | -0.227 |
anchester | -0.223 |
ysis | -0.222 |
Token | a |
Token ID | 257 |
Feature activation | -2.42e-03 |
Pos logit contributions | |
KEN | +0.032 |
biased | +0.030 |
annis | +0.030 |
comment | +0.030 |
rank | +0.030 |
Neg logit contributions | |
estial | -0.031 |
ergic | -0.031 |
alog | -0.029 |
anchester | -0.028 |
ysis | -0.028 |
Token | ( |
Token ID | 357 |
Feature activation | -8.49e-03 |
Pos logit contributions | |
KEN | +0.008 |
annis | +0.007 |
biased | +0.007 |
comment | +0.007 |
rank | +0.007 |
Neg logit contributions | |
estial | -0.011 |
ergic | -0.011 |
alog | -0.010 |
anchester | -0.010 |
ysis | -0.010 |
Token | such |
Token ID | 10508 |
Feature activation | -9.18e-02 |
Pos logit contributions | |
estial | +0.023 |
ergic | +0.023 |
alog | +0.021 |
ysis | +0.021 |
anchester | +0.021 |
Neg logit contributions | |
KEN | -0.016 |
annis | -0.015 |
biased | -0.015 |
comment | -0.015 |
rank | -0.014 |
Token | as |
Token ID | 355 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
ergic | +0.248 |
estial | +0.247 |
alog | +0.237 |
ysis | +0.231 |
opsis | +0.227 |
Neg logit contributions | |
KEN | -0.169 |
biased | -0.156 |
annis | -0.156 |
rank | -0.154 |
comment | -0.152 |
Token | a |
Token ID | 257 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
KEN | +0.059 |
annis | +0.055 |
biased | +0.055 |
comment | +0.055 |
rank | +0.055 |
Neg logit contributions | |
estial | -0.056 |
ergic | -0.056 |
alog | -0.052 |
anchester | -0.051 |
ysis | -0.051 |
Token | pac |
Token ID | 23503 |
Feature activation | +1.30e-03 |
Pos logit contributions | |
KEN | +0.023 |
annis | +0.022 |
biased | +0.022 |
comment | +0.022 |
rank | +0.021 |
Neg logit contributions | |
estial | -0.026 |
ergic | -0.026 |
alog | -0.024 |
ysis | -0.024 |
anchester | -0.024 |
Token | emaker |
Token ID | 32174 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
KEN | +0.004 |
annis | +0.004 |
biased | +0.004 |
comment | +0.004 |
rank | +0.004 |
Neg logit contributions | |
estial | -0.002 |
ergic | -0.002 |
alog | -0.001 |
anchester | -0.001 |
ysis | -0.001 |
Token | ), |
Token ID | 828 |
Feature activation | +7.99e-03 |
Pos logit contributions | |
ergic | +1.317 |
estial | +1.306 |
alog | +1.245 |
ysis | +1.225 |
anchester | +1.203 |
Neg logit contributions | |
KEN | -1.102 |
annis | -1.025 |
biased | -1.021 |
comment | -1.011 |
rank | -1.007 |
Token | but |
Token ID | 475 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
KEN | +0.018 |
annis | +0.017 |
biased | +0.017 |
comment | +0.017 |
rank | +0.017 |
Neg logit contributions | |
estial | -0.018 |
ergic | -0.018 |
alog | -0.017 |
ysis | -0.017 |
anchester | -0.017 |
Token | these |
Token ID | 777 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
ergic | +0.067 |
estial | +0.067 |
alog | +0.063 |
ysis | +0.061 |
anchester | +0.061 |
Neg logit contributions | |
KEN | -0.067 |
annis | -0.063 |
biased | -0.063 |
comment | -0.062 |
rank | -0.062 |
Token | are |
Token ID | 389 |
Feature activation | -3.58e-02 |
Pos logit contributions | |
estial | +0.058 |
ergic | +0.058 |
alog | +0.055 |
ysis | +0.053 |
anchester | +0.053 |
Neg logit contributions | |
KEN | -0.052 |
annis | -0.048 |
biased | -0.048 |
comment | -0.048 |
rank | -0.048 |
Token | exhaust |
Token ID | 12142 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
estial | +0.093 |
ergic | +0.093 |
alog | +0.088 |
ysis | +0.086 |
anchester | +0.086 |
Neg logit contributions | |
KEN | -0.069 |
annis | -0.064 |
biased | -0.064 |
comment | -0.064 |
rank | -0.063 |
Token | Add |
Token ID | 3060 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
KEN | +0.193 |
queue | +0.179 |
comment | +0.177 |
rank | +0.176 |
annis | +0.174 |
Neg logit contributions | |
estial | -0.207 |
ergic | -0.206 |
alog | -0.193 |
ysis | -0.191 |
anchester | -0.190 |
Token | a |
Token ID | 257 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
estial | +0.386 |
ergic | +0.384 |
alog | +0.362 |
anchester | +0.352 |
ysis | +0.352 |
Neg logit contributions | |
KEN | -0.362 |
annis | -0.339 |
comment | -0.338 |
biased | -0.337 |
rank | -0.335 |
Token | comment |
Token ID | 2912 |
Feature activation | +6.86e-02 |
Pos logit contributions | |
KEN | +0.028 |
annis | +0.027 |
biased | +0.027 |
rank | +0.026 |
200000 | +0.026 |
Neg logit contributions | |
estial | -0.036 |
ergic | -0.036 |
alog | -0.035 |
anchester | -0.034 |
ysis | -0.034 |
Token | here |
Token ID | 994 |
Feature activation | +4.89e-02 |
Pos logit contributions | |
KEN | +0.142 |
biased | +0.132 |
annis | +0.132 |
comment | +0.130 |
rank | +0.130 |
Neg logit contributions | |
estial | -0.170 |
ergic | -0.170 |
alog | -0.161 |
ysis | -0.158 |
anchester | -0.158 |
Token | Ver |
Token ID | 4643 |
Feature activation | +2.95e-03 |
Pos logit contributions | |
KEN | +0.131 |
comment | +0.125 |
annis | +0.125 |
biased | +0.123 |
queue | +0.123 |
Neg logit contributions | |
estial | -0.091 |
ergic | -0.091 |
alog | -0.084 |
ysis | -0.081 |
anchester | -0.080 |
Token | ification |
Token ID | 2649 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
KEN | +0.008 |
annis | +0.008 |
biased | +0.008 |
rank | +0.008 |
200000 | +0.008 |
Neg logit contributions | |
estial | -0.005 |
ergic | -0.005 |
alog | -0.005 |
ysis | -0.005 |
anchester | -0.005 |
Token | Send |
Token ID | 16290 |
Feature activation | -5.80e-02 |
Pos logit contributions | |
KEN | +1.032 |
annis | +0.974 |
biased | +0.972 |
comment | +0.968 |
rank | +0.965 |
Neg logit contributions | |
estial | -0.780 |
ergic | -0.775 |
alog | -0.723 |
anchester | -0.699 |
ysis | -0.699 |
Token | Email |
Token ID | 9570 |
Feature activation | -7.00e-03 |
Pos logit contributions | |
estial | +0.105 |
ergic | +0.104 |
alog | +0.096 |
ysis | +0.093 |
anchester | +0.093 |
Neg logit contributions | |
KEN | -0.159 |
annis | -0.151 |
biased | -0.151 |
comment | -0.150 |
rank | -0.149 |
Token | Cancel |
Token ID | 27910 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
estial | +0.013 |
ergic | +0.013 |
alog | +0.012 |
ysis | +0.012 |
anchester | +0.012 |
Neg logit contributions | |
KEN | -0.019 |
annis | -0.018 |
biased | -0.018 |
comment | -0.018 |
rank | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +1.67e-03 |
Pos logit contributions | |
estial | +0.307 |
ergic | +0.305 |
alog | +0.288 |
ysis | +0.281 |
anchester | +0.281 |
Neg logit contributions | |
KEN | -0.292 |
annis | -0.272 |
biased | -0.272 |
comment | -0.271 |
rank | -0.270 |
Token |
|
Token ID | 198 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
KEN | +0.004 |
annis | +0.004 |
biased | +0.004 |
suspic | +0.004 |
rank | +0.004 |
Neg logit contributions | |
ergic | -0.004 |
estial | -0.004 |
alog | -0.003 |
ysis | -0.003 |
opsis | -0.003 |
Token | b |
Token ID | 65 |
Feature activation | -6.51e-02 |
Pos logit contributions | |
estial | +0.049 |
ergic | +0.048 |
alog | +0.045 |
ysis | +0.044 |
anchester | +0.044 |
Neg logit contributions | |
KEN | -0.060 |
annis | -0.057 |
comment | -0.057 |
biased | -0.057 |
rank | -0.056 |
Token | res |
Token ID | 411 |
Feature activation | -7.06e-02 |
Pos logit contributions | |
estial | +0.145 |
ergic | +0.144 |
alog | +0.135 |
anchester | +0.133 |
ysis | +0.132 |
Neg logit contributions | |
KEN | -0.149 |
annis | -0.141 |
comment | -0.141 |
rank | -0.141 |
biased | -0.140 |
Token | , |
Token ID | 11 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
estial | +0.169 |
ergic | +0.168 |
alog | +0.159 |
ysis | +0.155 |
anchester | +0.154 |
Neg logit contributions | |
KEN | -0.152 |
biased | -0.142 |
annis | -0.141 |
comment | -0.140 |
rank | -0.140 |
Token | les |
Token ID | 10287 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
estial | +0.080 |
ergic | +0.080 |
alog | +0.075 |
ysis | +0.073 |
anchester | +0.073 |
Neg logit contributions | |
KEN | -0.080 |
biased | -0.075 |
annis | -0.075 |
comment | -0.074 |
rank | -0.074 |
Token | Offic |
Token ID | 6328 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
KEN | +0.049 |
annis | +0.046 |
biased | +0.046 |
comment | +0.045 |
rank | +0.045 |
Neg logit contributions | |
estial | -0.050 |
ergic | -0.049 |
alog | -0.047 |
anchester | -0.045 |
ysis | -0.045 |
Token | iers |
Token ID | 3183 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
estial | +0.109 |
ergic | +0.109 |
alog | +0.103 |
anchester | +0.100 |
ysis | +0.100 |
Neg logit contributions | |
KEN | -0.101 |
annis | -0.094 |
biased | -0.094 |
comment | -0.094 |
rank | -0.093 |
Token | et |
Token ID | 2123 |
Feature activation | -7.83e-02 |
Pos logit contributions | |
KEN | +0.850 |
annis | +0.801 |
biased | +0.796 |
comment | +0.794 |
rank | +0.791 |
Neg logit contributions | |
estial | -0.797 |
ergic | -0.793 |
alog | -0.745 |
anchester | -0.727 |
ysis | -0.726 |
Token | les |
Token ID | 10287 |
Feature activation | +7.78e-02 |
Pos logit contributions | |
estial | +0.171 |
ergic | +0.170 |
alog | +0.160 |
anchester | +0.155 |
ysis | +0.155 |
Neg logit contributions | |
KEN | -0.185 |
annis | -0.174 |
biased | -0.174 |
comment | -0.173 |
rank | -0.172 |
Token | F |
Token ID | 376 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
KEN | +0.184 |
annis | +0.173 |
biased | +0.173 |
comment | +0.172 |
rank | +0.171 |
Neg logit contributions | |
estial | -0.169 |
ergic | -0.168 |
alog | -0.158 |
anchester | -0.154 |
ysis | -0.154 |
Token | ond |
Token ID | 623 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
KEN | +0.072 |
annis | +0.067 |
comment | +0.066 |
rank | +0.066 |
biased | +0.066 |
Neg logit contributions | |
estial | -0.110 |
ergic | -0.110 |
alog | -0.105 |
anchester | -0.102 |
ysis | -0.102 |
Token | ateurs |
Token ID | 45211 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
KEN | +0.052 |
annis | +0.050 |
biased | +0.049 |
comment | +0.049 |
rank | +0.049 |
Neg logit contributions | |
estial | -0.046 |
ergic | -0.046 |
alog | -0.043 |
ysis | -0.042 |
anchester | -0.042 |
Token | One |
Token ID | 1881 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
KEN | +0.130 |
annis | +0.121 |
biased | +0.121 |
comment | +0.120 |
rank | +0.120 |
Neg logit contributions | |
estial | -0.125 |
ergic | -0.125 |
alog | -0.118 |
anchester | -0.115 |
ysis | -0.114 |
Token | race |
Token ID | 3234 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
estial | +0.225 |
ergic | +0.224 |
alog | +0.210 |
anchester | +0.204 |
ysis | +0.204 |
Neg logit contributions | |
KEN | -0.253 |
annis | -0.238 |
biased | -0.237 |
comment | -0.237 |
rank | -0.236 |
Token | track |
Token ID | 2610 |
Feature activation | +5.18e-02 |
Pos logit contributions | |
KEN | +0.304 |
annis | +0.282 |
biased | +0.281 |
comment | +0.280 |
rank | +0.278 |
Neg logit contributions | |
estial | -0.409 |
ergic | -0.407 |
alog | -0.386 |
anchester | -0.378 |
ysis | -0.378 |
Token | in |
Token ID | 287 |
Feature activation | -4.15e-02 |
Pos logit contributions | |
KEN | +0.101 |
annis | +0.094 |
biased | +0.094 |
comment | +0.093 |
rank | +0.093 |
Neg logit contributions | |
estial | -0.134 |
ergic | -0.134 |
alog | -0.127 |
anchester | -0.124 |
ysis | -0.124 |
Token | Mon |
Token ID | 2892 |
Feature activation | +6.97e-02 |
Pos logit contributions | |
estial | +0.083 |
ergic | +0.082 |
alog | +0.076 |
ysis | +0.074 |
anchester | +0.074 |
Neg logit contributions | |
KEN | -0.106 |
annis | -0.100 |
biased | -0.100 |
comment | -0.100 |
rank | -0.099 |
Token | za |
Token ID | 4496 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
KEN | +0.162 |
annis | +0.153 |
biased | +0.153 |
comment | +0.151 |
rank | +0.151 |
Neg logit contributions | |
estial | -0.155 |
ergic | -0.153 |
alog | -0.143 |
anchester | -0.141 |
ysis | -0.140 |
Token | , |
Token ID | 11 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
KEN | +0.665 |
annis | +0.610 |
biased | +0.607 |
comment | +0.604 |
rank | +0.600 |
Neg logit contributions | |
estial | -1.047 |
ergic | -1.043 |
alog | -0.992 |
anchester | -0.972 |
ysis | -0.970 |
Token | Italy |
Token ID | 8031 |
Feature activation | +6.66e-02 |
Pos logit contributions | |
estial | +0.043 |
ergic | +0.042 |
alog | +0.040 |
anchester | +0.039 |
ysis | +0.039 |
Neg logit contributions | |
KEN | -0.049 |
annis | -0.046 |
biased | -0.046 |
comment | -0.046 |
rank | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
KEN | +0.124 |
annis | +0.114 |
biased | +0.114 |
comment | +0.113 |
rank | +0.112 |
Neg logit contributions | |
estial | -0.179 |
ergic | -0.179 |
alog | -0.170 |
ysis | -0.166 |
anchester | -0.166 |
Token | The |
Token ID | 383 |
Feature activation | -5.11e-02 |
Pos logit contributions | |
estial | +0.081 |
ergic | +0.081 |
alog | +0.076 |
anchester | +0.074 |
ysis | +0.074 |
Neg logit contributions | |
KEN | -0.080 |
annis | -0.074 |
comment | -0.074 |
biased | -0.074 |
rank | -0.073 |
Token | runners |
Token ID | 19323 |
Feature activation | +7.89e-02 |
Pos logit contributions | |
estial | +0.135 |
ergic | +0.134 |
alog | +0.128 |
anchester | +0.125 |
ysis | +0.125 |
Neg logit contributions | |
KEN | -0.098 |
annis | -0.090 |
biased | -0.090 |
comment | -0.090 |
rank | -0.089 |
Token |
|
Token ID | 198 |
Feature activation | -3.60e-03 |
Pos logit contributions | |
estial | +0.003 |
ergic | +0.003 |
alog | +0.003 |
anchester | +0.003 |
ysis | +0.003 |
Neg logit contributions | |
KEN | -0.003 |
annis | -0.003 |
biased | -0.003 |
comment | -0.003 |
rank | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
ergic | +0.008 |
estial | +0.008 |
alog | +0.007 |
ysis | +0.007 |
opsis | +0.007 |
Neg logit contributions | |
KEN | -0.009 |
annis | -0.008 |
biased | -0.008 |
suspic | -0.008 |
rank | -0.008 |
Token | Ford |
Token ID | 37308 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
KEN | +0.018 |
annis | +0.017 |
biased | +0.016 |
rank | +0.016 |
comment | +0.016 |
Neg logit contributions | |
estial | -0.033 |
ergic | -0.033 |
alog | -0.031 |
ysis | -0.031 |
anchester | -0.031 |
Token | was |
Token ID | 373 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
estial | +0.035 |
ergic | +0.035 |
alog | +0.033 |
ysis | +0.033 |
anchester | +0.032 |
Neg logit contributions | |
KEN | -0.033 |
annis | -0.031 |
biased | -0.031 |
comment | -0.031 |
rank | -0.030 |
Token | ind |
Token ID | 773 |
Feature activation | -4.18e-03 |
Pos logit contributions | |
estial | +0.081 |
ergic | +0.081 |
alog | +0.076 |
ysis | +0.074 |
anchester | +0.074 |
Neg logit contributions | |
KEN | -0.067 |
annis | -0.062 |
biased | -0.062 |
comment | -0.062 |
rank | -0.062 |
Token | ignant |
Token ID | 25114 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
estial | +0.011 |
ergic | +0.011 |
alog | +0.011 |
anchester | +0.010 |
ysis | +0.010 |
Neg logit contributions | |
KEN | -0.008 |
annis | -0.007 |
biased | -0.007 |
comment | -0.007 |
rank | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
KEN | +0.583 |
biased | +0.537 |
annis | +0.537 |
comment | +0.535 |
rank | +0.530 |
Neg logit contributions | |
estial | -0.867 |
ergic | -0.862 |
alog | -0.822 |
anchester | -0.804 |
ysis | -0.803 |
Token | He |
Token ID | 679 |
Feature activation | -8.28e-02 |
Pos logit contributions | |
KEN | +0.104 |
annis | +0.098 |
biased | +0.098 |
comment | +0.097 |
rank | +0.097 |
Neg logit contributions | |
estial | -0.094 |
ergic | -0.094 |
alog | -0.088 |
anchester | -0.086 |
ysis | -0.086 |
Token | denied |
Token ID | 6699 |
Feature activation | -8.31e-02 |
Pos logit contributions | |
estial | +0.181 |
ergic | +0.180 |
alog | +0.169 |
ysis | +0.164 |
anchester | +0.164 |
Neg logit contributions | |
KEN | -0.196 |
annis | -0.184 |
biased | -0.183 |
comment | -0.182 |
rank | -0.182 |
Token | the |
Token ID | 262 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
ergic | +0.207 |
estial | +0.207 |
alog | +0.196 |
ysis | +0.192 |
anchester | +0.191 |
Neg logit contributions | |
KEN | -0.170 |
annis | -0.158 |
biased | -0.158 |
comment | -0.156 |
rank | -0.156 |
Token | allegation |
Token ID | 24389 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
estial | +0.070 |
ergic | +0.070 |
alog | +0.066 |
ysis | +0.065 |
anchester | +0.064 |
Neg logit contributions | |
KEN | -0.062 |
annis | -0.058 |
biased | -0.058 |
comment | -0.057 |
rank | -0.057 |
Token | When |
Token ID | 1649 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
estial | +0.019 |
ergic | +0.019 |
alog | +0.018 |
ysis | +0.017 |
anchester | +0.017 |
Neg logit contributions | |
KEN | -0.021 |
annis | -0.020 |
biased | -0.020 |
comment | -0.020 |
rank | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -7.44e-02 |
Pos logit contributions | |
KEN | +0.070 |
annis | +0.065 |
biased | +0.065 |
comment | +0.064 |
rank | +0.064 |
Neg logit contributions | |
estial | -0.079 |
ergic | -0.079 |
alog | -0.074 |
ysis | -0.073 |
anchester | -0.073 |
Token | thanks |
Token ID | 5176 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
estial | +0.200 |
ergic | +0.199 |
alog | +0.190 |
ysis | +0.186 |
anchester | +0.186 |
Neg logit contributions | |
KEN | -0.138 |
annis | -0.127 |
biased | -0.127 |
comment | -0.126 |
rank | -0.125 |
Token | to |
Token ID | 284 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
estial | +0.059 |
ergic | +0.058 |
alog | +0.056 |
ysis | +0.055 |
anchester | +0.055 |
Neg logit contributions | |
KEN | -0.028 |
biased | -0.026 |
annis | -0.025 |
comment | -0.025 |
rank | -0.025 |
Token | insol |
Token ID | 35831 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
estial | +0.461 |
ergic | +0.459 |
alog | +0.433 |
anchester | +0.422 |
ysis | +0.422 |
Neg logit contributions | |
KEN | -0.414 |
annis | -0.388 |
biased | -0.388 |
comment | -0.384 |
rank | -0.383 |
Token | vent |
Token ID | 1151 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
KEN | +0.169 |
biased | +0.152 |
annis | +0.152 |
comment | +0.150 |
queue | +0.148 |
Neg logit contributions | |
estial | -0.396 |
ergic | -0.395 |
alog | -0.379 |
anchester | -0.373 |
ysis | -0.372 |
Token | government |
Token ID | 1230 |
Feature activation | +7.25e-02 |
Pos logit contributions | |
KEN | +0.771 |
annis | +0.718 |
biased | +0.717 |
comment | +0.712 |
rank | +0.708 |
Neg logit contributions | |
estial | -0.946 |
ergic | -0.943 |
alog | -0.891 |
anchester | -0.872 |
ysis | -0.869 |
Token | regulations |
Token ID | 6647 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
KEN | +0.140 |
annis | +0.130 |
biased | +0.130 |
comment | +0.129 |
rank | +0.128 |
Neg logit contributions | |
estial | -0.189 |
ergic | -0.188 |
alog | -0.179 |
anchester | -0.175 |
ysis | -0.174 |
Token | but |
Token ID | 475 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
KEN | +0.258 |
annis | +0.239 |
biased | +0.238 |
comment | +0.234 |
rank | +0.233 |
Neg logit contributions | |
estial | -0.434 |
ergic | -0.431 |
alog | -0.411 |
ysis | -0.403 |
anchester | -0.402 |
Token | endless |
Token ID | 13079 |
Feature activation | +6.39e-02 |
Pos logit contributions | |
estial | +0.029 |
ergic | +0.029 |
alog | +0.028 |
anchester | +0.027 |
ysis | +0.027 |
Neg logit contributions | |
KEN | -0.023 |
annis | -0.021 |
biased | -0.021 |
comment | -0.021 |
rank | -0.021 |
Token | government |
Token ID | 1230 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
KEN | +0.122 |
annis | +0.113 |
biased | +0.112 |
comment | +0.112 |
rank | +0.111 |
Neg logit contributions | |
estial | -0.169 |
ergic | -0.168 |
alog | -0.160 |
ysis | -0.156 |
anchester | -0.156 |
Token | accents |
Token ID | 39271 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
estial | +0.123 |
ergic | +0.123 |
alog | +0.115 |
anchester | +0.112 |
ysis | +0.112 |
Neg logit contributions | |
KEN | -0.131 |
annis | -0.123 |
comment | -0.123 |
biased | -0.123 |
rank | -0.122 |
Token | playing |
Token ID | 2712 |
Feature activation | -9.37e-02 |
Pos logit contributions | |
estial | +0.027 |
ergic | +0.027 |
alog | +0.025 |
anchester | +0.025 |
ysis | +0.025 |
Neg logit contributions | |
KEN | -0.019 |
annis | -0.017 |
biased | -0.017 |
comment | -0.017 |
rank | -0.017 |
Token | in |
Token ID | 287 |
Feature activation | -6.95e-02 |
Pos logit contributions | |
estial | +0.245 |
ergic | +0.244 |
alog | +0.232 |
ysis | +0.226 |
anchester | +0.226 |
Neg logit contributions | |
KEN | -0.181 |
annis | -0.167 |
biased | -0.167 |
comment | -0.166 |
rank | -0.165 |
Token | the |
Token ID | 262 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
estial | +0.162 |
ergic | +0.160 |
alog | +0.151 |
ysis | +0.148 |
anchester | +0.148 |
Neg logit contributions | |
KEN | -0.154 |
annis | -0.144 |
biased | -0.144 |
comment | -0.143 |
rank | -0.143 |
Token | background |
Token ID | 4469 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
estial | +0.061 |
ergic | +0.060 |
alog | +0.057 |
anchester | +0.056 |
ysis | +0.056 |
Neg logit contributions | |
KEN | -0.040 |
annis | -0.037 |
biased | -0.037 |
comment | -0.036 |
rank | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +4.19e-03 |
Pos logit contributions | |
estial | +0.062 |
ergic | +0.061 |
alog | +0.058 |
anchester | +0.057 |
ysis | +0.057 |
Neg logit contributions | |
KEN | -0.042 |
annis | -0.039 |
biased | -0.039 |
comment | -0.038 |
rank | -0.038 |
Token | Survivor |
Token ID | 23740 |
Feature activation | -7.97e-02 |
Pos logit contributions | |
KEN | +0.008 |
annis | +0.007 |
biased | +0.007 |
comment | +0.007 |
rank | +0.007 |
Neg logit contributions | |
estial | -0.011 |
ergic | -0.011 |
alog | -0.011 |
anchester | -0.010 |
ysis | -0.010 |
Token | memor |
Token ID | 16181 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
estial | +0.189 |
ergic | +0.188 |
alog | +0.178 |
ysis | +0.173 |
anchester | +0.173 |
Neg logit contributions | |
KEN | -0.173 |
annis | -0.162 |
biased | -0.161 |
comment | -0.160 |
rank | -0.160 |
Token | abilia |
Token ID | 48249 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
KEN | +0.352 |
comment | +0.340 |
annis | +0.340 |
biased | +0.340 |
queue | +0.337 |
Neg logit contributions | |
estial | -0.139 |
ergic | -0.135 |
anchester | -0.119 |
alog | -0.118 |
ysis | -0.116 |
Token | throughout |
Token ID | 3690 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
estial | +0.646 |
ergic | +0.643 |
alog | +0.611 |
anchester | +0.600 |
ysis | +0.599 |
Neg logit contributions | |
KEN | -0.423 |
annis | -0.391 |
biased | -0.389 |
comment | -0.387 |
rank | -0.385 |
Token | the |
Token ID | 262 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
KEN | +0.039 |
annis | +0.037 |
comment | +0.037 |
biased | +0.036 |
rank | +0.036 |
Neg logit contributions | |
estial | -0.047 |
ergic | -0.046 |
alog | -0.044 |
anchester | -0.043 |
ysis | -0.043 |
Token | content |
Token ID | 2695 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
KEN | +0.107 |
biased | +0.099 |
annis | +0.099 |
comment | +0.099 |
rank | +0.098 |
Neg logit contributions | |
estial | -0.133 |
ergic | -0.132 |
alog | -0.125 |
anchester | -0.122 |
ysis | -0.122 |
Token | in |
Token ID | 287 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
KEN | +0.202 |
annis | +0.187 |
biased | +0.187 |
comment | +0.186 |
rank | +0.185 |
Neg logit contributions | |
estial | -0.288 |
ergic | -0.286 |
alog | -0.272 |
anchester | -0.266 |
ysis | -0.266 |
Token | ppm |
Token ID | 39719 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
KEN | +0.101 |
biased | +0.095 |
comment | +0.094 |
annis | +0.094 |
rank | +0.094 |
Neg logit contributions | |
estial | -0.095 |
ergic | -0.095 |
alog | -0.089 |
anchester | -0.086 |
ysis | -0.086 |
Token | measured |
Token ID | 8630 |
Feature activation | +9.81e-02 |
Pos logit contributions | |
estial | +0.180 |
ergic | +0.179 |
alog | +0.170 |
anchester | +0.166 |
ysis | +0.166 |
Neg logit contributions | |
KEN | -0.150 |
annis | -0.139 |
biased | -0.139 |
comment | -0.138 |
rank | -0.137 |
Token | at |
Token ID | 379 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
KEN | +0.192 |
annis | +0.178 |
biased | +0.178 |
comment | +0.177 |
rank | +0.176 |
Neg logit contributions | |
estial | -0.254 |
ergic | -0.252 |
alog | -0.239 |
anchester | -0.234 |
ysis | -0.234 |
Token | M |
Token ID | 337 |
Feature activation | +8.38e-02 |
Pos logit contributions | |
KEN | +0.100 |
biased | +0.094 |
annis | +0.093 |
rank | +0.093 |
comment | +0.093 |
Neg logit contributions | |
ergic | -0.090 |
estial | -0.090 |
alog | -0.084 |
anchester | -0.081 |
ysis | -0.081 |
Token | auna |
Token ID | 32837 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
KEN | +0.195 |
annis | +0.183 |
biased | +0.183 |
comment | +0.182 |
rank | +0.181 |
Neg logit contributions | |
estial | -0.186 |
ergic | -0.185 |
alog | -0.174 |
ysis | -0.169 |
anchester | -0.169 |
Token | Lo |
Token ID | 6706 |
Feature activation | +5.64e-02 |
Pos logit contributions | |
KEN | +0.347 |
biased | +0.330 |
annis | +0.328 |
comment | +0.327 |
queue | +0.325 |
Neg logit contributions | |
estial | -0.228 |
ergic | -0.228 |
alog | -0.214 |
ysis | -0.204 |
anchester | -0.204 |
Token | a |
Token ID | 64 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
KEN | +0.130 |
biased | +0.121 |
comment | +0.120 |
annis | +0.120 |
rank | +0.120 |
Neg logit contributions | |
estial | -0.127 |
ergic | -0.127 |
alog | -0.120 |
ysis | -0.115 |
anchester | -0.115 |
Token | observ |
Token ID | 3799 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
KEN | +0.214 |
annis | +0.199 |
biased | +0.198 |
comment | +0.198 |
rank | +0.197 |
Neg logit contributions | |
estial | -0.260 |
ergic | -0.259 |
alog | -0.245 |
anchester | -0.240 |
ysis | -0.239 |
Token | atory |
Token ID | 2870 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
KEN | +0.266 |
comment | +0.251 |
biased | +0.251 |
annis | +0.251 |
rank | +0.251 |
Neg logit contributions | |
ergic | -0.280 |
estial | -0.278 |
alog | -0.261 |
anchester | -0.257 |
ysis | -0.255 |
Token | Scientology |
Token ID | 24990 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
estial | +0.000 |
ergic | +0.000 |
alog | +0.000 |
ysis | +0.000 |
anchester | +0.000 |
Neg logit contributions | |
KEN | -0.000 |
annis | -0.000 |
biased | -0.000 |
comment | -0.000 |
rank | -0.000 |
Token | reportedly |
Token ID | 7478 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
estial | +0.339 |
ergic | +0.336 |
alog | +0.319 |
anchester | +0.311 |
ysis | +0.310 |
Neg logit contributions | |
KEN | -0.307 |
annis | -0.287 |
biased | -0.286 |
comment | -0.285 |
rank | -0.283 |
Token | did |
Token ID | 750 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
estial | +0.273 |
ergic | +0.272 |
alog | +0.257 |
anchester | +0.251 |
ysis | +0.251 |
Neg logit contributions | |
KEN | -0.252 |
annis | -0.236 |
biased | -0.236 |
comment | -0.235 |
rank | -0.233 |
Token | when |
Token ID | 618 |
Feature activation | +7.64e-02 |
Pos logit contributions | |
KEN | +0.086 |
annis | +0.079 |
biased | +0.079 |
rank | +0.078 |
comment | +0.078 |
Neg logit contributions | |
estial | -0.130 |
ergic | -0.130 |
alog | -0.123 |
anchester | -0.121 |
ysis | -0.121 |
Token | " |
Token ID | 366 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
KEN | +0.158 |
annis | +0.147 |
biased | +0.147 |
comment | +0.146 |
rank | +0.146 |
Neg logit contributions | |
estial | -0.189 |
ergic | -0.188 |
alog | -0.178 |
ysis | -0.174 |
anchester | -0.174 |
Token | South |
Token ID | 14942 |
Feature activation | +3.76e-04 |
Pos logit contributions | |
KEN | +0.097 |
annis | +0.090 |
biased | +0.090 |
comment | +0.089 |
rank | +0.089 |
Neg logit contributions | |
estial | -0.142 |
ergic | -0.142 |
alog | -0.135 |
ysis | -0.132 |
anchester | -0.132 |
Token | Park |
Token ID | 3250 |
Feature activation | -8.82e-02 |
Pos logit contributions | |
KEN | +0.001 |
biased | +0.001 |
annis | +0.001 |
comment | +0.001 |
rank | +0.001 |
Neg logit contributions | |
estial | -0.001 |
ergic | -0.001 |
alog | -0.001 |
ysis | -0.001 |
anchester | -0.001 |
Token | " |
Token ID | 1 |
Feature activation | +6.41e-02 |
Pos logit contributions | |
estial | +0.247 |
ergic | +0.246 |
alog | +0.235 |
ysis | +0.230 |
anchester | +0.230 |
Neg logit contributions | |
KEN | -0.154 |
annis | -0.141 |
biased | -0.141 |
comment | -0.140 |
rank | -0.139 |
Token | mocked |
Token ID | 29180 |
Feature activation | -1.18e-05 |
Pos logit contributions | |
KEN | +0.136 |
annis | +0.127 |
biased | +0.126 |
comment | +0.126 |
rank | +0.125 |
Neg logit contributions | |
estial | -0.156 |
ergic | -0.155 |
alog | -0.147 |
anchester | -0.143 |
ysis | -0.143 |
Token | them |
Token ID | 606 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
estial | +0.000 |
ergic | +0.000 |
alog | +0.000 |
anchester | +0.000 |
ysis | +0.000 |
Neg logit contributions | |
KEN | -0.000 |
annis | -0.000 |
biased | -0.000 |
comment | -0.000 |
rank | -0.000 |
Token | ? |
Token ID | 30 |
Feature activation | -7.71e-02 |
Pos logit contributions | |
KEN | +0.207 |
annis | +0.190 |
biased | +0.190 |
comment | +0.188 |
rank | +0.187 |
Neg logit contributions | |
estial | -0.317 |
ergic | -0.316 |
alog | -0.301 |
ysis | -0.294 |
anchester | -0.294 |
Token | what |
Token ID | 644 |
Feature activation | +6.87e-02 |
Pos logit contributions | |
KEN | +0.101 |
annis | +0.094 |
biased | +0.094 |
comment | +0.093 |
rank | +0.093 |
Neg logit contributions | |
estial | -0.122 |
ergic | -0.121 |
alog | -0.115 |
anchester | -0.112 |
ysis | -0.112 |
Token | by |
Token ID | 416 |
Feature activation | +4.75e-02 |
Pos logit contributions | |
KEN | +0.119 |
annis | +0.109 |
biased | +0.109 |
comment | +0.108 |
rank | +0.107 |
Neg logit contributions | |
estial | -0.193 |
ergic | -0.193 |
alog | -0.184 |
ysis | -0.180 |
anchester | -0.180 |
Token | all |
Token ID | 477 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
KEN | +0.100 |
annis | +0.094 |
biased | +0.093 |
comment | +0.093 |
rank | +0.093 |
Neg logit contributions | |
estial | -0.116 |
ergic | -0.115 |
alog | -0.109 |
ysis | -0.106 |
anchester | -0.106 |
Token | rights |
Token ID | 2489 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
KEN | +0.062 |
annis | +0.057 |
biased | +0.057 |
comment | +0.056 |
rank | +0.056 |
Neg logit contributions | |
estial | -0.079 |
ergic | -0.079 |
alog | -0.075 |
anchester | -0.073 |
ysis | -0.073 |
Token | should |
Token ID | 815 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
KEN | +0.024 |
annis | +0.023 |
biased | +0.023 |
comment | +0.022 |
rank | +0.022 |
Neg logit contributions | |
estial | -0.035 |
ergic | -0.035 |
alog | -0.033 |
anchester | -0.032 |
ysis | -0.032 |
Token | be |
Token ID | 307 |
Feature activation | -5.23e-04 |
Pos logit contributions | |
estial | +0.050 |
ergic | +0.050 |
alog | +0.048 |
ysis | +0.047 |
anchester | +0.047 |
Neg logit contributions | |
KEN | -0.033 |
annis | -0.030 |
biased | -0.030 |
comment | -0.030 |
rank | -0.030 |
Token | utterly |
Token ID | 15950 |
Feature activation | -6.84e-02 |
Pos logit contributions | |
estial | +0.001 |
ergic | +0.001 |
alog | +0.001 |
ysis | +0.001 |
anchester | +0.001 |
Neg logit contributions | |
KEN | -0.001 |
annis | -0.001 |
biased | -0.001 |
comment | -0.001 |
rank | -0.001 |
Token | unacceptable |
Token ID | 18010 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
estial | +0.184 |
ergic | +0.183 |
alog | +0.175 |
ysis | +0.171 |
anchester | +0.171 |
Neg logit contributions | |
KEN | -0.127 |
annis | -0.117 |
biased | -0.117 |
comment | -0.116 |
rank | -0.115 |
Token | bears |
Token ID | 13062 |
Feature activation | -6.88e-02 |
Pos logit contributions | |
KEN | +0.040 |
annis | +0.037 |
biased | +0.037 |
comment | +0.037 |
rank | +0.037 |
Neg logit contributions | |
estial | -0.060 |
ergic | -0.060 |
alog | -0.057 |
ysis | -0.056 |
anchester | -0.056 |
Token | any |
Token ID | 597 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
estial | +0.174 |
ergic | +0.173 |
alog | +0.165 |
ysis | +0.161 |
anchester | +0.161 |
Neg logit contributions | |
KEN | -0.139 |
annis | -0.129 |
biased | -0.129 |
comment | -0.128 |
rank | -0.127 |
Token | relation |
Token ID | 8695 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
KEN | +0.069 |
annis | +0.064 |
biased | +0.064 |
comment | +0.064 |
rank | +0.063 |
Neg logit contributions | |
estial | -0.079 |
ergic | -0.079 |
alog | -0.075 |
ysis | -0.073 |
anchester | -0.073 |
Token | of |
Token ID | 286 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
KEN | +0.318 |
annis | +0.293 |
biased | +0.293 |
comment | +0.291 |
rank | +0.289 |
Neg logit contributions | |
estial | -0.456 |
ergic | -0.454 |
alog | -0.431 |
ysis | -0.422 |
anchester | -0.422 |
Token | a |
Token ID | 257 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
KEN | +0.089 |
biased | +0.083 |
annis | +0.083 |
comment | +0.082 |
rank | +0.082 |
Neg logit contributions | |
estial | -0.095 |
ergic | -0.095 |
alog | -0.089 |
ysis | -0.087 |
anchester | -0.087 |
Token | Louisville |
Token ID | 21525 |
Feature activation | -2.00e-04 |
Pos logit contributions | |
KEN | +0.066 |
annis | +0.062 |
biased | +0.062 |
comment | +0.061 |
rank | +0.061 |
Neg logit contributions | |
estial | -0.072 |
ergic | -0.071 |
alog | -0.067 |
ysis | -0.066 |
anchester | -0.065 |
Token | purge |
Token ID | 35714 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
estial | +0.000 |
ergic | +0.000 |
alog | +0.000 |
ysis | +0.000 |
anchester | +0.000 |
Neg logit contributions | |
KEN | -0.000 |
annis | -0.000 |
biased | -0.000 |
comment | -0.000 |
rank | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +9.38e-03 |
Pos logit contributions | |
estial | +0.194 |
ergic | +0.194 |
alog | +0.185 |
ysis | +0.181 |
anchester | +0.180 |
Neg logit contributions | |
KEN | -0.138 |
annis | -0.128 |
biased | -0.128 |
comment | -0.126 |
rank | -0.126 |
Token | According |
Token ID | 4784 |
Feature activation | -4.18e-03 |
Pos logit contributions | |
KEN | +0.022 |
annis | +0.021 |
biased | +0.021 |
comment | +0.021 |
rank | +0.020 |
Neg logit contributions | |
estial | -0.021 |
ergic | -0.021 |
alog | -0.019 |
anchester | -0.019 |
ysis | -0.019 |
Token | to |
Token ID | 284 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
ergic | +0.012 |
estial | +0.012 |
alog | +0.011 |
ysis | +0.011 |
opsis | +0.011 |
Neg logit contributions | |
KEN | -0.007 |
annis | -0.007 |
biased | -0.006 |
queue | -0.006 |
rank | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
KEN | +0.091 |
biased | +0.086 |
annis | +0.086 |
comment | +0.085 |
rank | +0.085 |
Neg logit contributions | |
estial | -0.087 |
ergic | -0.086 |
alog | -0.081 |
ysis | -0.079 |
anchester | -0.079 |
Token | post |
Token ID | 1281 |
Feature activation | -5.64e-03 |
Pos logit contributions | |
KEN | +0.044 |
annis | +0.041 |
biased | +0.041 |
comment | +0.041 |
rank | +0.041 |
Neg logit contributions | |
estial | -0.044 |
ergic | -0.044 |
alog | -0.042 |
ysis | -0.041 |
anchester | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
estial | +0.016 |
ergic | +0.016 |
alog | +0.015 |
ysis | +0.015 |
anchester | +0.015 |
Neg logit contributions | |
KEN | -0.010 |
annis | -0.009 |
comment | -0.009 |
biased | -0.009 |
rank | -0.009 |
Token | someone |
Token ID | 2130 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
KEN | +0.027 |
annis | +0.025 |
biased | +0.025 |
comment | +0.025 |
rank | +0.025 |
Neg logit contributions | |
estial | -0.029 |
ergic | -0.029 |
alog | -0.027 |
ysis | -0.026 |
anchester | -0.026 |
Token | - |
Token ID | 12 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
estial | +0.066 |
ergic | +0.066 |
alog | +0.062 |
anchester | +0.061 |
ysis | +0.061 |
Neg logit contributions | |
KEN | -0.053 |
annis | -0.049 |
biased | -0.049 |
comment | -0.048 |
rank | -0.048 |
Token | class |
Token ID | 4871 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
estial | +0.370 |
ergic | +0.370 |
alog | +0.356 |
ysis | +0.349 |
anchester | +0.349 |
Neg logit contributions | |
KEN | -0.122 |
annis | -0.107 |
biased | -0.105 |
comment | -0.104 |
rank | -0.102 |
Token | promotion |
Token ID | 12148 |
Feature activation | +7.24e-02 |
Pos logit contributions | |
KEN | +0.073 |
annis | +0.068 |
biased | +0.068 |
comment | +0.067 |
rank | +0.067 |
Neg logit contributions | |
estial | -0.077 |
ergic | -0.077 |
alog | -0.073 |
ysis | -0.071 |
anchester | -0.071 |
Token | of |
Token ID | 286 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
KEN | +0.133 |
annis | +0.122 |
biased | +0.122 |
comment | +0.121 |
rank | +0.121 |
Neg logit contributions | |
estial | -0.196 |
ergic | -0.196 |
alog | -0.186 |
ysis | -0.182 |
anchester | -0.182 |
Token | music |
Token ID | 2647 |
Feature activation | -9.92e-02 |
Pos logit contributions | |
KEN | +0.104 |
annis | +0.097 |
biased | +0.097 |
comment | +0.097 |
rank | +0.096 |
Neg logit contributions | |
estial | -0.113 |
ergic | -0.113 |
alog | -0.107 |
ysis | -0.104 |
anchester | -0.104 |
Token | in |
Token ID | 287 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
estial | +0.268 |
ergic | +0.267 |
alog | +0.254 |
ysis | +0.248 |
anchester | +0.248 |
Neg logit contributions | |
KEN | -0.183 |
annis | -0.169 |
biased | -0.169 |
comment | -0.167 |
rank | -0.166 |
Token | Europe |
Token ID | 2031 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
estial | +0.091 |
ergic | +0.090 |
alog | +0.085 |
ysis | +0.083 |
anchester | +0.083 |
Neg logit contributions | |
KEN | -0.093 |
annis | -0.087 |
biased | -0.087 |
comment | -0.087 |
rank | -0.086 |
Token | since |
Token ID | 1201 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
KEN | +0.072 |
annis | +0.067 |
biased | +0.066 |
comment | +0.066 |
rank | +0.066 |
Neg logit contributions | |
estial | -0.111 |
ergic | -0.111 |
alog | -0.106 |
ysis | -0.103 |
anchester | -0.103 |
Token | about |
Token ID | 546 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
KEN | +0.040 |
annis | +0.037 |
biased | +0.037 |
comment | +0.037 |
rank | +0.037 |
Neg logit contributions | |
estial | -0.037 |
ergic | -0.037 |
alog | -0.035 |
anchester | -0.034 |
ysis | -0.034 |
Token | 1830 |
Token ID | 45440 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
estial | +0.022 |
ergic | +0.022 |
alog | +0.020 |
ysis | +0.020 |
anchester | +0.020 |
Neg logit contributions | |
KEN | -0.024 |
biased | -0.022 |
annis | -0.022 |
comment | -0.022 |
rank | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +4.03e-02 |
Pos logit contributions | |
estial | +0.283 |
ergic | +0.282 |
alog | +0.269 |
ysis | +0.263 |
anchester | +0.263 |
Neg logit contributions | |
KEN | -0.189 |
annis | -0.174 |
biased | -0.174 |
comment | -0.173 |
rank | -0.172 |
Token | a |
Token ID | 257 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
KEN | +0.076 |
annis | +0.071 |
biased | +0.071 |
comment | +0.071 |
rank | +0.070 |
Neg logit contributions | |
estial | -0.087 |
ergic | -0.086 |
alog | -0.081 |
anchester | -0.080 |
ysis | -0.080 |
Token | pipeline |
Token ID | 11523 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
KEN | +0.033 |
annis | +0.031 |
biased | +0.031 |
comment | +0.030 |
rank | +0.030 |
Neg logit contributions | |
estial | -0.047 |
ergic | -0.047 |
alog | -0.044 |
ysis | -0.043 |
anchester | -0.043 |
Token | of |
Token ID | 286 |
Feature activation | +4.83e-02 |
Pos logit contributions | |
ergic | +0.056 |
estial | +0.056 |
alog | +0.053 |
ysis | +0.052 |
anchester | +0.052 |
Neg logit contributions | |
KEN | -0.039 |
annis | -0.036 |
biased | -0.035 |
comment | -0.035 |
rank | -0.035 |
Token | new |
Token ID | 649 |
Feature activation | +7.39e-02 |
Pos logit contributions | |
KEN | +0.095 |
annis | +0.088 |
biased | +0.088 |
comment | +0.087 |
rank | +0.087 |
Neg logit contributions | |
estial | -0.125 |
ergic | -0.124 |
alog | -0.118 |
ysis | -0.115 |
anchester | -0.115 |
Token | supply |
Token ID | 5127 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
KEN | +0.181 |
annis | +0.171 |
biased | +0.171 |
comment | +0.170 |
rank | +0.169 |
Neg logit contributions | |
estial | -0.154 |
ergic | -0.154 |
alog | -0.144 |
ysis | -0.140 |
anchester | -0.140 |
Token | likely |
Token ID | 1884 |
Feature activation | -4.90e-02 |
Pos logit contributions | |
KEN | +0.286 |
annis | +0.264 |
biased | +0.263 |
comment | +0.261 |
rank | +0.260 |
Neg logit contributions | |
estial | -0.408 |
ergic | -0.407 |
alog | -0.387 |
ysis | -0.378 |
anchester | -0.378 |
Token | to |
Token ID | 284 |
Feature activation | +6.54e-02 |
Pos logit contributions | |
estial | +0.143 |
ergic | +0.143 |
alog | +0.136 |
ysis | +0.133 |
anchester | +0.133 |
Neg logit contributions | |
KEN | -0.080 |
annis | -0.072 |
biased | -0.072 |
comment | -0.072 |
rank | -0.071 |
Token | flow |
Token ID | 5202 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
KEN | +0.117 |
annis | +0.108 |
biased | +0.107 |
comment | +0.106 |
rank | +0.106 |
Neg logit contributions | |
ergic | -0.180 |
estial | -0.180 |
alog | -0.172 |
ysis | -0.167 |
anchester | -0.166 |
Token | over |
Token ID | 625 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
KEN | +0.049 |
annis | +0.045 |
biased | +0.045 |
comment | +0.045 |
rank | +0.045 |
Neg logit contributions | |
estial | -0.071 |
ergic | -0.071 |
alog | -0.068 |
ysis | -0.066 |
anchester | -0.066 |
Token | time |
Token ID | 640 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
KEN | +0.070 |
biased | +0.066 |
annis | +0.066 |
comment | +0.066 |
rank | +0.065 |
Neg logit contributions | |
estial | -0.079 |
ergic | -0.079 |
alog | -0.074 |
ysis | -0.073 |
anchester | -0.072 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e-03 |
Pos logit contributions | |
estial | +0.052 |
ergic | +0.051 |
alog | +0.049 |
anchester | +0.048 |
ysis | +0.048 |
Neg logit contributions | |
KEN | -0.034 |
annis | -0.031 |
biased | -0.031 |
comment | -0.031 |
rank | -0.031 |
Token | to |
Token ID | 284 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
estial | +0.216 |
ergic | +0.215 |
alog | +0.205 |
anchester | +0.201 |
ysis | +0.201 |
Neg logit contributions | |
KEN | -0.107 |
annis | -0.097 |
biased | -0.097 |
comment | -0.096 |
rank | -0.096 |
Token | 40 |
Token ID | 2319 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
estial | +0.048 |
ergic | +0.048 |
alog | +0.046 |
ysis | +0.045 |
anchester | +0.044 |
Neg logit contributions | |
KEN | -0.045 |
annis | -0.042 |
biased | -0.042 |
comment | -0.041 |
queue | -0.041 |
Token | % |
Token ID | 4 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
estial | +0.083 |
ergic | +0.083 |
alog | +0.079 |
ysis | +0.077 |
anchester | +0.077 |
Neg logit contributions | |
KEN | -0.065 |
annis | -0.060 |
biased | -0.060 |
comment | -0.060 |
rank | -0.059 |
Token | shopping |
Token ID | 9735 |
Feature activation | -8.07e-02 |
Pos logit contributions | |
KEN | +0.023 |
annis | +0.021 |
biased | +0.021 |
comment | +0.021 |
rank | +0.021 |
Neg logit contributions | |
estial | -0.031 |
ergic | -0.031 |
alog | -0.029 |
ysis | -0.029 |
anchester | -0.029 |
Token | online |
Token ID | 2691 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
estial | +0.206 |
ergic | +0.206 |
alog | +0.197 |
ysis | +0.191 |
anchester | +0.191 |
Neg logit contributions | |
KEN | -0.160 |
annis | -0.149 |
biased | -0.148 |
comment | -0.147 |
rank | -0.145 |
Token | . |
Token ID | 13 |
Feature activation | -5.88e-02 |
Pos logit contributions | |
estial | +0.034 |
ergic | +0.034 |
alog | +0.032 |
ysis | +0.031 |
anchester | +0.031 |
Neg logit contributions | |
KEN | -0.024 |
annis | -0.022 |
biased | -0.022 |
comment | -0.022 |
rank | -0.021 |
Token | To |
Token ID | 1675 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
estial | +0.127 |
ergic | +0.127 |
alog | +0.119 |
ysis | +0.116 |
anchester | +0.115 |
Neg logit contributions | |
KEN | -0.140 |
annis | -0.132 |
biased | -0.131 |
comment | -0.130 |
rank | -0.130 |
Token | learn |
Token ID | 2193 |
Feature activation | +8.31e-03 |
Pos logit contributions | |
ergic | +0.103 |
estial | +0.102 |
alog | +0.099 |
ysis | +0.096 |
anchester | +0.095 |
Neg logit contributions | |
KEN | -0.067 |
biased | -0.063 |
annis | -0.063 |
comment | -0.061 |
rank | -0.061 |
Token | more |
Token ID | 517 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
KEN | +0.017 |
annis | +0.015 |
biased | +0.015 |
comment | +0.015 |
rank | +0.015 |
Neg logit contributions | |
estial | -0.021 |
ergic | -0.021 |
alog | -0.020 |
ysis | -0.020 |
anchester | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -4.08e-02 |
Pos logit contributions | |
estial | +0.075 |
ergic | +0.075 |
alog | +0.071 |
ysis | +0.070 |
anchester | +0.070 |
Neg logit contributions | |
KEN | -0.058 |
annis | -0.054 |
biased | -0.054 |
comment | -0.053 |
rank | -0.053 |
Token | and |
Token ID | 290 |
Feature activation | -5.51e-02 |
Pos logit contributions | |
ergic | +0.113 |
estial | +0.112 |
alog | +0.108 |
ysis | +0.105 |
anchester | +0.105 |
Neg logit contributions | |
KEN | -0.072 |
annis | -0.067 |
biased | -0.067 |
rank | -0.065 |
comment | -0.065 |
Token | 4 |
Token ID | 19 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
KEN | +0.039 |
annis | +0.036 |
biased | +0.036 |
comment | +0.035 |
rank | +0.035 |
Neg logit contributions | |
estial | -0.063 |
ergic | -0.063 |
alog | -0.060 |
ysis | -0.059 |
anchester | -0.059 |
Token | All |
Token ID | 1439 |
Feature activation | -6.01e-02 |
Pos logit contributions | |
KEN | +0.387 |
annis | +0.360 |
biased | +0.360 |
comment | +0.358 |
rank | +0.356 |
Neg logit contributions | |
estial | -0.460 |
ergic | -0.458 |
alog | -0.434 |
ysis | -0.423 |
anchester | -0.422 |
Token | Access |
Token ID | 8798 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
estial | +0.161 |
ergic | +0.159 |
alog | +0.152 |
anchester | +0.149 |
ysis | +0.149 |
Neg logit contributions | |
KEN | -0.112 |
annis | -0.104 |
biased | -0.103 |
comment | -0.103 |
rank | -0.102 |
Token | Show |
Token ID | 5438 |
Feature activation | -8.30e-02 |
Pos logit contributions | |
KEN | +0.104 |
annis | +0.098 |
biased | +0.097 |
comment | +0.097 |
rank | +0.096 |
Neg logit contributions | |
estial | -0.113 |
ergic | -0.113 |
alog | -0.107 |
ysis | -0.104 |
anchester | -0.103 |
Token | , |
Token ID | 11 |
Feature activation | +7.32e-03 |
Pos logit contributions | |
estial | +0.254 |
ergic | +0.253 |
alog | +0.242 |
anchester | +0.238 |
ysis | +0.237 |
Neg logit contributions | |
KEN | -0.124 |
biased | -0.111 |
annis | -0.111 |
comment | -0.111 |
rank | -0.110 |
Token | we |
Token ID | 356 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
KEN | +0.016 |
annis | +0.015 |
biased | +0.015 |
comment | +0.015 |
rank | +0.015 |
Neg logit contributions | |
estial | -0.017 |
ergic | -0.017 |
alog | -0.016 |
ysis | -0.016 |
anchester | -0.016 |
Token | are |
Token ID | 389 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
estial | +0.101 |
ergic | +0.101 |
alog | +0.096 |
ysis | +0.093 |
anchester | +0.093 |
Neg logit contributions | |
KEN | -0.077 |
biased | -0.071 |
annis | -0.071 |
comment | -0.071 |
rank | -0.070 |
Token | thinking |
Token ID | 3612 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
estial | +0.033 |
ergic | +0.033 |
alog | +0.031 |
anchester | +0.031 |
ysis | +0.031 |
Neg logit contributions | |
KEN | -0.024 |
annis | -0.023 |
biased | -0.023 |
comment | -0.022 |
rank | -0.022 |
Token | these |
Token ID | 777 |
Feature activation | +6.21e-03 |
Pos logit contributions | |
KEN | +0.254 |
annis | +0.236 |
biased | +0.236 |
comment | +0.234 |
rank | +0.233 |
Neg logit contributions | |
estial | -0.316 |
ergic | -0.315 |
alog | -0.299 |
ysis | -0.292 |
anchester | -0.291 |
Token | clips |
Token ID | 19166 |
Feature activation | +4.63e-04 |
Pos logit contributions | |
KEN | +0.014 |
annis | +0.013 |
biased | +0.013 |
comment | +0.013 |
rank | +0.013 |
Neg logit contributions | |
estial | -0.014 |
ergic | -0.014 |
alog | -0.013 |
ysis | -0.013 |
anchester | -0.013 |
Token | are |
Token ID | 389 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
KEN | +0.001 |
annis | +0.001 |
biased | +0.001 |
comment | +0.001 |
rank | +0.001 |
Neg logit contributions | |
estial | -0.001 |
ergic | -0.001 |
alog | -0.001 |
ysis | -0.001 |
anchester | -0.001 |
Token | As |
Token ID | 1081 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
KEN | +0.073 |
annis | +0.068 |
biased | +0.068 |
comment | +0.068 |
rank | +0.067 |
Neg logit contributions | |
ergic | -0.068 |
estial | -0.068 |
alog | -0.064 |
ysis | -0.062 |
anchester | -0.062 |
Token | a |
Token ID | 257 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
estial | +0.038 |
ergic | +0.038 |
alog | +0.036 |
ysis | +0.035 |
anchester | +0.035 |
Neg logit contributions | |
KEN | -0.035 |
annis | -0.032 |
biased | -0.032 |
comment | -0.032 |
rank | -0.032 |
Token | long |
Token ID | 890 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
KEN | +0.054 |
annis | +0.051 |
biased | +0.050 |
comment | +0.050 |
rank | +0.050 |
Neg logit contributions | |
estial | -0.063 |
ergic | -0.063 |
alog | -0.060 |
ysis | -0.058 |
anchester | -0.058 |
Token | - |
Token ID | 12 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
KEN | +0.036 |
biased | +0.034 |
annis | +0.033 |
comment | +0.033 |
rank | +0.033 |
Neg logit contributions | |
estial | -0.050 |
ergic | -0.050 |
alog | -0.048 |
anchester | -0.047 |
ysis | -0.047 |
Token | time |
Token ID | 2435 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
estial | +0.059 |
ergic | +0.059 |
alog | +0.056 |
ysis | +0.055 |
anchester | +0.055 |
Neg logit contributions | |
KEN | -0.035 |
annis | -0.032 |
biased | -0.032 |
comment | -0.032 |
rank | -0.031 |
Token | vi |
Token ID | 25357 |
Feature activation | -5.95e-02 |
Pos logit contributions | |
KEN | +0.427 |
biased | +0.399 |
annis | +0.399 |
comment | +0.398 |
rank | +0.395 |
Neg logit contributions | |
estial | -0.430 |
ergic | -0.425 |
alog | -0.401 |
anchester | -0.393 |
ysis | -0.390 |
Token | user |
Token ID | 2836 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
estial | +0.139 |
ergic | +0.138 |
alog | +0.131 |
ysis | +0.127 |
anchester | +0.127 |
Neg logit contributions | |
KEN | -0.131 |
annis | -0.123 |
biased | -0.123 |
comment | -0.122 |
rank | -0.121 |
Token | , |
Token ID | 11 |
Feature activation | -8.42e-03 |
Pos logit contributions | |
KEN | +0.267 |
annis | +0.246 |
biased | +0.246 |
comment | +0.245 |
rank | +0.242 |
Neg logit contributions | |
estial | -0.396 |
ergic | -0.392 |
alog | -0.374 |
anchester | -0.366 |
ysis | -0.365 |
Token | I |
Token ID | 314 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
estial | +0.020 |
ergic | +0.020 |
alog | +0.019 |
ysis | +0.018 |
anchester | +0.018 |
Neg logit contributions | |
KEN | -0.018 |
annis | -0.017 |
biased | -0.017 |
comment | -0.017 |
rank | -0.017 |
Token | activate |
Token ID | 15155 |
Feature activation | -5.96e-02 |
Pos logit contributions | |
estial | +0.089 |
ergic | +0.088 |
alog | +0.084 |
ysis | +0.082 |
anchester | +0.082 |
Neg logit contributions | |
KEN | -0.072 |
annis | -0.067 |
biased | -0.067 |
comment | -0.067 |
rank | -0.066 |
Token | Arduino |
Token ID | 27634 |
Feature activation | +7.61e-02 |
Pos logit contributions | |
estial | +0.139 |
ergic | +0.138 |
alog | +0.130 |
ysis | +0.127 |
anchester | +0.127 |
Neg logit contributions | |
KEN | -0.132 |
annis | -0.124 |
biased | -0.124 |
comment | -0.123 |
rank | -0.122 |
Token | package |
Token ID | 5301 |
Feature activation | +4.77e-02 |
Pos logit contributions | |
estial | +0.616 |
ergic | +0.614 |
alog | +0.589 |
ysis | +0.571 |
anchester | +0.569 |
Neg logit contributions | |
KEN | -0.450 |
annis | -0.416 |
biased | -0.416 |
comment | -0.411 |
rank | -0.409 |
Token | ". |
Token ID | 1911 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
KEN | +0.091 |
annis | +0.084 |
biased | +0.084 |
comment | +0.083 |
rank | +0.083 |
Neg logit contributions | |
estial | -0.126 |
ergic | -0.125 |
alog | -0.119 |
anchester | -0.117 |
ysis | -0.116 |
Token |
|
Token ID | 198 |
Feature activation | +6.81e-02 |
Pos logit contributions | |
KEN | +0.059 |
annis | +0.056 |
biased | +0.056 |
comment | +0.055 |
rank | +0.055 |
Neg logit contributions | |
estial | -0.056 |
ergic | -0.056 |
alog | -0.053 |
ysis | -0.051 |
anchester | -0.051 |
Token |
|
Token ID | 198 |
Feature activation | +7.75e-02 |
Pos logit contributions | |
KEN | +0.162 |
annis | +0.155 |
biased | +0.154 |
suspic | +0.152 |
rank | +0.150 |
Neg logit contributions | |
ergic | -0.146 |
estial | -0.143 |
alog | -0.137 |
ysis | -0.132 |
opsis | -0.130 |
Token | Fl |
Token ID | 7414 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
KEN | +0.124 |
annis | +0.113 |
biased | +0.113 |
comment | +0.111 |
rank | +0.111 |
Neg logit contributions | |
estial | -0.227 |
ergic | -0.227 |
alog | -0.217 |
ysis | -0.212 |
anchester | -0.212 |
Token | at |
Token ID | 265 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
estial | +0.026 |
ergic | +0.026 |
alog | +0.025 |
ysis | +0.024 |
anchester | +0.024 |
Neg logit contributions | |
KEN | -0.021 |
annis | -0.020 |
biased | -0.019 |
comment | -0.019 |
rank | -0.019 |
Token | pak |
Token ID | 41091 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
estial | +0.866 |
ergic | +0.861 |
alog | +0.808 |
ysis | +0.775 |
anchester | +0.775 |
Neg logit contributions | |
KEN | -1.212 |
annis | -1.148 |
biased | -1.147 |
comment | -1.139 |
rank | -1.134 |
Token | 's |
Token ID | 338 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
estial | +0.669 |
ergic | +0.667 |
alog | +0.634 |
anchester | +0.617 |
ysis | +0.616 |
Neg logit contributions | |
KEN | -0.542 |
annis | -0.505 |
biased | -0.504 |
comment | -0.500 |
rank | -0.498 |
Token | website |
Token ID | 3052 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
KEN | +0.045 |
annis | +0.042 |
biased | +0.042 |
comment | +0.042 |
rank | +0.042 |
Neg logit contributions | |
estial | -0.050 |
ergic | -0.049 |
alog | -0.047 |
ysis | -0.046 |
anchester | -0.045 |
Token | offers |
Token ID | 4394 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
KEN | +0.229 |
annis | +0.215 |
biased | +0.214 |
comment | +0.213 |
rank | +0.212 |
Neg logit contributions | |
estial | -0.246 |
ergic | -0.244 |
alog | -0.230 |
anchester | -0.225 |
ysis | -0.225 |
Token | the |
Token ID | 262 |
Feature activation | +6.20e-02 |
Pos logit contributions | |
KEN | +0.101 |
annis | +0.094 |
biased | +0.094 |
comment | +0.094 |
rank | +0.093 |
Neg logit contributions | |
estial | -0.108 |
ergic | -0.107 |
alog | -0.101 |
anchester | -0.099 |
ysis | -0.099 |
Token | here |
Token ID | 994 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
KEN | +0.223 |
annis | +0.206 |
biased | +0.206 |
comment | +0.204 |
rank | +0.203 |
Neg logit contributions | |
estial | -0.303 |
ergic | -0.301 |
alog | -0.286 |
anchester | -0.279 |
ysis | -0.279 |
Token | , |
Token ID | 11 |
Feature activation | +7.15e-03 |
Pos logit contributions | |
KEN | +0.031 |
annis | +0.029 |
biased | +0.029 |
comment | +0.028 |
rank | +0.028 |
Neg logit contributions | |
estial | -0.044 |
ergic | -0.044 |
alog | -0.042 |
ysis | -0.041 |
anchester | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | -9.23e-03 |
Pos logit contributions | |
KEN | +0.015 |
annis | +0.014 |
biased | +0.014 |
comment | +0.014 |
rank | +0.014 |
Neg logit contributions | |
estial | -0.018 |
ergic | -0.017 |
alog | -0.017 |
ysis | -0.016 |
anchester | -0.016 |
Token | talks |
Token ID | 6130 |
Feature activation | +7.73e-02 |
Pos logit contributions | |
estial | +0.024 |
ergic | +0.024 |
alog | +0.022 |
ysis | +0.022 |
anchester | +0.022 |
Neg logit contributions | |
KEN | -0.018 |
biased | -0.017 |
annis | -0.017 |
comment | -0.017 |
rank | -0.017 |
Token | glow |
Token ID | 19634 |
Feature activation | +4.97e-02 |
Pos logit contributions | |
KEN | +0.158 |
annis | +0.147 |
biased | +0.147 |
comment | +0.146 |
rank | +0.145 |
Neg logit contributions | |
estial | -0.193 |
ergic | -0.192 |
alog | -0.182 |
ysis | -0.178 |
anchester | -0.178 |
Token | ingly |
Token ID | 4420 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
KEN | +0.089 |
annis | +0.082 |
biased | +0.082 |
comment | +0.081 |
rank | +0.081 |
Neg logit contributions | |
estial | -0.137 |
ergic | -0.136 |
alog | -0.129 |
anchester | -0.127 |
ysis | -0.126 |
Token | of |
Token ID | 286 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
estial | +1.059 |
ergic | +1.058 |
alog | +1.000 |
ysis | +0.975 |
anchester | +0.974 |
Neg logit contributions | |
KEN | -0.895 |
annis | -0.833 |
biased | -0.831 |
comment | -0.825 |
rank | -0.821 |
Token | things |
Token ID | 1243 |
Feature activation | +5.64e-02 |
Pos logit contributions | |
estial | +0.087 |
ergic | +0.086 |
alog | +0.081 |
anchester | +0.080 |
ysis | +0.079 |
Neg logit contributions | |
KEN | -0.080 |
annis | -0.075 |
biased | -0.075 |
comment | -0.075 |
rank | -0.074 |
Token | Americans |
Token ID | 3399 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
KEN | +0.107 |
annis | +0.099 |
biased | +0.099 |
comment | +0.098 |
rank | +0.098 |
Neg logit contributions | |
estial | -0.149 |
ergic | -0.149 |
alog | -0.141 |
anchester | -0.138 |
ysis | -0.138 |
Token | take |
Token ID | 1011 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
KEN | +0.021 |
biased | +0.019 |
annis | +0.019 |
comment | +0.019 |
rank | +0.019 |
Neg logit contributions | |
estial | -0.028 |
ergic | -0.028 |
alog | -0.027 |
ysis | -0.026 |
anchester | -0.026 |
Token | for |
Token ID | 329 |
Feature activation | -5.94e-02 |
Pos logit contributions | |
KEN | +0.060 |
annis | +0.055 |
biased | +0.055 |
comment | +0.055 |
rank | +0.055 |
Neg logit contributions | |
estial | -0.095 |
ergic | -0.095 |
alog | -0.091 |
ysis | -0.089 |
anchester | -0.089 |
Token | . |
Token ID | 13 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
KEN | +0.014 |
annis | +0.013 |
biased | +0.013 |
comment | +0.013 |
rank | +0.013 |
Neg logit contributions | |
estial | -0.021 |
ergic | -0.021 |
alog | -0.020 |
ysis | -0.020 |
anchester | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -4.30e-02 |
Pos logit contributions | |
estial | +0.151 |
ergic | +0.150 |
alog | +0.142 |
anchester | +0.138 |
ysis | +0.138 |
Neg logit contributions | |
KEN | -0.137 |
biased | -0.128 |
annis | -0.128 |
comment | -0.128 |
rank | -0.127 |
Token |
|
Token ID | 198 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
ergic | +0.092 |
estial | +0.090 |
alog | +0.086 |
ysis | +0.083 |
opsis | +0.082 |
Neg logit contributions | |
KEN | -0.102 |
annis | -0.098 |
biased | -0.097 |
suspic | -0.097 |
queue | -0.095 |
Token | J |
Token ID | 41 |
Feature activation | -6.92e-02 |
Pos logit contributions | |
estial | +0.063 |
ergic | +0.063 |
alog | +0.060 |
ysis | +0.059 |
anchester | +0.058 |
Neg logit contributions | |
KEN | -0.035 |
annis | -0.032 |
biased | -0.032 |
comment | -0.032 |
rank | -0.032 |
Token | oint |
Token ID | 1563 |
Feature activation | -4.23e-02 |
Pos logit contributions | |
estial | +0.174 |
ergic | +0.173 |
alog | +0.164 |
anchester | +0.160 |
ysis | +0.160 |
Neg logit contributions | |
KEN | -0.141 |
annis | -0.131 |
biased | -0.130 |
comment | -0.130 |
rank | -0.129 |
Token | ly |
Token ID | 306 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
estial | +0.097 |
ergic | +0.096 |
alog | +0.091 |
anchester | +0.088 |
ysis | +0.088 |
Neg logit contributions | |
KEN | -0.095 |
annis | -0.089 |
biased | -0.089 |
comment | -0.089 |
rank | -0.089 |
Token | organized |
Token ID | 8389 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
estial | +0.905 |
ergic | +0.901 |
alog | +0.849 |
ysis | +0.825 |
anchester | +0.825 |
Neg logit contributions | |
KEN | -0.922 |
annis | -0.865 |
biased | -0.863 |
comment | -0.858 |
rank | -0.855 |
Token | by |
Token ID | 416 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
estial | +0.386 |
ergic | +0.384 |
alog | +0.364 |
anchester | +0.355 |
ysis | +0.355 |
Neg logit contributions | |
KEN | -0.310 |
annis | -0.288 |
biased | -0.288 |
comment | -0.286 |
rank | -0.284 |
Token | Zionist |
Token ID | 29390 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
estial | +0.079 |
ergic | +0.079 |
alog | +0.074 |
anchester | +0.072 |
ysis | +0.072 |
Neg logit contributions | |
KEN | -0.086 |
biased | -0.081 |
annis | -0.081 |
comment | -0.080 |
rank | -0.080 |
Token | youth |
Token ID | 6205 |
Feature activation | -5.27e-02 |
Pos logit contributions | |
KEN | +0.235 |
annis | +0.219 |
biased | +0.219 |
comment | +0.219 |
rank | +0.218 |
Neg logit contributions | |
estial | -0.230 |
ergic | -0.228 |
alog | -0.215 |
anchester | -0.210 |
ysis | -0.209 |
Token | movement |
Token ID | 3356 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
estial | +0.126 |
ergic | +0.126 |
alog | +0.119 |
ysis | +0.116 |
anchester | +0.116 |
Neg logit contributions | |
KEN | -0.113 |
annis | -0.106 |
biased | -0.105 |
comment | -0.105 |
rank | -0.104 |
Token | Pelosi |
Token ID | 29611 |
Feature activation | -6.71e-03 |
Pos logit contributions | |
estial | +0.078 |
ergic | +0.077 |
alog | +0.072 |
anchester | +0.070 |
ysis | +0.070 |
Neg logit contributions | |
KEN | -0.090 |
annis | -0.085 |
biased | -0.085 |
comment | -0.085 |
rank | -0.084 |
Token | , |
Token ID | 11 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
estial | +0.018 |
ergic | +0.018 |
alog | +0.017 |
ysis | +0.017 |
anchester | +0.017 |
Neg logit contributions | |
KEN | -0.012 |
annis | -0.011 |
biased | -0.011 |
comment | -0.011 |
rank | -0.011 |
Token | while |
Token ID | 981 |
Feature activation | -2.77e-03 |
Pos logit contributions | |
KEN | +0.035 |
annis | +0.032 |
biased | +0.032 |
comment | +0.032 |
rank | +0.032 |
Neg logit contributions | |
estial | -0.046 |
ergic | -0.046 |
alog | -0.043 |
ysis | -0.042 |
anchester | -0.042 |
Token | an |
Token ID | 281 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
estial | +0.006 |
ergic | +0.006 |
alog | +0.006 |
ysis | +0.006 |
anchester | +0.006 |
Neg logit contributions | |
KEN | -0.006 |
annis | -0.006 |
biased | -0.006 |
comment | -0.006 |
queue | -0.006 |
Token | Associated |
Token ID | 10575 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
KEN | +0.027 |
annis | +0.025 |
biased | +0.025 |
comment | +0.025 |
rank | +0.025 |
Neg logit contributions | |
estial | -0.029 |
ergic | -0.028 |
alog | -0.027 |
ysis | -0.026 |
anchester | -0.026 |
Token | Press |
Token ID | 4332 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
ergic | +0.192 |
estial | +0.188 |
alog | +0.179 |
opsis | +0.168 |
ysis | +0.168 |
Neg logit contributions | |
KEN | -0.330 |
annis | -0.315 |
biased | -0.312 |
queue | -0.308 |
200000 | -0.307 |
Token | poll |
Token ID | 3278 |
Feature activation | -9.46e-02 |
Pos logit contributions | |
ergic | +1.245 |
estial | +1.243 |
alog | +1.182 |
ysis | +1.146 |
anchester | +1.143 |
Neg logit contributions | |
KEN | -1.083 |
annis | -1.007 |
biased | -1.001 |
comment | -0.991 |
queue | -0.990 |
Token | in |
Token ID | 287 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
estial | +0.234 |
ergic | +0.234 |
alog | +0.221 |
ysis | +0.216 |
anchester | +0.216 |
Neg logit contributions | |
KEN | -0.195 |
annis | -0.182 |
biased | -0.181 |
comment | -0.180 |
rank | -0.179 |
Token | December |
Token ID | 3426 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
KEN | +0.049 |
annis | +0.046 |
biased | +0.046 |
comment | +0.046 |
rank | +0.045 |
Neg logit contributions | |
ergic | -0.046 |
estial | -0.046 |
alog | -0.044 |
ysis | -0.042 |
anchester | -0.042 |
Token | of |
Token ID | 286 |
Feature activation | +7.66e-03 |
Pos logit contributions | |
KEN | +0.316 |
annis | +0.295 |
biased | +0.295 |
comment | +0.293 |
rank | +0.291 |
Neg logit contributions | |
estial | -0.356 |
ergic | -0.355 |
alog | -0.335 |
ysis | -0.327 |
anchester | -0.327 |
Token | that |
Token ID | 326 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
KEN | +0.015 |
annis | +0.014 |
biased | +0.014 |
comment | +0.014 |
rank | +0.014 |
Neg logit contributions | |
estial | -0.019 |
ergic | -0.019 |
alog | -0.018 |
ysis | -0.018 |
anchester | -0.018 |
Token | � |
Token ID | 14360 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
estial | +0.060 |
ergic | +0.059 |
alog | +0.056 |
anchester | +0.055 |
ysis | +0.055 |
Neg logit contributions | |
KEN | -0.044 |
annis | -0.041 |
biased | -0.041 |
comment | -0.041 |
rank | -0.040 |
Token | � |
Token ID | 243 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
estial | +0.158 |
ergic | +0.157 |
alog | +0.143 |
anchester | +0.137 |
ysis | +0.137 |
Neg logit contributions | |
KEN | -0.330 |
annis | -0.314 |
biased | -0.314 |
comment | -0.313 |
rank | -0.312 |
Token | י� |
Token ID | 33951 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
estial | +0.654 |
ergic | +0.651 |
alog | +0.615 |
ysis | +0.598 |
anchester | +0.596 |
Neg logit contributions | |
KEN | -0.613 |
annis | -0.574 |
biased | -0.573 |
comment | -0.568 |
rank | -0.567 |
Token | � |
Token ID | 95 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
estial | +0.205 |
ergic | +0.203 |
alog | +0.186 |
anchester | +0.179 |
ysis | +0.179 |
Neg logit contributions | |
KEN | -0.396 |
biased | -0.377 |
annis | -0.377 |
comment | -0.376 |
rank | -0.374 |
Token | � |
Token ID | 147 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
estial | +0.693 |
ergic | +0.689 |
alog | +0.653 |
ysis | +0.637 |
anchester | +0.636 |
Neg logit contributions | |
KEN | -0.534 |
annis | -0.498 |
biased | -0.496 |
comment | -0.492 |
rank | -0.490 |
Token | � |
Token ID | 254 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
estial | +0.049 |
ergic | +0.048 |
alog | +0.044 |
anchester | +0.043 |
ysis | +0.042 |
Neg logit contributions | |
KEN | -0.090 |
biased | -0.085 |
comment | -0.085 |
annis | -0.085 |
rank | -0.085 |
Token | ה |
Token ID | 38269 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
estial | +1.152 |
ergic | +1.150 |
alog | +1.088 |
ysis | +1.061 |
anchester | +1.055 |
Neg logit contributions | |
KEN | -0.918 |
annis | -0.856 |
biased | -0.855 |
comment | -0.847 |
rank | -0.845 |
Token | . |
Token ID | 13 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
estial | +0.563 |
ergic | +0.560 |
alog | +0.531 |
ysis | +0.517 |
anchester | +0.517 |
Neg logit contributions | |
KEN | -0.462 |
annis | -0.431 |
biased | -0.430 |
comment | -0.426 |
rank | -0.425 |
Token | Joseph |
Token ID | 7212 |
Feature activation | -6.03e-02 |
Pos logit contributions | |
estial | +0.043 |
ergic | +0.043 |
alog | +0.041 |
anchester | +0.040 |
ysis | +0.040 |
Neg logit contributions | |
KEN | -0.043 |
annis | -0.040 |
biased | -0.040 |
comment | -0.040 |
rank | -0.040 |
Token | us |
Token ID | 385 |
Feature activation | -5.48e-02 |
Pos logit contributions | |
estial | +0.137 |
ergic | +0.135 |
alog | +0.127 |
anchester | +0.126 |
ysis | +0.125 |
Neg logit contributions | |
KEN | -0.137 |
annis | -0.129 |
biased | -0.128 |
comment | -0.128 |
rank | -0.127 |
Token | � |
Token ID | 447 |
Feature activation | -5.03e-02 |
Pos logit contributions | |
estial | +0.135 |
ergic | +0.134 |
alog | +0.127 |
ysis | +0.124 |
anchester | +0.124 |
Neg logit contributions | |
KEN | -0.114 |
annis | -0.107 |
biased | -0.106 |
comment | -0.106 |
rank | -0.105 |