Token | Irvine |
Token ID | 37277 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
uberty | +0.069 |
taboola | +0.067 |
nered | +0.066 |
sum | +0.061 |
pric | +0.060 |
Neg logit contributions | |
Greek | -0.049 |
Elias | -0.048 |
abal | -0.047 |
ascript | -0.047 |
'). | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | +6.66e-02 |
Pos logit contributions | |
Greek | +0.306 |
Elias | +0.299 |
ascript | +0.290 |
abal | +0.290 |
'). | +0.265 |
Neg logit contributions | |
uberty | -0.448 |
taboola | -0.441 |
nered | -0.433 |
sum | -0.401 |
pric | -0.394 |
Token | California |
Token ID | 3442 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
uberty | +0.168 |
taboola | +0.164 |
nered | +0.161 |
sum | +0.146 |
pric | +0.143 |
Neg logit contributions | |
Greek | -0.182 |
Elias | -0.179 |
abal | -0.175 |
ascript | -0.175 |
'). | -0.162 |
Token | . |
Token ID | 13 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
Greek | +0.394 |
Elias | +0.389 |
abal | +0.375 |
ascript | +0.374 |
'). | +0.340 |
Neg logit contributions | |
uberty | -0.641 |
taboola | -0.628 |
nered | -0.617 |
sum | -0.573 |
pric | -0.563 |
Token | Hide |
Token ID | 10415 |
Feature activation | -3.59e-02 |
Pos logit contributions | |
Greek | +0.025 |
Elias | +0.024 |
ascript | +0.024 |
abal | +0.024 |
'). | +0.021 |
Neg logit contributions | |
uberty | -0.040 |
taboola | -0.040 |
nered | -0.039 |
sum | -0.036 |
pric | -0.036 |
Token | Caption |
Token ID | 11260 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
Greek | +0.098 |
Elias | +0.097 |
ascript | +0.096 |
abal | +0.095 |
'). | +0.088 |
Neg logit contributions | |
uberty | -0.090 |
taboola | -0.089 |
nered | -0.086 |
sum | -0.078 |
pric | -0.076 |
Token | 10 |
Token ID | 838 |
Feature activation | +5.87e-03 |
Pos logit contributions | |
taboola | +1.105 |
uberty | +1.085 |
nered | +1.040 |
sum | +0.993 |
pric | +0.948 |
Neg logit contributions | |
ascript | -1.326 |
Greek | -1.314 |
Elias | -1.306 |
abal | -1.287 |
'). | -1.177 |
Token | of |
Token ID | 286 |
Feature activation | +9.56e-03 |
Pos logit contributions | |
uberty | +0.015 |
taboola | +0.015 |
nered | +0.014 |
sum | +0.013 |
pric | +0.013 |
Neg logit contributions | |
Greek | -0.016 |
Elias | -0.016 |
ascript | -0.015 |
abal | -0.015 |
'). | -0.014 |
Token | 15 |
Token ID | 1315 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
uberty | +0.026 |
taboola | +0.026 |
nered | +0.026 |
sum | +0.024 |
pric | +0.023 |
Neg logit contributions | |
Greek | -0.023 |
Elias | -0.023 |
ascript | -0.023 |
abal | -0.023 |
'). | -0.021 |
Token | Photos |
Token ID | 9434 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
Greek | +0.079 |
Elias | +0.078 |
ascript | +0.077 |
abal | +0.076 |
'). | +0.071 |
Neg logit contributions | |
uberty | -0.065 |
taboola | -0.065 |
nered | -0.063 |
sum | -0.057 |
pric | -0.055 |
Token | : |
Token ID | 25 |
Feature activation | -5.46e-03 |
Pos logit contributions | |
taboola | +0.576 |
uberty | +0.568 |
nered | +0.561 |
sum | +0.521 |
pric | +0.499 |
Neg logit contributions | |
Greek | -0.504 |
ascript | -0.502 |
Elias | -0.501 |
abal | -0.486 |
'). | -0.441 |
Token | sk |
Token ID | 8135 |
Feature activation | -5.98e-03 |
Pos logit contributions | |
uberty | +0.131 |
taboola | +0.128 |
nered | +0.123 |
sum | +0.109 |
pric | +0.108 |
Neg logit contributions | |
Elias | -0.158 |
Greek | -0.157 |
abal | -0.153 |
ascript | -0.150 |
'). | -0.141 |
Token | . |
Token ID | 13 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
Greek | +0.015 |
Elias | +0.014 |
ascript | +0.014 |
abal | +0.014 |
'). | +0.013 |
Neg logit contributions | |
uberty | -0.017 |
taboola | -0.016 |
nered | -0.016 |
sum | -0.015 |
pric | -0.015 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
Greek | +0.100 |
Elias | +0.099 |
abal | +0.096 |
ascript | +0.096 |
'). | +0.089 |
Neg logit contributions | |
uberty | -0.101 |
taboola | -0.098 |
nered | -0.096 |
sum | -0.088 |
pric | -0.086 |
Token | [ |
Token ID | 58 |
Feature activation | -4.10e-02 |
Pos logit contributions | |
uberty | +0.046 |
taboola | +0.045 |
nered | +0.044 |
sum | +0.041 |
pric | +0.040 |
Neg logit contributions | |
Elias | -0.038 |
Greek | -0.038 |
abal | -0.037 |
ascript | -0.037 |
'). | -0.034 |
Token | Ex |
Token ID | 3109 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
Greek | +0.104 |
Elias | +0.103 |
abal | +0.100 |
ascript | +0.100 |
'). | +0.092 |
Neg logit contributions | |
uberty | -0.112 |
taboola | -0.108 |
nered | -0.107 |
sum | -0.097 |
pric | -0.096 |
Token | clusive |
Token ID | 5731 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
Greek | +0.329 |
Elias | +0.326 |
abal | +0.317 |
ascript | +0.316 |
'). | +0.293 |
Neg logit contributions | |
uberty | -0.343 |
taboola | -0.335 |
nered | -0.328 |
sum | -0.299 |
pric | -0.293 |
Token | ] |
Token ID | 60 |
Feature activation | +8.96e-02 |
Pos logit contributions | |
uberty | +1.454 |
taboola | +1.422 |
nered | +1.401 |
sum | +1.300 |
pric | +1.278 |
Neg logit contributions | |
Greek | -1.020 |
Elias | -1.004 |
ascript | -0.974 |
abal | -0.973 |
'). | -0.887 |
Token | Best |
Token ID | 6705 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
uberty | +0.240 |
taboola | +0.234 |
nered | +0.230 |
sum | +0.209 |
pric | +0.205 |
Neg logit contributions | |
Greek | -0.230 |
Elias | -0.229 |
abal | -0.222 |
ascript | -0.222 |
'). | -0.205 |
Token | Buy |
Token ID | 11763 |
Feature activation | -8.55e-02 |
Pos logit contributions | |
uberty | +0.064 |
taboola | +0.063 |
nered | +0.062 |
sum | +0.056 |
pric | +0.055 |
Neg logit contributions | |
Greek | -0.067 |
Elias | -0.067 |
abal | -0.065 |
ascript | -0.065 |
'). | -0.060 |
Token | to |
Token ID | 284 |
Feature activation | +6.20e-02 |
Pos logit contributions | |
Greek | +0.231 |
Elias | +0.229 |
abal | +0.223 |
ascript | +0.223 |
'). | +0.207 |
Neg logit contributions | |
uberty | -0.218 |
taboola | -0.212 |
nered | -0.208 |
sum | -0.189 |
pric | -0.186 |
Token | have |
Token ID | 423 |
Feature activation | +6.40e-02 |
Pos logit contributions | |
uberty | +0.150 |
taboola | +0.146 |
nered | +0.143 |
sum | +0.130 |
pric | +0.128 |
Neg logit contributions | |
Greek | -0.175 |
Elias | -0.173 |
ascript | -0.170 |
abal | -0.169 |
'). | -0.158 |
Token | ... |
Token ID | 986 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
Greek | +0.403 |
Elias | +0.399 |
abal | +0.384 |
ascript | +0.382 |
'). | +0.346 |
Neg logit contributions | |
uberty | -0.654 |
taboola | -0.642 |
nered | -0.631 |
sum | -0.586 |
pric | -0.576 |
Token |
|
Token ID | 198 |
Feature activation | +4.39e-02 |
Pos logit contributions | |
uberty | +0.087 |
taboola | +0.085 |
nered | +0.083 |
sum | +0.076 |
pric | +0.074 |
Neg logit contributions | |
Greek | -0.084 |
Elias | -0.083 |
abal | -0.082 |
ascript | -0.082 |
'). | -0.075 |
Token |
|
Token ID | 198 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
uberty | +0.117 |
taboola | +0.115 |
nered | +0.112 |
sum | +0.103 |
pric | +0.100 |
Neg logit contributions | |
Greek | -0.113 |
Elias | -0.112 |
ascript | -0.109 |
abal | -0.109 |
'). | -0.100 |
Token | Fund |
Token ID | 24553 |
Feature activation | +8.21e-03 |
Pos logit contributions | |
uberty | +0.042 |
taboola | +0.042 |
nered | +0.041 |
sum | +0.037 |
pric | +0.036 |
Neg logit contributions | |
Elias | -0.035 |
Greek | -0.035 |
ascript | -0.034 |
abal | -0.034 |
'). | -0.031 |
Token | ament |
Token ID | 3263 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
uberty | +0.020 |
taboola | +0.019 |
nered | +0.019 |
sum | +0.017 |
pric | +0.016 |
Neg logit contributions | |
Greek | -0.024 |
Elias | -0.023 |
abal | -0.023 |
ascript | -0.023 |
'). | -0.021 |
Token | ally |
Token ID | 453 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
uberty | +0.553 |
taboola | +0.536 |
nered | +0.528 |
sum | +0.472 |
pric | +0.459 |
Neg logit contributions | |
Greek | -0.698 |
Elias | -0.694 |
abal | -0.675 |
ascript | -0.674 |
'). | -0.632 |
Token | there |
Token ID | 612 |
Feature activation | +6.35e-02 |
Pos logit contributions | |
uberty | +1.261 |
taboola | +1.230 |
nered | +1.214 |
sum | +1.127 |
pric | +1.087 |
Neg logit contributions | |
Greek | -1.153 |
Elias | -1.121 |
abal | -1.121 |
ascript | -1.110 |
'). | -1.028 |
Token | is |
Token ID | 318 |
Feature activation | +7.09e-02 |
Pos logit contributions | |
uberty | +0.147 |
taboola | +0.143 |
nered | +0.140 |
sum | +0.126 |
pric | +0.123 |
Neg logit contributions | |
Greek | -0.186 |
Elias | -0.185 |
abal | -0.180 |
ascript | -0.179 |
'). | -0.168 |
Token | much |
Token ID | 881 |
Feature activation | -2.32e-03 |
Pos logit contributions | |
uberty | +0.148 |
taboola | +0.143 |
nered | +0.140 |
sum | +0.126 |
pric | +0.121 |
Neg logit contributions | |
Greek | -0.223 |
Elias | -0.222 |
ascript | -0.217 |
abal | -0.217 |
'). | -0.204 |
Token | more |
Token ID | 517 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
Greek | +0.007 |
Elias | +0.006 |
ascript | +0.006 |
abal | +0.006 |
'). | +0.006 |
Neg logit contributions | |
uberty | -0.006 |
taboola | -0.005 |
nered | -0.005 |
sum | -0.005 |
pric | -0.005 |
Token | in |
Token ID | 287 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
uberty | +0.076 |
taboola | +0.074 |
nered | +0.073 |
sum | +0.067 |
pric | +0.064 |
Neg logit contributions | |
Greek | -0.095 |
Elias | -0.094 |
ascript | -0.093 |
abal | -0.092 |
'). | -0.086 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
uberty | +0.308 |
taboola | +0.303 |
nered | +0.300 |
sum | +0.278 |
pric | +0.273 |
Neg logit contributions | |
Greek | -0.204 |
Elias | -0.201 |
ascript | -0.200 |
abal | -0.195 |
'). | -0.177 |
Token | United |
Token ID | 1578 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
Greek | +0.036 |
Elias | +0.035 |
abal | +0.034 |
ascript | +0.034 |
'). | +0.031 |
Neg logit contributions | |
uberty | -0.045 |
taboola | -0.044 |
nered | -0.044 |
sum | -0.040 |
pric | -0.039 |
Token | States |
Token ID | 1829 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
uberty | +0.056 |
taboola | +0.055 |
nered | +0.053 |
sum | +0.047 |
pric | +0.046 |
Neg logit contributions | |
Greek | -0.075 |
Elias | -0.074 |
abal | -0.072 |
ascript | -0.072 |
'). | -0.068 |
Token | 21 |
Token ID | 2310 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
Greek | +0.088 |
Elias | +0.087 |
ascript | +0.086 |
abal | +0.085 |
'). | +0.079 |
Neg logit contributions | |
uberty | -0.085 |
taboola | -0.083 |
nered | -0.081 |
sum | -0.074 |
pric | -0.073 |
Token | 50 |
Token ID | 1120 |
Feature activation | -4.47e-02 |
Pos logit contributions | |
Greek | +0.129 |
Elias | +0.128 |
ascript | +0.125 |
abal | +0.124 |
'). | +0.115 |
Neg logit contributions | |
uberty | -0.124 |
taboola | -0.121 |
nered | -0.119 |
sum | -0.108 |
pric | -0.105 |
Token | Posts |
Token ID | 12043 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
Greek | +0.150 |
Elias | +0.149 |
abal | +0.145 |
ascript | +0.144 |
'). | +0.137 |
Neg logit contributions | |
uberty | -0.086 |
taboola | -0.082 |
nered | -0.080 |
sum | -0.070 |
pric | -0.068 |
Token | # |
Token ID | 1303 |
Feature activation | +7.95e-02 |
Pos logit contributions | |
uberty | +1.246 |
taboola | +1.208 |
nered | +1.198 |
sum | +1.100 |
pric | +1.070 |
Neg logit contributions | |
Greek | -1.154 |
Elias | -1.138 |
abal | -1.101 |
ascript | -1.099 |
'). | -1.024 |
Token | 16 |
Token ID | 1433 |
Feature activation | -6.99e-02 |
Pos logit contributions | |
uberty | +0.227 |
taboola | +0.221 |
nered | +0.217 |
sum | +0.198 |
pric | +0.196 |
Neg logit contributions | |
Greek | -0.192 |
Elias | -0.190 |
abal | -0.184 |
ascript | -0.182 |
'). | -0.170 |
Token | Glad |
Token ID | 28442 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Greek | +0.186 |
Elias | +0.186 |
abal | +0.180 |
ascript | +0.179 |
'). | +0.167 |
Neg logit contributions | |
uberty | -0.180 |
taboola | -0.176 |
nered | -0.172 |
sum | -0.156 |
pric | -0.153 |
Token | to |
Token ID | 284 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
Greek | +0.346 |
Elias | +0.345 |
abal | +0.334 |
ascript | +0.332 |
'). | +0.311 |
Neg logit contributions | |
uberty | -0.305 |
taboola | -0.297 |
nered | -0.289 |
sum | -0.260 |
pric | -0.255 |
Token | hear |
Token ID | 3285 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Greek | +0.060 |
Elias | +0.059 |
ascript | +0.058 |
abal | +0.058 |
'). | +0.055 |
Neg logit contributions | |
uberty | -0.039 |
taboola | -0.037 |
nered | -0.036 |
sum | -0.032 |
pric | -0.031 |
Token | Pasadena |
Token ID | 41010 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
uberty | +0.059 |
taboola | +0.058 |
nered | +0.057 |
sum | +0.051 |
pric | +0.050 |
Neg logit contributions | |
Greek | -0.063 |
Elias | -0.062 |
abal | -0.060 |
ascript | -0.060 |
'). | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | +5.95e-02 |
Pos logit contributions | |
Greek | +0.090 |
Elias | +0.089 |
ascript | +0.086 |
abal | +0.085 |
'). | +0.078 |
Neg logit contributions | |
uberty | -0.132 |
taboola | -0.129 |
nered | -0.127 |
sum | -0.117 |
pric | -0.115 |
Token | California |
Token ID | 3442 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
uberty | +0.151 |
taboola | +0.147 |
nered | +0.144 |
sum | +0.131 |
pric | +0.128 |
Neg logit contributions | |
Greek | -0.162 |
Elias | -0.160 |
abal | -0.156 |
ascript | -0.156 |
'). | -0.145 |
Token | . |
Token ID | 13 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
Greek | +0.267 |
Elias | +0.263 |
ascript | +0.253 |
abal | +0.253 |
'). | +0.230 |
Neg logit contributions | |
uberty | -0.428 |
taboola | -0.419 |
nered | -0.412 |
sum | -0.382 |
pric | -0.375 |
Token | Hide |
Token ID | 10415 |
Feature activation | -4.16e-02 |
Pos logit contributions | |
Greek | +0.062 |
Elias | +0.061 |
ascript | +0.060 |
abal | +0.059 |
'). | +0.053 |
Neg logit contributions | |
uberty | -0.113 |
taboola | -0.111 |
nered | -0.109 |
sum | -0.102 |
pric | -0.100 |
Token | Caption |
Token ID | 11260 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
Greek | +0.114 |
Elias | +0.112 |
ascript | +0.111 |
abal | +0.110 |
'). | +0.102 |
Neg logit contributions | |
uberty | -0.104 |
taboola | -0.102 |
nered | -0.099 |
sum | -0.091 |
pric | -0.088 |
Token | 11 |
Token ID | 1367 |
Feature activation | +2.25e-03 |
Pos logit contributions | |
taboola | +1.007 |
uberty | +1.006 |
nered | +0.960 |
sum | +0.885 |
pric | +0.852 |
Neg logit contributions | |
Greek | -1.335 |
ascript | -1.324 |
Elias | -1.321 |
abal | -1.291 |
λ | -1.207 |
Token | of |
Token ID | 286 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
uberty | +0.006 |
taboola | +0.006 |
nered | +0.006 |
sum | +0.005 |
pric | +0.005 |
Neg logit contributions | |
Greek | -0.006 |
Elias | -0.006 |
ascript | -0.006 |
abal | -0.006 |
'). | -0.005 |
Token | 15 |
Token ID | 1315 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
uberty | +0.029 |
taboola | +0.029 |
nered | +0.028 |
sum | +0.026 |
pric | +0.025 |
Neg logit contributions | |
Greek | -0.026 |
Elias | -0.025 |
ascript | -0.025 |
abal | -0.025 |
'). | -0.023 |
Token | Photos |
Token ID | 9434 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
Greek | +0.099 |
Elias | +0.098 |
ascript | +0.097 |
abal | +0.095 |
'). | +0.089 |
Neg logit contributions | |
uberty | -0.082 |
taboola | -0.082 |
nered | -0.080 |
sum | -0.072 |
pric | -0.070 |
Token | : |
Token ID | 25 |
Feature activation | +2.23e-03 |
Pos logit contributions | |
taboola | +0.467 |
uberty | +0.461 |
nered | +0.455 |
sum | +0.422 |
pric | +0.405 |
Neg logit contributions | |
Greek | -0.406 |
ascript | -0.404 |
Elias | -0.403 |
abal | -0.391 |
'). | -0.355 |
Token | Grove |
Token ID | 24144 |
Feature activation | -6.52e-02 |
Pos logit contributions | |
uberty | +0.004 |
taboola | +0.004 |
nered | +0.004 |
sum | +0.004 |
pric | +0.003 |
Neg logit contributions | |
Greek | -0.004 |
Elias | -0.004 |
ascript | -0.004 |
abal | -0.004 |
'). | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
Greek | +0.138 |
Elias | +0.136 |
abal | +0.131 |
ascript | +0.131 |
'). | +0.120 |
Neg logit contributions | |
uberty | -0.205 |
taboola | -0.200 |
nered | -0.197 |
sum | -0.183 |
pric | -0.179 |
Token | California |
Token ID | 3442 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
uberty | +0.084 |
taboola | +0.082 |
nered | +0.081 |
sum | +0.073 |
pric | +0.072 |
Neg logit contributions | |
Greek | -0.090 |
Elias | -0.089 |
abal | -0.087 |
ascript | -0.086 |
'). | -0.080 |
Token | . |
Token ID | 13 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
Greek | +0.277 |
Elias | +0.273 |
ascript | +0.263 |
abal | +0.262 |
'). | +0.240 |
Neg logit contributions | |
uberty | -0.439 |
taboola | -0.430 |
nered | -0.423 |
sum | -0.392 |
pric | -0.384 |
Token | Hide |
Token ID | 10415 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
Greek | +0.028 |
Elias | +0.027 |
ascript | +0.027 |
abal | +0.026 |
'). | +0.024 |
Neg logit contributions | |
uberty | -0.050 |
taboola | -0.049 |
nered | -0.048 |
sum | -0.045 |
pric | -0.044 |
Token | Caption |
Token ID | 11260 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
Greek | +0.106 |
Elias | +0.105 |
ascript | +0.103 |
abal | +0.102 |
'). | +0.095 |
Neg logit contributions | |
uberty | -0.097 |
taboola | -0.096 |
nered | -0.093 |
sum | -0.085 |
pric | -0.082 |
Token | 15 |
Token ID | 1315 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
taboola | +1.182 |
uberty | +1.157 |
nered | +1.137 |
sum | +1.068 |
pric | +1.025 |
Neg logit contributions | |
Greek | -1.130 |
ascript | -1.130 |
Elias | -1.117 |
abal | -1.095 |
λ | -1.011 |
Token | of |
Token ID | 286 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
uberty | +0.152 |
taboola | +0.149 |
nered | +0.146 |
sum | +0.133 |
pric | +0.130 |
Neg logit contributions | |
Greek | -0.156 |
Elias | -0.155 |
ascript | -0.151 |
abal | -0.150 |
'). | -0.139 |
Token | 15 |
Token ID | 1315 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
uberty | +0.030 |
taboola | +0.030 |
nered | +0.029 |
sum | +0.027 |
pric | +0.026 |
Neg logit contributions | |
Greek | -0.026 |
Elias | -0.025 |
ascript | -0.025 |
abal | -0.025 |
'). | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
uberty | +0.114 |
taboola | +0.112 |
nered | +0.110 |
sum | +0.100 |
pric | +0.098 |
Neg logit contributions | |
Greek | -0.111 |
Elias | -0.110 |
ascript | -0.107 |
abal | -0.107 |
'). | -0.099 |
Token |
|
Token ID | 198 |
Feature activation | +8.08e-02 |
Pos logit contributions | |
uberty | +0.274 |
taboola | +0.272 |
nered | +0.265 |
sum | +0.242 |
pric | +0.235 |
Neg logit contributions | |
Greek | -0.275 |
Elias | -0.273 |
ascript | -0.270 |
abal | -0.266 |
'). | -0.245 |
Token | length |
Token ID | 4129 |
Feature activation | +5.77e-02 |
Pos logit contributions | |
Greek | +0.130 |
Elias | +0.129 |
abal | +0.126 |
ascript | +0.126 |
'). | +0.119 |
Neg logit contributions | |
uberty | -0.072 |
taboola | -0.070 |
nered | -0.068 |
sum | -0.059 |
pric | -0.057 |
Token | .) |
Token ID | 2014 |
Feature activation | +7.48e-02 |
Pos logit contributions | |
uberty | +0.178 |
taboola | +0.174 |
nered | +0.172 |
sum | +0.159 |
pric | +0.155 |
Neg logit contributions | |
Greek | -0.125 |
Elias | -0.124 |
abal | -0.119 |
ascript | -0.119 |
'). | -0.108 |
Token |
|
Token ID | 198 |
Feature activation | +4.90e-02 |
Pos logit contributions | |
uberty | +0.223 |
taboola | +0.218 |
nered | +0.214 |
sum | +0.198 |
pric | +0.193 |
Neg logit contributions | |
Greek | -0.170 |
Elias | -0.168 |
abal | -0.162 |
ascript | -0.162 |
'). | -0.149 |
Token |
|
Token ID | 198 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
uberty | +0.131 |
taboola | +0.128 |
nered | +0.126 |
sum | +0.115 |
pric | +0.112 |
Neg logit contributions | |
Greek | -0.126 |
Elias | -0.125 |
ascript | -0.122 |
abal | -0.121 |
'). | -0.112 |
Token | E |
Token ID | 36 |
Feature activation | -7.67e-02 |
Pos logit contributions | |
uberty | +0.088 |
taboola | +0.087 |
nered | +0.085 |
sum | +0.078 |
pric | +0.076 |
Neg logit contributions | |
Elias | -0.072 |
Greek | -0.072 |
ascript | -0.070 |
abal | -0.070 |
'). | -0.064 |
Token | minent |
Token ID | 19669 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
Greek | +0.212 |
Elias | +0.211 |
abal | +0.206 |
ascript | +0.204 |
'). | +0.191 |
Neg logit contributions | |
uberty | -0.190 |
taboola | -0.186 |
nered | -0.181 |
sum | -0.164 |
pric | -0.161 |
Token | Domain |
Token ID | 20021 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
uberty | +1.245 |
taboola | +1.220 |
nered | +1.207 |
sum | +1.127 |
pric | +1.080 |
Neg logit contributions | |
Greek | -1.084 |
abal | -1.062 |
Elias | -1.061 |
ascript | -1.053 |
'). | -0.968 |
Token | Issue |
Token ID | 18232 |
Feature activation | -4.92e-03 |
Pos logit contributions | |
Greek | +0.623 |
Elias | +0.618 |
abal | +0.599 |
ascript | +0.598 |
'). | +0.553 |
Neg logit contributions | |
uberty | -0.699 |
taboola | -0.683 |
nered | -0.672 |
sum | -0.614 |
pric | -0.601 |
Token | : |
Token ID | 25 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
Greek | +0.012 |
Elias | +0.012 |
abal | +0.012 |
ascript | +0.012 |
'). | +0.011 |
Neg logit contributions | |
uberty | -0.014 |
taboola | -0.013 |
nered | -0.013 |
sum | -0.012 |
pric | -0.012 |
Token | Business |
Token ID | 7320 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
uberty | +0.050 |
taboola | +0.049 |
nered | +0.048 |
sum | +0.044 |
pric | +0.043 |
Neg logit contributions | |
Greek | -0.048 |
Elias | -0.047 |
abal | -0.046 |
ascript | -0.046 |
'). | -0.042 |
Token | Tr |
Token ID | 833 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
Greek | +0.232 |
Elias | +0.229 |
ascript | +0.223 |
abal | +0.222 |
'). | +0.206 |
Neg logit contributions | |
uberty | -0.251 |
taboola | -0.246 |
nered | -0.241 |
sum | -0.221 |
pric | -0.216 |
Token | the |
Token ID | 262 |
Feature activation | -8.33e-03 |
Pos logit contributions | |
Greek | +0.200 |
Elias | +0.197 |
ascript | +0.193 |
abal | +0.192 |
'). | +0.179 |
Neg logit contributions | |
uberty | -0.185 |
taboola | -0.180 |
nered | -0.178 |
sum | -0.162 |
pric | -0.157 |
Token | statue |
Token ID | 15207 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Greek | +0.020 |
Elias | +0.020 |
abal | +0.019 |
ascript | +0.019 |
'). | +0.018 |
Neg logit contributions | |
uberty | -0.024 |
taboola | -0.023 |
nered | -0.023 |
sum | -0.021 |
pric | -0.021 |
Token | of |
Token ID | 286 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
uberty | +0.345 |
taboola | +0.336 |
nered | +0.332 |
sum | +0.306 |
pric | +0.299 |
Neg logit contributions | |
Greek | -0.302 |
Elias | -0.299 |
abal | -0.290 |
ascript | -0.290 |
'). | -0.268 |
Token | the |
Token ID | 262 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
Greek | +0.052 |
Elias | +0.051 |
ascript | +0.050 |
abal | +0.050 |
'). | +0.045 |
Neg logit contributions | |
uberty | -0.078 |
taboola | -0.076 |
nered | -0.076 |
sum | -0.070 |
pric | -0.069 |
Token | R |
Token ID | 371 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
Greek | +0.051 |
Elias | +0.050 |
ascript | +0.049 |
abal | +0.049 |
'). | +0.045 |
Neg logit contributions | |
uberty | -0.055 |
taboola | -0.054 |
nered | -0.053 |
sum | -0.049 |
pric | -0.048 |
Token | isen |
Token ID | 13254 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
uberty | +0.147 |
taboola | +0.143 |
nered | +0.140 |
sum | +0.129 |
pric | +0.126 |
Neg logit contributions | |
Greek | -0.128 |
Elias | -0.127 |
abal | -0.123 |
ascript | -0.123 |
'). | -0.113 |
Token | Christ |
Token ID | 1951 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
uberty | +1.256 |
taboola | +1.225 |
nered | +1.223 |
sum | +1.141 |
pric | +1.107 |
Neg logit contributions | |
Greek | -1.052 |
ascript | -1.045 |
abal | -1.019 |
Elias | -1.019 |
'). | -0.938 |
Token | that |
Token ID | 326 |
Feature activation | -5.27e-02 |
Pos logit contributions | |
uberty | +0.085 |
taboola | +0.083 |
nered | +0.082 |
sum | +0.075 |
pric | +0.074 |
Neg logit contributions | |
Greek | -0.071 |
Elias | -0.070 |
abal | -0.068 |
ascript | -0.068 |
'). | -0.063 |
Token | currently |
Token ID | 3058 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
Greek | +0.153 |
Elias | +0.151 |
ascript | +0.148 |
abal | +0.148 |
'). | +0.138 |
Neg logit contributions | |
uberty | -0.124 |
taboola | -0.120 |
nered | -0.118 |
sum | -0.107 |
pric | -0.104 |
Token | is |
Token ID | 318 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
uberty | +0.088 |
taboola | +0.085 |
nered | +0.083 |
sum | +0.074 |
pric | +0.072 |
Neg logit contributions | |
Greek | -0.132 |
Elias | -0.131 |
ascript | -0.128 |
abal | -0.128 |
'). | -0.120 |
Token | mounted |
Token ID | 12623 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
Greek | +0.101 |
Elias | +0.101 |
ascript | +0.098 |
abal | +0.098 |
'). | +0.092 |
Neg logit contributions | |
uberty | -0.087 |
taboola | -0.085 |
nered | -0.083 |
sum | -0.075 |
pric | -0.074 |
Token | Hills |
Token ID | 14379 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
uberty | +0.128 |
taboola | +0.125 |
nered | +0.123 |
sum | +0.115 |
pric | +0.112 |
Neg logit contributions | |
Greek | -0.092 |
Elias | -0.090 |
ascript | -0.087 |
abal | -0.087 |
'). | -0.080 |
Token | , |
Token ID | 11 |
Feature activation | +6.78e-02 |
Pos logit contributions | |
Greek | +0.266 |
Elias | +0.262 |
abal | +0.253 |
ascript | +0.253 |
'). | +0.231 |
Neg logit contributions | |
uberty | -0.390 |
taboola | -0.382 |
nered | -0.375 |
sum | -0.348 |
pric | -0.342 |
Token | California |
Token ID | 3442 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
uberty | +0.170 |
taboola | +0.166 |
nered | +0.163 |
sum | +0.148 |
pric | +0.145 |
Neg logit contributions | |
Greek | -0.186 |
Elias | -0.183 |
abal | -0.179 |
ascript | -0.179 |
'). | -0.166 |
Token | . |
Token ID | 13 |
Feature activation | -2.64e-03 |
Pos logit contributions | |
Greek | +0.274 |
Elias | +0.268 |
ascript | +0.259 |
abal | +0.258 |
'). | +0.238 |
Neg logit contributions | |
uberty | -0.427 |
taboola | -0.417 |
nered | -0.410 |
sum | -0.380 |
pric | -0.372 |
Token | Hide |
Token ID | 10415 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
Greek | +0.005 |
Elias | +0.005 |
ascript | +0.005 |
abal | +0.004 |
'). | +0.004 |
Neg logit contributions | |
uberty | -0.009 |
taboola | -0.009 |
nered | -0.009 |
sum | -0.008 |
pric | -0.008 |
Token | Caption |
Token ID | 11260 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
Greek | +0.074 |
Elias | +0.073 |
ascript | +0.072 |
abal | +0.071 |
'). | +0.066 |
Neg logit contributions | |
uberty | -0.068 |
taboola | -0.067 |
nered | -0.065 |
sum | -0.059 |
pric | -0.058 |
Token | 14 |
Token ID | 1478 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
taboola | +1.223 |
uberty | +1.198 |
nered | +1.184 |
sum | +1.099 |
pric | +1.062 |
Neg logit contributions | |
ascript | -1.031 |
Greek | -1.022 |
Elias | -1.020 |
abal | -1.007 |
'). | -0.906 |
Token | of |
Token ID | 286 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
uberty | +0.283 |
taboola | +0.281 |
nered | +0.275 |
sum | +0.251 |
pric | +0.243 |
Neg logit contributions | |
Greek | -0.305 |
Elias | -0.303 |
ascript | -0.298 |
abal | -0.295 |
'). | -0.273 |
Token | 15 |
Token ID | 1315 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
uberty | +0.080 |
taboola | +0.079 |
nered | +0.078 |
sum | +0.072 |
pric | +0.070 |
Neg logit contributions | |
Greek | -0.070 |
Elias | -0.069 |
ascript | -0.068 |
abal | -0.068 |
'). | -0.062 |
Token | Photos |
Token ID | 9434 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
uberty | +0.050 |
taboola | +0.050 |
nered | +0.049 |
sum | +0.044 |
pric | +0.043 |
Neg logit contributions | |
Greek | -0.060 |
Elias | -0.059 |
ascript | -0.059 |
abal | -0.058 |
'). | -0.054 |
Token | : |
Token ID | 25 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
taboola | +0.496 |
uberty | +0.490 |
nered | +0.483 |
sum | +0.448 |
pric | +0.430 |
Neg logit contributions | |
Greek | -0.431 |
ascript | -0.429 |
Elias | -0.428 |
abal | -0.416 |
'). | -0.377 |
Token | aga |
Token ID | 8126 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
Greek | +0.099 |
Elias | +0.098 |
ascript | +0.095 |
abal | +0.095 |
'). | +0.088 |
Neg logit contributions | |
uberty | -0.109 |
taboola | -0.106 |
nered | -0.105 |
sum | -0.096 |
pric | -0.094 |
Token | , |
Token ID | 11 |
Feature activation | +7.38e-02 |
Pos logit contributions | |
Greek | +0.226 |
Elias | +0.223 |
ascript | +0.216 |
abal | +0.215 |
'). | +0.197 |
Neg logit contributions | |
uberty | -0.323 |
taboola | -0.316 |
nered | -0.311 |
sum | -0.287 |
pric | -0.282 |
Token | California |
Token ID | 3442 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
uberty | +0.189 |
taboola | +0.185 |
nered | +0.182 |
sum | +0.166 |
pric | +0.162 |
Neg logit contributions | |
Greek | -0.197 |
Elias | -0.194 |
ascript | -0.191 |
abal | -0.190 |
'). | -0.176 |
Token | . |
Token ID | 13 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
Greek | +0.277 |
Elias | +0.273 |
ascript | +0.263 |
abal | +0.263 |
'). | +0.240 |
Neg logit contributions | |
uberty | -0.437 |
taboola | -0.428 |
nered | -0.421 |
sum | -0.390 |
pric | -0.382 |
Token | Hide |
Token ID | 10415 |
Feature activation | -4.52e-02 |
Pos logit contributions | |
Greek | +0.018 |
Elias | +0.018 |
ascript | +0.017 |
abal | +0.017 |
'). | +0.015 |
Neg logit contributions | |
uberty | -0.036 |
taboola | -0.036 |
nered | -0.035 |
sum | -0.033 |
pric | -0.032 |
Token | Caption |
Token ID | 11260 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
Greek | +0.124 |
Elias | +0.122 |
ascript | +0.120 |
abal | +0.119 |
'). | +0.110 |
Neg logit contributions | |
uberty | -0.113 |
taboola | -0.112 |
nered | -0.108 |
sum | -0.099 |
pric | -0.096 |
Token | 13 |
Token ID | 1511 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
taboola | +1.116 |
uberty | +1.114 |
nered | +1.081 |
sum | +0.988 |
pric | +0.959 |
Neg logit contributions | |
Greek | -1.156 |
Elias | -1.144 |
ascript | -1.134 |
abal | -1.119 |
'). | -1.030 |
Token | of |
Token ID | 286 |
Feature activation | +4.39e-02 |
Pos logit contributions | |
uberty | +0.054 |
taboola | +0.053 |
nered | +0.052 |
sum | +0.047 |
pric | +0.046 |
Neg logit contributions | |
Greek | -0.057 |
Elias | -0.057 |
ascript | -0.056 |
abal | -0.055 |
'). | -0.051 |
Token | 15 |
Token ID | 1315 |
Feature activation | -8.42e-03 |
Pos logit contributions | |
uberty | +0.121 |
taboola | +0.120 |
nered | +0.118 |
sum | +0.109 |
pric | +0.106 |
Neg logit contributions | |
Greek | -0.107 |
Elias | -0.106 |
ascript | -0.104 |
abal | -0.104 |
'). | -0.095 |
Token | Photos |
Token ID | 9434 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
Greek | +0.024 |
Elias | +0.023 |
ascript | +0.023 |
abal | +0.023 |
'). | +0.021 |
Neg logit contributions | |
uberty | -0.020 |
taboola | -0.020 |
nered | -0.019 |
sum | -0.018 |
pric | -0.017 |
Token | : |
Token ID | 25 |
Feature activation | +6.92e-03 |
Pos logit contributions | |
taboola | +0.520 |
uberty | +0.514 |
nered | +0.507 |
sum | +0.471 |
pric | +0.451 |
Neg logit contributions | |
Greek | -0.453 |
ascript | -0.450 |
Elias | -0.450 |
abal | -0.437 |
'). | -0.396 |
Token | up |
Token ID | 510 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
Greek | +0.044 |
Elias | +0.043 |
abal | +0.042 |
ascript | +0.042 |
'). | +0.039 |
Neg logit contributions | |
uberty | -0.035 |
taboola | -0.034 |
nered | -0.033 |
sum | -0.030 |
pric | -0.030 |
Token | small |
Token ID | 1402 |
Feature activation | +6.38e-02 |
Pos logit contributions | |
uberty | +0.112 |
taboola | +0.109 |
nered | +0.107 |
sum | +0.098 |
pric | +0.095 |
Neg logit contributions | |
Greek | -0.139 |
Elias | -0.137 |
abal | -0.134 |
ascript | -0.134 |
'). | -0.126 |
Token | Bitcoin |
Token ID | 6185 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
uberty | +0.155 |
taboola | +0.151 |
nered | +0.148 |
sum | +0.135 |
pric | +0.131 |
Neg logit contributions | |
Greek | -0.180 |
Elias | -0.178 |
abal | -0.174 |
ascript | -0.173 |
'). | -0.162 |
Token | and |
Token ID | 290 |
Feature activation | +5.71e-02 |
Pos logit contributions | |
uberty | +0.098 |
taboola | +0.095 |
nered | +0.093 |
sum | +0.084 |
pric | +0.082 |
Neg logit contributions | |
Greek | -0.118 |
Elias | -0.117 |
abal | -0.114 |
ascript | -0.113 |
'). | -0.106 |
Token | Ethereum |
Token ID | 20313 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
uberty | +0.165 |
taboola | +0.164 |
nered | +0.161 |
sum | +0.150 |
pric | +0.147 |
Neg logit contributions | |
Greek | -0.131 |
Elias | -0.129 |
abal | -0.127 |
ascript | -0.126 |
'). | -0.116 |
Token | mining |
Token ID | 9691 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
uberty | +0.344 |
taboola | +0.336 |
nered | +0.329 |
sum | +0.299 |
pric | +0.291 |
Neg logit contributions | |
Greek | -0.397 |
Elias | -0.394 |
abal | -0.384 |
ascript | -0.383 |
'). | -0.358 |
Token | operations |
Token ID | 4560 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
uberty | +0.800 |
taboola | +0.797 |
nered | +0.771 |
sum | +0.703 |
pric | +0.667 |
Neg logit contributions | |
Greek | -1.466 |
Elias | -1.445 |
ascript | -1.428 |
abal | -1.423 |
'). | -1.339 |
Token | , |
Token ID | 11 |
Feature activation | +1.45e-03 |
Pos logit contributions | |
uberty | +0.285 |
taboola | +0.281 |
nered | +0.276 |
sum | +0.253 |
pric | +0.245 |
Neg logit contributions | |
Greek | -0.301 |
Elias | -0.297 |
abal | -0.290 |
ascript | -0.290 |
'). | -0.269 |
Token | just |
Token ID | 655 |
Feature activation | +8.78e-02 |
Pos logit contributions | |
uberty | +0.004 |
taboola | +0.003 |
nered | +0.003 |
sum | +0.003 |
pric | +0.003 |
Neg logit contributions | |
Greek | -0.004 |
Elias | -0.004 |
abal | -0.004 |
ascript | -0.004 |
'). | -0.004 |
Token | done |
Token ID | 1760 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
uberty | +0.219 |
taboola | +0.215 |
nered | +0.210 |
sum | +0.192 |
pric | +0.187 |
Neg logit contributions | |
Greek | -0.241 |
Elias | -0.238 |
abal | -0.233 |
ascript | -0.232 |
'). | -0.216 |
Token | in |
Token ID | 287 |
Feature activation | +7.03e-03 |
Pos logit contributions | |
uberty | +0.356 |
taboola | +0.351 |
nered | +0.344 |
sum | +0.315 |
pric | +0.305 |
Neg logit contributions | |
Greek | -0.429 |
Elias | -0.421 |
abal | -0.413 |
ascript | -0.411 |
'). | -0.385 |
Token | OTT |
Token ID | 29089 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
uberty | +0.291 |
taboola | +0.285 |
nered | +0.279 |
sum | +0.254 |
pric | +0.249 |
Neg logit contributions | |
Greek | -0.288 |
Elias | -0.286 |
ascript | -0.279 |
abal | -0.278 |
'). | -0.257 |
Token | MOR |
Token ID | 35208 |
Feature activation | +5.65e-03 |
Pos logit contributions | |
uberty | +0.085 |
taboola | +0.082 |
nered | +0.081 |
sum | +0.073 |
pric | +0.071 |
Neg logit contributions | |
Greek | -0.090 |
Elias | -0.089 |
abal | -0.087 |
ascript | -0.086 |
'). | -0.081 |
Token | GAN |
Token ID | 45028 |
Feature activation | +5.97e-02 |
Pos logit contributions | |
uberty | +0.018 |
taboola | +0.018 |
nered | +0.017 |
sum | +0.016 |
pric | +0.016 |
Neg logit contributions | |
Greek | -0.012 |
Elias | -0.011 |
ascript | -0.011 |
abal | -0.011 |
'). | -0.010 |
Token | / |
Token ID | 14 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
uberty | +0.171 |
taboola | +0.167 |
nered | +0.164 |
sum | +0.150 |
pric | +0.147 |
Neg logit contributions | |
Greek | -0.143 |
Elias | -0.142 |
abal | -0.137 |
ascript | -0.137 |
'). | -0.126 |
Token | RE |
Token ID | 2200 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
uberty | +0.336 |
taboola | +0.329 |
nered | +0.324 |
sum | +0.300 |
pric | +0.296 |
Neg logit contributions | |
Greek | -0.206 |
Elias | -0.205 |
abal | -0.197 |
ascript | -0.196 |
'). | -0.177 |
Token | UTERS |
Token ID | 14974 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
uberty | +0.239 |
taboola | +0.233 |
nered | +0.226 |
sum | +0.200 |
pric | +0.195 |
Neg logit contributions | |
Greek | -0.361 |
Elias | -0.359 |
abal | -0.351 |
ascript | -0.350 |
'). | -0.329 |
Token | Supporters |
Token ID | 39995 |
Feature activation | +4.45e-02 |
Pos logit contributions | |
uberty | +1.130 |
taboola | +1.110 |
nered | +1.083 |
sum | +0.996 |
pric | +0.968 |
Neg logit contributions | |
Greek | -1.150 |
Elias | -1.122 |
ascript | -1.119 |
abal | -1.114 |
'). | -1.024 |
Token | of |
Token ID | 286 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
uberty | +0.107 |
taboola | +0.105 |
nered | +0.103 |
sum | +0.096 |
pric | +0.092 |
Neg logit contributions | |
Greek | -0.125 |
Elias | -0.123 |
abal | -0.121 |
ascript | -0.121 |
λ | -0.112 |
Token | Democratic |
Token ID | 4390 |
Feature activation | +8.91e-02 |
Pos logit contributions | |
Greek | +0.034 |
Elias | +0.034 |
abal | +0.033 |
ascript | +0.033 |
'). | +0.031 |
Neg logit contributions | |
uberty | -0.031 |
taboola | -0.030 |
nered | -0.029 |
sum | -0.026 |
pric | -0.026 |
Token | presidential |
Token ID | 4787 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
uberty | +0.237 |
taboola | +0.233 |
nered | +0.228 |
sum | +0.209 |
pric | +0.205 |
Neg logit contributions | |
Greek | -0.230 |
Elias | -0.227 |
abal | -0.222 |
ascript | -0.222 |
'). | -0.205 |
Token | hopeful |
Token ID | 17836 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
uberty | +0.490 |
taboola | +0.479 |
nered | +0.473 |
sum | +0.436 |
pric | +0.427 |
Neg logit contributions | |
Greek | -0.466 |
Elias | -0.456 |
ascript | -0.450 |
abal | -0.448 |
'). | -0.412 |
Token | 2011 |
Token ID | 2813 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
Greek | +0.084 |
Elias | +0.083 |
ascript | +0.082 |
abal | +0.080 |
'). | +0.073 |
Neg logit contributions | |
uberty | -0.123 |
taboola | -0.121 |
nered | -0.119 |
sum | -0.110 |
pric | -0.108 |
Token | United |
Token ID | 1578 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
Greek | +0.265 |
Elias | +0.262 |
abal | +0.254 |
ascript | +0.253 |
'). | +0.233 |
Neg logit contributions | |
uberty | -0.335 |
taboola | -0.327 |
nered | -0.321 |
sum | -0.295 |
pric | -0.290 |
Token | States |
Token ID | 1829 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
Greek | +0.102 |
Elias | +0.101 |
abal | +0.098 |
ascript | +0.098 |
'). | +0.092 |
Neg logit contributions | |
uberty | -0.077 |
taboola | -0.075 |
nered | -0.073 |
sum | -0.065 |
pric | -0.064 |
Token | 228 |
Token ID | 29041 |
Feature activation | -9.18e-02 |
Pos logit contributions | |
Greek | +0.333 |
Elias | +0.330 |
ascript | +0.322 |
abal | +0.321 |
'). | +0.298 |
Neg logit contributions | |
uberty | -0.324 |
taboola | -0.316 |
nered | -0.310 |
sum | -0.282 |
pric | -0.276 |
Token | 65 |
Token ID | 2996 |
Feature activation | -8.46e-02 |
Pos logit contributions | |
Greek | +0.243 |
Elias | +0.241 |
abal | +0.234 |
ascript | +0.233 |
'). | +0.217 |
Neg logit contributions | |
uberty | -0.240 |
taboola | -0.233 |
nered | -0.229 |
sum | -0.208 |
pric | -0.204 |
Token | Posts |
Token ID | 12043 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
Greek | +0.283 |
Elias | +0.282 |
abal | +0.275 |
ascript | +0.272 |
'). | +0.259 |
Neg logit contributions | |
uberty | -0.163 |
taboola | -0.156 |
nered | -0.152 |
sum | -0.132 |
pric | -0.129 |
Token | # |
Token ID | 1303 |
Feature activation | +9.36e-02 |
Pos logit contributions | |
uberty | +1.188 |
taboola | +1.150 |
nered | +1.141 |
sum | +1.049 |
pric | +1.020 |
Neg logit contributions | |
Greek | -1.105 |
Elias | -1.089 |
abal | -1.053 |
ascript | -1.052 |
'). | -0.980 |
Token | 13 |
Token ID | 1485 |
Feature activation | -5.78e-02 |
Pos logit contributions | |
uberty | +0.254 |
taboola | +0.249 |
nered | +0.244 |
sum | +0.223 |
pric | +0.218 |
Neg logit contributions | |
Greek | -0.236 |
Elias | -0.235 |
abal | -0.228 |
ascript | -0.227 |
'). | -0.210 |
Token | On |
Token ID | 1550 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Greek | +0.153 |
Elias | +0.152 |
abal | +0.147 |
ascript | +0.147 |
'). | +0.137 |
Neg logit contributions | |
uberty | -0.151 |
taboola | -0.147 |
nered | -0.144 |
sum | -0.131 |
pric | -0.128 |
Token | September |
Token ID | 2693 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
uberty | +0.310 |
taboola | +0.302 |
nered | +0.296 |
sum | +0.269 |
pric | +0.262 |
Neg logit contributions | |
Greek | -0.359 |
Elias | -0.355 |
abal | -0.346 |
ascript | -0.346 |
'). | -0.322 |
Token | 20 |
Token ID | 1160 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
uberty | +0.041 |
taboola | +0.040 |
nered | +0.039 |
sum | +0.036 |
pric | +0.035 |
Neg logit contributions | |
Greek | -0.038 |
Elias | -0.037 |
ascript | -0.036 |
abal | -0.036 |
'). | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
uberty | +0.214 |
taboola | +0.211 |
nered | +0.208 |
sum | +0.193 |
pric | +0.189 |
Neg logit contributions | |
Greek | -0.132 |
Elias | -0.131 |
abal | -0.126 |
ascript | -0.126 |
'). | -0.113 |
Token | [ |
Token ID | 685 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
Greek | +0.043 |
Elias | +0.042 |
abal | +0.041 |
ascript | +0.041 |
'). | +0.038 |
Neg logit contributions | |
uberty | -0.054 |
taboola | -0.053 |
nered | -0.052 |
sum | -0.048 |
pric | -0.047 |
Token | color |
Token ID | 8043 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
uberty | +0.435 |
taboola | +0.426 |
nered | +0.416 |
sum | +0.376 |
pric | +0.368 |
Neg logit contributions | |
Greek | -0.483 |
Elias | -0.481 |
abal | -0.466 |
ascript | -0.465 |
'). | -0.434 |
Token | = |
Token ID | 28 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
Greek | +0.031 |
Elias | +0.031 |
abal | +0.030 |
ascript | +0.030 |
'). | +0.028 |
Neg logit contributions | |
uberty | -0.034 |
taboola | -0.033 |
nered | -0.033 |
sum | -0.030 |
pric | -0.029 |
Token | red |
Token ID | 445 |
Feature activation | -4.91e-02 |
Pos logit contributions | |
uberty | +0.290 |
taboola | +0.284 |
nered | +0.279 |
sum | +0.253 |
pric | +0.246 |
Neg logit contributions | |
Elias | -0.301 |
Greek | -0.299 |
abal | -0.291 |
ascript | -0.290 |
'). | -0.269 |
Token | ][ |
Token ID | 7131 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
Greek | +0.110 |
Elias | +0.109 |
abal | +0.105 |
ascript | +0.105 |
'). | +0.096 |
Neg logit contributions | |
uberty | -0.148 |
taboola | -0.145 |
nered | -0.142 |
sum | -0.131 |
pric | -0.129 |
Token | b |
Token ID | 65 |
Feature activation | +8.96e-02 |
Pos logit contributions | |
uberty | +1.124 |
taboola | +1.114 |
nered | +1.089 |
sum | +0.984 |
pric | +0.964 |
Neg logit contributions | |
Elias | -1.143 |
Greek | -1.136 |
abal | -1.092 |
ascript | -1.092 |
'). | -1.012 |
Token | ] |
Token ID | 60 |
Feature activation | +9.34e-02 |
Pos logit contributions | |
uberty | +0.302 |
taboola | +0.298 |
nered | +0.293 |
sum | +0.273 |
pric | +0.267 |
Neg logit contributions | |
Greek | -0.166 |
Elias | -0.165 |
ascript | -0.159 |
abal | -0.157 |
'). | -0.141 |
Token | U |
Token ID | 52 |
Feature activation | +5.27e-02 |
Pos logit contributions | |
uberty | +0.269 |
taboola | +0.264 |
nered | +0.259 |
sum | +0.238 |
pric | +0.233 |
Neg logit contributions | |
Greek | -0.219 |
Elias | -0.219 |
ascript | -0.212 |
abal | -0.211 |
'). | -0.194 |
Token | f |
Token ID | 69 |
Feature activation | +9.63e-02 |
Pos logit contributions | |
uberty | +0.142 |
taboola | +0.139 |
nered | +0.136 |
sum | +0.124 |
pric | +0.122 |
Neg logit contributions | |
Greek | -0.135 |
Elias | -0.134 |
abal | -0.130 |
ascript | -0.129 |
'). | -0.120 |
Token | ou |
Token ID | 280 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
uberty | +0.270 |
taboola | +0.264 |
nered | +0.259 |
sum | +0.237 |
pric | +0.233 |
Neg logit contributions | |
Greek | -0.236 |
Elias | -0.234 |
abal | -0.227 |
ascript | -0.226 |
'). | -0.209 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
uberty | +0.149 |
taboola | +0.146 |
nered | +0.144 |
sum | +0.134 |
pric | +0.131 |
Neg logit contributions | |
Greek | -0.106 |
Elias | -0.105 |
ascript | -0.104 |
abal | -0.102 |
'). | -0.093 |
Token | United |
Token ID | 1578 |
Feature activation | +6.43e-02 |
Pos logit contributions | |
Greek | +0.077 |
Elias | +0.076 |
ascript | +0.074 |
abal | +0.074 |
'). | +0.068 |
Neg logit contributions | |
uberty | -0.095 |
taboola | -0.093 |
nered | -0.091 |
sum | -0.084 |
pric | -0.082 |
Token | States |
Token ID | 1829 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
uberty | +0.145 |
taboola | +0.141 |
nered | +0.137 |
sum | +0.122 |
pric | +0.120 |
Neg logit contributions | |
Greek | -0.193 |
Elias | -0.192 |
abal | -0.186 |
ascript | -0.186 |
'). | -0.175 |
Token | 10 |
Token ID | 838 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
Greek | +0.042 |
Elias | +0.042 |
ascript | +0.041 |
abal | +0.041 |
'). | +0.038 |
Neg logit contributions | |
uberty | -0.041 |
taboola | -0.040 |
nered | -0.039 |
sum | -0.036 |
pric | -0.035 |
Token | 53 |
Token ID | 4310 |
Feature activation | +3.01e-03 |
Pos logit contributions | |
Greek | +0.051 |
Elias | +0.051 |
ascript | +0.049 |
abal | +0.049 |
'). | +0.045 |
Neg logit contributions | |
uberty | -0.059 |
taboola | -0.058 |
nered | -0.057 |
sum | -0.052 |
pric | -0.051 |
Token | Posts |
Token ID | 12043 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
uberty | +0.006 |
taboola | +0.006 |
nered | +0.006 |
sum | +0.005 |
pric | +0.005 |
Neg logit contributions | |
Greek | -0.010 |
Elias | -0.010 |
abal | -0.010 |
ascript | -0.010 |
'). | -0.009 |
Token | # |
Token ID | 1303 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
uberty | +1.181 |
taboola | +1.145 |
nered | +1.134 |
sum | +1.041 |
pric | +1.013 |
Neg logit contributions | |
Greek | -1.093 |
Elias | -1.078 |
abal | -1.043 |
ascript | -1.041 |
'). | -0.969 |
Token | 15 |
Token ID | 1314 |
Feature activation | -6.85e-02 |
Pos logit contributions | |
uberty | +0.310 |
taboola | +0.307 |
nered | +0.300 |
sum | +0.277 |
pric | +0.271 |
Neg logit contributions | |
Elias | -0.247 |
Greek | -0.247 |
ascript | -0.239 |
abal | -0.238 |
'). | -0.217 |
Token | honestly |
Token ID | 12698 |
Feature activation | -4.04e-03 |
Pos logit contributions | |
Greek | +0.182 |
Elias | +0.181 |
abal | +0.176 |
ascript | +0.175 |
'). | +0.163 |
Neg logit contributions | |
uberty | -0.178 |
taboola | -0.173 |
nered | -0.170 |
sum | -0.154 |
pric | -0.151 |
Token | if |
Token ID | 611 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
Greek | +0.010 |
Elias | +0.010 |
abal | +0.010 |
ascript | +0.010 |
'). | +0.009 |
Neg logit contributions | |
uberty | -0.011 |
taboola | -0.010 |
nered | -0.010 |
sum | -0.009 |
pric | -0.009 |
Token | we |
Token ID | 356 |
Feature activation | -5.42e-02 |
Pos logit contributions | |
uberty | +0.063 |
taboola | +0.061 |
nered | +0.060 |
sum | +0.054 |
pric | +0.053 |
Neg logit contributions | |
Greek | -0.070 |
Elias | -0.070 |
abal | -0.068 |
ascript | -0.068 |
'). | -0.063 |
Token | gas |
Token ID | 3623 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
Greek | +0.649 |
Elias | +0.644 |
abal | +0.628 |
ascript | +0.626 |
'). | +0.591 |
Neg logit contributions | |
uberty | -0.434 |
taboola | -0.419 |
nered | -0.408 |
sum | -0.360 |
pric | -0.351 |
Token | , |
Token ID | 11 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
uberty | +0.602 |
taboola | +0.593 |
nered | +0.581 |
sum | +0.537 |
pric | +0.529 |
Neg logit contributions | |
Greek | -0.524 |
Elias | -0.520 |
ascript | -0.507 |
abal | -0.507 |
'). | -0.465 |
Token | but |
Token ID | 475 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
uberty | +0.241 |
taboola | +0.235 |
nered | +0.229 |
sum | +0.210 |
pric | +0.205 |
Neg logit contributions | |
Greek | -0.292 |
Elias | -0.287 |
ascript | -0.284 |
abal | -0.283 |
'). | -0.263 |
Token | Hawai |
Token ID | 10847 |
Feature activation | -5.69e-02 |
Pos logit contributions | |
uberty | +0.241 |
taboola | +0.234 |
nered | +0.229 |
sum | +0.210 |
pric | +0.205 |
Neg logit contributions | |
Greek | -0.290 |
Elias | -0.286 |
ascript | -0.282 |
abal | -0.282 |
'). | -0.261 |
Token | ` |
Token ID | 63 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
Greek | +0.123 |
Elias | +0.122 |
ascript | +0.118 |
abal | +0.117 |
'). | +0.106 |
Neg logit contributions | |
uberty | -0.176 |
taboola | -0.172 |
nered | -0.169 |
sum | -0.157 |
pric | -0.154 |
Token | i |
Token ID | 72 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
Greek | +0.039 |
Elias | +0.038 |
ascript | +0.037 |
abal | +0.037 |
'). | +0.035 |
Neg logit contributions | |
uberty | -0.032 |
taboola | -0.031 |
nered | -0.030 |
sum | -0.027 |
pric | -0.027 |
Token | ` |
Token ID | 63 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
uberty | +1.056 |
taboola | +1.030 |
nered | +1.011 |
sum | +0.921 |
pric | +0.901 |
Neg logit contributions | |
Greek | -1.187 |
Elias | -1.176 |
ascript | -1.153 |
abal | -1.143 |
'). | -1.060 |
Token | s |
Token ID | 82 |
Feature activation | +6.52e-02 |
Pos logit contributions | |
Greek | +0.273 |
Elias | +0.271 |
abal | +0.263 |
ascript | +0.263 |
'). | +0.244 |
Neg logit contributions | |
uberty | -0.262 |
taboola | -0.257 |
nered | -0.251 |
sum | -0.228 |
pric | -0.223 |
Token | utilities |
Token ID | 20081 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
uberty | +0.153 |
taboola | +0.149 |
nered | +0.145 |
sum | +0.131 |
pric | +0.128 |
Neg logit contributions | |
Greek | -0.189 |
Elias | -0.188 |
abal | -0.183 |
ascript | -0.183 |
'). | -0.171 |
Token | face |
Token ID | 1986 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
uberty | +0.024 |
taboola | +0.023 |
nered | +0.023 |
sum | +0.021 |
pric | +0.020 |
Neg logit contributions | |
Greek | -0.037 |
Elias | -0.037 |
ascript | -0.036 |
abal | -0.036 |
'). | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | +9.27e-02 |
Pos logit contributions | |
uberty | +0.054 |
taboola | +0.053 |
nered | +0.052 |
sum | +0.047 |
pric | +0.046 |
Neg logit contributions | |
Greek | -0.075 |
Elias | -0.075 |
ascript | -0.073 |
abal | -0.073 |
'). | -0.068 |
Token | Entertainment |
Token ID | 11058 |
Feature activation | +9.85e-02 |
Pos logit contributions | |
uberty | +0.266 |
taboola | +0.259 |
nered | +0.255 |
sum | +0.233 |
pric | +0.228 |
Neg logit contributions | |
Greek | -0.260 |
Elias | -0.258 |
abal | -0.251 |
ascript | -0.250 |
'). | -0.233 |
Token | | |
Token ID | 930 |
Feature activation | -6.28e-02 |
Pos logit contributions | |
uberty | +0.265 |
taboola | +0.259 |
nered | +0.254 |
sum | +0.233 |
pric | +0.229 |
Neg logit contributions | |
Greek | -0.252 |
Elias | -0.249 |
abal | -0.242 |
ascript | -0.241 |
'). | -0.225 |
Token | Streaming |
Token ID | 43124 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Greek | +0.157 |
Elias | +0.157 |
abal | +0.151 |
ascript | +0.150 |
'). | +0.140 |
Neg logit contributions | |
uberty | -0.173 |
taboola | -0.169 |
nered | -0.165 |
sum | -0.151 |
pric | -0.148 |
Token | Every |
Token ID | 3887 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
uberty | +0.331 |
taboola | +0.322 |
nered | +0.316 |
sum | +0.286 |
pric | +0.281 |
Neg logit contributions | |
Greek | -0.338 |
Elias | -0.336 |
abal | -0.325 |
ascript | -0.324 |
'). | -0.302 |
Token | Es |
Token ID | 8678 |
Feature activation | -5.54e-03 |
Pos logit contributions | |
uberty | +0.101 |
taboola | +0.098 |
nered | +0.096 |
sum | +0.086 |
pric | +0.083 |
Neg logit contributions | |
Greek | -0.147 |
Elias | -0.146 |
abal | -0.143 |
ascript | -0.142 |
'). | -0.134 |
Token | port |
Token ID | 634 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
Greek | +0.016 |
Elias | +0.016 |
abal | +0.016 |
ascript | +0.016 |
'). | +0.015 |
Neg logit contributions | |
uberty | -0.013 |
taboola | -0.013 |
nered | -0.012 |
sum | -0.011 |
pric | -0.011 |
Token | Under |
Token ID | 4698 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
uberty | +1.126 |
taboola | +1.095 |
nered | +1.078 |
sum | +0.984 |
pric | +0.965 |
Neg logit contributions | |
Greek | -1.118 |
Elias | -1.107 |
ascript | -1.081 |
abal | -1.075 |
'). | -0.998 |
Token | the |
Token ID | 262 |
Feature activation | +8.28e-02 |
Pos logit contributions | |
uberty | +0.043 |
taboola | +0.042 |
nered | +0.041 |
sum | +0.037 |
pric | +0.037 |
Neg logit contributions | |
Greek | -0.043 |
Elias | -0.043 |
abal | -0.042 |
ascript | -0.041 |
'). | -0.039 |
Token | Sun |
Token ID | 3825 |
Feature activation | +4.70e-02 |
Pos logit contributions | |
uberty | +0.206 |
taboola | +0.202 |
nered | +0.197 |
sum | +0.178 |
pric | +0.175 |
Neg logit contributions | |
Greek | -0.229 |
Elias | -0.227 |
abal | -0.221 |
ascript | -0.220 |
'). | -0.205 |
Token |
|
Token ID | 198 |
Feature activation | +8.14e-02 |
Pos logit contributions | |
uberty | +0.127 |
taboola | +0.124 |
nered | +0.122 |
sum | +0.111 |
pric | +0.109 |
Neg logit contributions | |
Greek | -0.120 |
Elias | -0.119 |
abal | -0.115 |
ascript | -0.115 |
'). | -0.106 |
Token |
|
Token ID | 198 |
Feature activation | +6.39e-02 |
Pos logit contributions | |
uberty | +0.217 |
taboola | +0.213 |
nered | +0.209 |
sum | +0.191 |
pric | +0.187 |
Neg logit contributions | |
Greek | -0.208 |
Elias | -0.207 |
ascript | -0.201 |
abal | -0.200 |
'). | -0.185 |
Token | . |
Token ID | 13 |
Feature activation | +3.08e-03 |
Pos logit contributions | |
Greek | +0.233 |
Elias | +0.232 |
abal | +0.223 |
ascript | +0.222 |
'). | +0.203 |
Neg logit contributions | |
uberty | -0.341 |
taboola | -0.334 |
nered | -0.329 |
sum | -0.303 |
pric | -0.299 |
Token |
|
Token ID | 198 |
Feature activation | +9.40e-02 |
Pos logit contributions | |
uberty | +0.008 |
taboola | +0.008 |
nered | +0.008 |
sum | +0.007 |
pric | +0.007 |
Neg logit contributions | |
Greek | -0.008 |
Elias | -0.008 |
abal | -0.008 |
ascript | -0.008 |
'). | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +9.81e-02 |
Pos logit contributions | |
uberty | +0.251 |
taboola | +0.247 |
nered | +0.241 |
sum | +0.220 |
pric | +0.215 |
Neg logit contributions | |
Greek | -0.240 |
Elias | -0.239 |
ascript | -0.233 |
abal | -0.232 |
'). | -0.214 |
Token | South |
Token ID | 14942 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
uberty | +0.286 |
taboola | +0.281 |
nered | +0.275 |
sum | +0.252 |
pric | +0.248 |
Neg logit contributions | |
Greek | -0.227 |
Elias | -0.227 |
ascript | -0.220 |
abal | -0.220 |
'). | -0.201 |
Token | Sudan |
Token ID | 19610 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
uberty | +0.116 |
taboola | +0.113 |
nered | +0.111 |
sum | +0.101 |
pric | +0.099 |
Neg logit contributions | |
Greek | -0.113 |
Elias | -0.112 |
abal | -0.109 |
ascript | -0.109 |
'). | -0.101 |
Token | ese |
Token ID | 2771 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
uberty | +0.666 |
taboola | +0.650 |
nered | +0.641 |
sum | +0.587 |
pric | +0.575 |
Neg logit contributions | |
Greek | -0.563 |
Elias | -0.558 |
ascript | -0.540 |
abal | -0.539 |
'). | -0.497 |
Token | military |
Token ID | 2422 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
uberty | +1.030 |
taboola | +1.000 |
nered | +0.982 |
sum | +0.891 |
pric | +0.865 |
Neg logit contributions | |
Greek | -1.218 |
Elias | -1.200 |
ascript | -1.179 |
abal | -1.175 |
'). | -1.094 |
Token | parade |
Token ID | 16134 |
Feature activation | +7.36e-02 |
Pos logit contributions | |
uberty | +0.153 |
taboola | +0.149 |
nered | +0.145 |
sum | +0.131 |
pric | +0.128 |
Neg logit contributions | |
Greek | -0.186 |
Elias | -0.184 |
abal | -0.179 |
ascript | -0.179 |
'). | -0.167 |
Token | during |
Token ID | 1141 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
uberty | +0.185 |
taboola | +0.181 |
nered | +0.177 |
sum | +0.160 |
pric | +0.157 |
Neg logit contributions | |
Greek | -0.201 |
Elias | -0.199 |
abal | -0.194 |
ascript | -0.194 |
'). | -0.180 |
Token | a |
Token ID | 257 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
uberty | +0.283 |
taboola | +0.275 |
nered | +0.269 |
sum | +0.243 |
pric | +0.237 |
Neg logit contributions | |
Greek | -0.334 |
Elias | -0.331 |
abal | -0.322 |
ascript | -0.322 |
'). | -0.300 |
Token | ceremony |
Token ID | 10542 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
uberty | +0.026 |
taboola | +0.026 |
nered | +0.025 |
sum | +0.023 |
pric | +0.022 |
Neg logit contributions | |
Greek | -0.031 |
Elias | -0.031 |
abal | -0.030 |
ascript | -0.030 |
'). | -0.028 |
Token | June |
Token ID | 2795 |
Feature activation | +7.22e-02 |
Pos logit contributions | |
uberty | +0.262 |
taboola | +0.255 |
nered | +0.249 |
sum | +0.224 |
pric | +0.218 |
Neg logit contributions | |
Greek | -0.358 |
Elias | -0.354 |
ascript | -0.348 |
abal | -0.346 |
'). | -0.324 |
Token | 2009 |
Token ID | 3717 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
uberty | +0.222 |
taboola | +0.218 |
nered | +0.215 |
sum | +0.199 |
pric | +0.196 |
Neg logit contributions | |
Greek | -0.155 |
Elias | -0.153 |
ascript | -0.151 |
abal | -0.148 |
'). | -0.135 |
Token | Germany |
Token ID | 4486 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
Greek | +0.255 |
Elias | +0.253 |
abal | +0.244 |
ascript | +0.243 |
'). | +0.223 |
Neg logit contributions | |
uberty | -0.331 |
taboola | -0.324 |
nered | -0.318 |
sum | -0.293 |
pric | -0.288 |
Token | 247 |
Token ID | 30179 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
Greek | +0.107 |
Elias | +0.106 |
ascript | +0.104 |
abal | +0.103 |
'). | +0.096 |
Neg logit contributions | |
uberty | -0.103 |
taboola | -0.101 |
nered | -0.099 |
sum | -0.090 |
pric | -0.088 |
Token | 34 |
Token ID | 2682 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
Greek | +0.048 |
Elias | +0.048 |
abal | +0.046 |
ascript | +0.046 |
'). | +0.043 |
Neg logit contributions | |
uberty | -0.039 |
taboola | -0.038 |
nered | -0.037 |
sum | -0.033 |
pric | -0.033 |
Token | Posts |
Token ID | 12043 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
Greek | +0.049 |
Elias | +0.049 |
abal | +0.048 |
ascript | +0.047 |
'). | +0.045 |
Neg logit contributions | |
uberty | -0.028 |
taboola | -0.027 |
nered | -0.026 |
sum | -0.022 |
pric | -0.022 |
Token | # |
Token ID | 1303 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
uberty | +1.168 |
taboola | +1.131 |
nered | +1.120 |
sum | +1.029 |
pric | +1.001 |
Neg logit contributions | |
Greek | -1.072 |
Elias | -1.058 |
abal | -1.023 |
ascript | -1.021 |
'). | -0.950 |
Token | 20 |
Token ID | 1238 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
uberty | +0.111 |
taboola | +0.109 |
nered | +0.107 |
sum | +0.099 |
pric | +0.098 |
Neg logit contributions | |
Greek | -0.072 |
Elias | -0.072 |
abal | -0.069 |
ascript | -0.069 |
'). | -0.063 |
Token | Nice |
Token ID | 18460 |
Feature activation | -3.38e-03 |
Pos logit contributions | |
Greek | +0.506 |
Elias | +0.504 |
abal | +0.489 |
ascript | +0.484 |
'). | +0.453 |
Neg logit contributions | |
uberty | -0.501 |
taboola | -0.489 |
nered | -0.478 |
sum | -0.432 |
pric | -0.425 |
Token | , |
Token ID | 11 |
Feature activation | -6.10e-02 |
Pos logit contributions | |
Greek | +0.010 |
Elias | +0.009 |
ascript | +0.009 |
abal | +0.009 |
'). | +0.009 |
Neg logit contributions | |
uberty | -0.008 |
taboola | -0.008 |
nered | -0.008 |
sum | -0.007 |
pric | -0.007 |
Token | happy |
Token ID | 3772 |
Feature activation | +8.35e-02 |
Pos logit contributions | |
Greek | +0.171 |
Elias | +0.170 |
abal | +0.165 |
ascript | +0.164 |
'). | +0.153 |
Neg logit contributions | |
uberty | -0.150 |
taboola | -0.146 |
nered | -0.142 |
sum | -0.128 |
pric | -0.126 |
Token | a |
Token ID | 257 |
Feature activation | +8.67e-02 |
Pos logit contributions | |
uberty | +0.144 |
taboola | +0.139 |
nered | +0.138 |
sum | +0.126 |
pric | +0.123 |
Neg logit contributions | |
Greek | -0.160 |
Elias | -0.158 |
abal | -0.155 |
ascript | -0.155 |
'). | -0.144 |
Token | children |
Token ID | 1751 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
uberty | +0.191 |
taboola | +0.185 |
nered | +0.181 |
sum | +0.162 |
pric | +0.158 |
Neg logit contributions | |
Greek | -0.264 |
Elias | -0.263 |
abal | -0.256 |
ascript | -0.256 |
'). | -0.240 |
Token | 's |
Token ID | 338 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
uberty | +0.357 |
taboola | +0.349 |
nered | +0.345 |
sum | +0.318 |
pric | +0.312 |
Neg logit contributions | |
Greek | -0.265 |
Elias | -0.264 |
abal | -0.254 |
ascript | -0.253 |
'). | -0.232 |
Token | pop |
Token ID | 1461 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
uberty | +0.446 |
taboola | +0.434 |
nered | +0.425 |
sum | +0.384 |
pric | +0.376 |
Neg logit contributions | |
Greek | -0.495 |
Elias | -0.491 |
abal | -0.478 |
ascript | -0.476 |
'). | -0.444 |
Token | music |
Token ID | 2647 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
uberty | +0.673 |
taboola | +0.654 |
nered | +0.643 |
sum | +0.585 |
pric | +0.572 |
Neg logit contributions | |
Greek | -0.690 |
Elias | -0.684 |
abal | -0.665 |
ascript | -0.662 |
'). | -0.616 |
Token | style |
Token ID | 3918 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
uberty | +0.541 |
taboola | +0.527 |
nered | +0.519 |
sum | +0.475 |
pric | +0.464 |
Neg logit contributions | |
Greek | -0.535 |
Elias | -0.529 |
abal | -0.515 |
ascript | -0.514 |
'). | -0.477 |
Token | and |
Token ID | 290 |
Feature activation | +8.66e-02 |
Pos logit contributions | |
uberty | +1.277 |
taboola | +1.248 |
nered | +1.243 |
sum | +1.151 |
pric | +1.119 |
Neg logit contributions | |
Greek | -0.946 |
Elias | -0.932 |
abal | -0.907 |
ascript | -0.891 |
'). | -0.829 |
Token | contrast |
Token ID | 6273 |
Feature activation | +9.99e-02 |
Pos logit contributions | |
uberty | +0.194 |
taboola | +0.188 |
nered | +0.184 |
sum | +0.165 |
pric | +0.161 |
Neg logit contributions | |
Greek | -0.261 |
Elias | -0.259 |
abal | -0.253 |
ascript | -0.252 |
'). | -0.236 |
Token | sharply |
Token ID | 18939 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
uberty | +0.234 |
taboola | +0.228 |
nered | +0.223 |
sum | +0.200 |
pric | +0.195 |
Neg logit contributions | |
Greek | -0.291 |
Elias | -0.289 |
abal | -0.281 |
ascript | -0.280 |
'). | -0.263 |
Token | with |
Token ID | 351 |
Feature activation | +5.76e-02 |
Pos logit contributions | |
uberty | +0.135 |
taboola | +0.131 |
nered | +0.129 |
sum | +0.117 |
pric | +0.114 |
Neg logit contributions | |
Greek | -0.150 |
Elias | -0.150 |
abal | -0.146 |
ascript | -0.145 |
'). | -0.135 |
Token | the |
Token ID | 262 |
Feature activation | +5.99e-02 |
Pos logit contributions | |
uberty | +0.143 |
taboola | +0.138 |
nered | +0.136 |
sum | +0.124 |
pric | +0.121 |
Neg logit contributions | |
Greek | -0.160 |
Elias | -0.158 |
abal | -0.155 |
ascript | -0.154 |
'). | -0.144 |
Token | an |
Token ID | 281 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
Greek | +0.194 |
Elias | +0.193 |
abal | +0.188 |
ascript | +0.187 |
'). | +0.175 |
Neg logit contributions | |
uberty | -0.157 |
taboola | -0.153 |
nered | -0.150 |
sum | -0.135 |
pric | -0.131 |
Token | extra |
Token ID | 3131 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
Greek | +0.306 |
Elias | +0.303 |
abal | +0.296 |
ascript | +0.295 |
'). | +0.276 |
Neg logit contributions | |
uberty | -0.248 |
taboola | -0.241 |
nered | -0.236 |
sum | -0.212 |
pric | -0.207 |
Token | nomination |
Token ID | 11872 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
Greek | +0.156 |
Elias | +0.155 |
abal | +0.151 |
ascript | +0.151 |
'). | +0.142 |
Neg logit contributions | |
uberty | -0.107 |
taboola | -0.104 |
nered | -0.101 |
sum | -0.090 |
pric | -0.088 |
Token | — |
Token ID | 960 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
Greek | +0.477 |
Elias | +0.469 |
ascript | +0.457 |
abal | +0.457 |
'). | +0.421 |
Neg logit contributions | |
uberty | -0.579 |
taboola | -0.567 |
nered | -0.558 |
sum | -0.517 |
pric | -0.505 |
Token | crit |
Token ID | 22213 |
Feature activation | -8.08e-02 |
Pos logit contributions | |
Greek | +0.449 |
Elias | +0.446 |
abal | +0.432 |
ascript | +0.430 |
'). | +0.398 |
Neg logit contributions | |
uberty | -0.506 |
taboola | -0.494 |
nered | -0.485 |
sum | -0.443 |
pric | -0.435 |
Token | ics |
Token ID | 873 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
Greek | +0.159 |
Elias | +0.158 |
abal | +0.152 |
ascript | +0.151 |
'). | +0.136 |
Neg logit contributions | |
uberty | -0.265 |
taboola | -0.259 |
nered | -0.256 |
sum | -0.237 |
pric | -0.234 |
Token | couldn |
Token ID | 3521 |
Feature activation | -4.68e-02 |
Pos logit contributions | |
Elias | +1.446 |
Greek | +1.441 |
abal | +1.394 |
ascript | +1.385 |
'). | +1.309 |
Neg logit contributions | |
uberty | -1.235 |
taboola | -1.199 |
nered | -1.168 |
sum | -1.042 |
pric | -1.028 |
Token | 't |
Token ID | 470 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
Greek | +0.146 |
Elias | +0.145 |
abal | +0.142 |
ascript | +0.140 |
'). | +0.133 |
Neg logit contributions | |
uberty | -0.100 |
taboola | -0.097 |
nered | -0.094 |
sum | -0.084 |
pric | -0.082 |
Token | decide |
Token ID | 5409 |
Feature activation | +7.45e-03 |
Pos logit contributions | |
Greek | +0.084 |
Elias | +0.084 |
abal | +0.081 |
ascript | +0.081 |
'). | +0.076 |
Neg logit contributions | |
uberty | -0.061 |
taboola | -0.059 |
nered | -0.058 |
sum | -0.051 |
pric | -0.050 |
Token | if |
Token ID | 611 |
Feature activation | -9.86e-03 |
Pos logit contributions | |
uberty | +0.019 |
taboola | +0.018 |
nered | +0.018 |
sum | +0.016 |
pric | +0.016 |
Neg logit contributions | |
Greek | -0.020 |
Elias | -0.020 |
abal | -0.020 |
ascript | -0.019 |
'). | -0.018 |
Token | those |
Token ID | 883 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
Greek | +0.028 |
Elias | +0.028 |
abal | +0.027 |
ascript | +0.027 |
'). | +0.025 |
Neg logit contributions | |
uberty | -0.024 |
taboola | -0.023 |
nered | -0.022 |
sum | -0.020 |
pric | -0.020 |
Token | are |
Token ID | 389 |
Feature activation | -1.99e-03 |
Pos logit contributions | |
uberty | +0.018 |
taboola | +0.017 |
nered | +0.017 |
sum | +0.015 |
pric | +0.015 |
Neg logit contributions | |
Greek | -0.025 |
Elias | -0.025 |
ascript | -0.025 |
abal | -0.025 |
'). | -0.023 |
Token | in |
Token ID | 287 |
Feature activation | +2.64e-03 |
Pos logit contributions | |
Greek | +0.006 |
Elias | +0.006 |
abal | +0.006 |
ascript | +0.006 |
'). | +0.006 |
Neg logit contributions | |
uberty | -0.004 |
taboola | -0.004 |
nered | -0.004 |
sum | -0.004 |
pric | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +4.62e-03 |
Pos logit contributions | |
uberty | +0.007 |
taboola | +0.006 |
nered | +0.006 |
sum | +0.006 |
pric | +0.006 |
Neg logit contributions | |
Greek | -0.007 |
Elias | -0.007 |
abal | -0.007 |
ascript | -0.007 |
'). | -0.007 |
Token | nond |
Token ID | 30745 |
Feature activation | -9.85e-02 |
Pos logit contributions | |
uberty | +0.010 |
taboola | +0.010 |
nered | +0.009 |
sum | +0.008 |
pric | +0.008 |
Neg logit contributions | |
Greek | -0.014 |
Elias | -0.014 |
abal | -0.014 |
ascript | -0.014 |
'). | -0.013 |
Token | esc |
Token ID | 3798 |
Feature activation | +8.78e-02 |
Pos logit contributions | |
Greek | +0.248 |
Elias | +0.246 |
abal | +0.239 |
ascript | +0.238 |
'). | +0.220 |
Neg logit contributions | |
uberty | -0.269 |
taboola | -0.263 |
nered | -0.257 |
sum | -0.235 |
pric | -0.231 |
Token | ript |
Token ID | 1968 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
uberty | +0.186 |
taboola | +0.178 |
nered | +0.176 |
sum | +0.156 |
pric | +0.152 |
Neg logit contributions | |
Greek | -0.277 |
Elias | -0.273 |
ascript | -0.268 |
abal | -0.266 |
'). | -0.250 |
Token | pre |
Token ID | 662 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
Greek | +1.380 |
Elias | +1.373 |
abal | +1.343 |
ascript | +1.318 |
'). | +1.250 |
Neg logit contributions | |
uberty | -1.055 |
taboola | -1.033 |
nered | -0.990 |
sum | -0.869 |
pric | -0.853 |
Token | war |
Token ID | 5767 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
Greek | +0.605 |
Elias | +0.591 |
abal | +0.583 |
ascript | +0.577 |
'). | +0.541 |
Neg logit contributions | |
uberty | -0.505 |
taboola | -0.489 |
nered | -0.482 |
sum | -0.429 |
pric | -0.422 |
Token | building |
Token ID | 2615 |
Feature activation | -5.33e-02 |
Pos logit contributions | |
uberty | +0.350 |
taboola | +0.340 |
nered | +0.332 |
sum | +0.296 |
pric | +0.290 |
Neg logit contributions | |
Greek | -0.458 |
Elias | -0.455 |
abal | -0.443 |
ascript | -0.442 |
'). | -0.415 |
Token | overlooking |
Token ID | 34603 |
Feature activation | -5.70e-02 |
Pos logit contributions | |
Greek | +0.144 |
Elias | +0.143 |
abal | +0.139 |
ascript | +0.138 |
'). | +0.128 |
Neg logit contributions | |
uberty | -0.137 |
taboola | -0.133 |
nered | -0.130 |
sum | -0.117 |
pric | -0.115 |
Token | Herald |
Token ID | 18277 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
Greek | +0.156 |
Elias | +0.155 |
abal | +0.150 |
ascript | +0.149 |
'). | +0.140 |
Neg logit contributions | |
uberty | -0.143 |
taboola | -0.140 |
nered | -0.137 |
sum | -0.123 |
pric | -0.121 |
Token | from |
Token ID | 422 |
Feature activation | -6.18e-02 |
Pos logit contributions | |
Greek | +0.479 |
Elias | +0.476 |
abal | +0.462 |
ascript | +0.460 |
'). | +0.428 |
Neg logit contributions | |
uberty | -0.480 |
taboola | -0.468 |
nered | -0.458 |
sum | -0.416 |
pric | -0.409 |
Token | Chern |
Token ID | 37243 |
Feature activation | -8.25e-02 |
Pos logit contributions | |
Greek | +0.175 |
Elias | +0.174 |
abal | +0.170 |
ascript | +0.169 |
'). | +0.158 |
Neg logit contributions | |
uberty | -0.149 |
taboola | -0.145 |
nered | -0.142 |
sum | -0.128 |
pric | -0.125 |
Token | obyl |
Token ID | 46666 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
Greek | +0.274 |
Elias | +0.272 |
abal | +0.265 |
ascript | +0.265 |
'). | +0.250 |
Neg logit contributions | |
uberty | -0.160 |
taboola | -0.154 |
nered | -0.150 |
sum | -0.131 |
pric | -0.127 |
Token | , |
Token ID | 11 |
Feature activation | -8.08e-02 |
Pos logit contributions | |
Greek | +0.303 |
Elias | +0.300 |
abal | +0.291 |
ascript | +0.291 |
'). | +0.270 |
Neg logit contributions | |
uberty | -0.312 |
taboola | -0.304 |
nered | -0.298 |
sum | -0.272 |
pric | -0.266 |
Token | but |
Token ID | 475 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
Greek | +0.231 |
Elias | +0.229 |
abal | +0.223 |
ascript | +0.223 |
'). | +0.208 |
Neg logit contributions | |
uberty | -0.193 |
taboola | -0.188 |
nered | -0.184 |
sum | -0.166 |
pric | -0.162 |
Token | Greenpeace |
Token ID | 42793 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
Greek | +0.094 |
Elias | +0.093 |
abal | +0.091 |
ascript | +0.091 |
'). | +0.085 |
Neg logit contributions | |
uberty | -0.075 |
taboola | -0.073 |
nered | -0.072 |
sum | -0.065 |
pric | -0.063 |
Token | has |
Token ID | 468 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
Greek | +1.278 |
Elias | +1.270 |
abal | +1.236 |
ascript | +1.229 |
'). | +1.150 |
Neg logit contributions | |
uberty | -1.134 |
taboola | -1.104 |
nered | -1.081 |
sum | -0.973 |
pric | -0.954 |
Token | said |
Token ID | 531 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Greek | +0.117 |
Elias | +0.116 |
abal | +0.113 |
ascript | +0.113 |
'). | +0.106 |
Neg logit contributions | |
uberty | -0.087 |
taboola | -0.085 |
nered | -0.083 |
sum | -0.075 |
pric | -0.073 |
Token | that |
Token ID | 326 |
Feature activation | -8.76e-02 |
Pos logit contributions | |
Greek | +0.389 |
Elias | +0.387 |
abal | +0.376 |
ascript | +0.374 |
'). | +0.350 |
Neg logit contributions | |
uberty | -0.333 |
taboola | -0.325 |
nered | -0.318 |
sum | -0.285 |
pric | -0.279 |
Token | the |
Token ID | 262 |
Feature activation | -5.63e-02 |
Pos logit contributions | |
Greek | +0.258 |
Elias | +0.257 |
abal | +0.250 |
ascript | +0.249 |
'). | +0.234 |
Neg logit contributions | |
uberty | -0.202 |
taboola | -0.196 |
nered | -0.192 |
sum | -0.172 |
pric | -0.168 |
Token | disaster |
Token ID | 9336 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
Greek | +0.160 |
Elias | +0.159 |
abal | +0.155 |
ascript | +0.154 |
'). | +0.144 |
Neg logit contributions | |
uberty | -0.136 |
taboola | -0.132 |
nered | -0.129 |
sum | -0.116 |
pric | -0.114 |
Token | is |
Token ID | 318 |
Feature activation | -4.40e-02 |
Pos logit contributions | |
Greek | +0.071 |
Elias | +0.070 |
abal | +0.068 |
ascript | +0.068 |
'). | +0.064 |
Neg logit contributions | |
uberty | -0.051 |
taboola | -0.050 |
nered | -0.048 |
sum | -0.043 |
pric | -0.042 |
Token | something |
Token ID | 1223 |
Feature activation | -6.64e-03 |
Pos logit contributions | |
Greek | +0.132 |
Elias | +0.131 |
abal | +0.128 |
ascript | +0.128 |
'). | +0.120 |
Neg logit contributions | |
uberty | -0.098 |
taboola | -0.096 |
nered | -0.094 |
sum | -0.085 |
pric | -0.082 |
Token | of |
Token ID | 286 |
Feature activation | -9.97e-03 |
Pos logit contributions | |
Greek | +0.019 |
Elias | +0.019 |
ascript | +0.018 |
abal | +0.018 |
'). | +0.017 |
Neg logit contributions | |
uberty | -0.016 |
taboola | -0.015 |
nered | -0.015 |
sum | -0.014 |
pric | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
Greek | +0.029 |
Elias | +0.029 |
abal | +0.028 |
ascript | +0.028 |
'). | +0.026 |
Neg logit contributions | |
uberty | -0.023 |
taboola | -0.022 |
nered | -0.022 |
sum | -0.020 |
pric | -0.019 |
Token | vind |
Token ID | 29178 |
Feature activation | -7.27e-02 |
Pos logit contributions | |
Greek | +0.120 |
Elias | +0.119 |
abal | +0.116 |
ascript | +0.115 |
'). | +0.108 |
Neg logit contributions | |
uberty | -0.096 |
taboola | -0.093 |
nered | -0.091 |
sum | -0.082 |
pric | -0.080 |
Token | ication |
Token ID | 3299 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
Greek | +0.182 |
Elias | +0.180 |
ascript | +0.176 |
abal | +0.173 |
'). | +0.161 |
Neg logit contributions | |
uberty | -0.200 |
taboola | -0.194 |
nered | -0.193 |
sum | -0.176 |
pric | -0.171 |
Token | of |
Token ID | 286 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
Greek | +1.115 |
Elias | +1.112 |
abal | +1.077 |
ascript | +1.065 |
'). | +0.986 |
Neg logit contributions | |
uberty | -1.273 |
taboola | -1.241 |
nered | -1.214 |
sum | -1.104 |
pric | -1.086 |
Token | Democratic |
Token ID | 4390 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
Greek | +0.140 |
Elias | +0.137 |
ascript | +0.135 |
abal | +0.135 |
'). | +0.126 |
Neg logit contributions | |
uberty | -0.112 |
taboola | -0.108 |
nered | -0.108 |
sum | -0.098 |
pric | -0.095 |
Token | strategic |
Token ID | 10039 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
uberty | +0.106 |
taboola | +0.104 |
nered | +0.102 |
sum | +0.092 |
pric | +0.090 |
Neg logit contributions | |
Greek | -0.133 |
Elias | -0.132 |
ascript | -0.129 |
abal | -0.129 |
'). | -0.120 |
Token | thinking |
Token ID | 3612 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
Greek | +0.058 |
Elias | +0.057 |
ascript | +0.056 |
abal | +0.056 |
'). | +0.052 |
Neg logit contributions | |
uberty | -0.046 |
taboola | -0.045 |
nered | -0.044 |
sum | -0.040 |
pric | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
Greek | +0.256 |
Elias | +0.253 |
abal | +0.245 |
ascript | +0.245 |
'). | +0.224 |
Neg logit contributions | |
uberty | -0.343 |
taboola | -0.337 |
nered | -0.334 |
sum | -0.309 |
pric | -0.302 |
Token | astronauts |
Token ID | 26835 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
Greek | +0.049 |
Elias | +0.048 |
ascript | +0.048 |
abal | +0.047 |
'). | +0.044 |
Neg logit contributions | |
uberty | -0.039 |
taboola | -0.038 |
nered | -0.037 |
sum | -0.033 |
pric | -0.032 |
Token | Thomas |
Token ID | 5658 |
Feature activation | +5.75e-02 |
Pos logit contributions | |
Greek | +0.390 |
Elias | +0.384 |
abal | +0.377 |
ascript | +0.376 |
'). | +0.352 |
Neg logit contributions | |
uberty | -0.282 |
taboola | -0.274 |
nered | -0.268 |
sum | -0.242 |
pric | -0.236 |
Token | Pes |
Token ID | 38434 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
uberty | +0.159 |
taboola | +0.155 |
nered | +0.153 |
sum | +0.140 |
pric | +0.137 |
Neg logit contributions | |
Greek | -0.142 |
Elias | -0.140 |
ascript | -0.137 |
abal | -0.137 |
'). | -0.126 |
Token | quet |
Token ID | 21108 |
Feature activation | -8.73e-02 |
Pos logit contributions | |
uberty | +0.030 |
taboola | +0.029 |
nered | +0.029 |
sum | +0.026 |
pric | +0.025 |
Neg logit contributions | |
Greek | -0.029 |
Elias | -0.028 |
ascript | -0.028 |
abal | -0.027 |
'). | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | -6.71e-02 |
Pos logit contributions | |
Greek | +0.211 |
Elias | +0.210 |
abal | +0.203 |
ascript | +0.202 |
'). | +0.187 |
Neg logit contributions | |
uberty | -0.247 |
taboola | -0.241 |
nered | -0.237 |
sum | -0.217 |
pric | -0.213 |
Token | Peggy |
Token ID | 40910 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
Greek | +0.155 |
Elias | +0.152 |
abal | +0.149 |
ascript | +0.149 |
'). | +0.136 |
Neg logit contributions | |
uberty | -0.197 |
taboola | -0.193 |
nered | -0.190 |
sum | -0.175 |
pric | -0.172 |
Token | Wh |
Token ID | 854 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
Elias | +1.349 |
Greek | +1.268 |
abal | +1.243 |
Evangel | +1.196 |
'). | +1.192 |
Neg logit contributions | |
taboola | -1.064 |
uberty | -1.055 |
nered | -0.996 |
aturdays | -0.888 |
sum | -0.869 |
Token | its |
Token ID | 896 |
Feature activation | +8.81e-02 |
Pos logit contributions | |
uberty | +0.481 |
taboola | +0.463 |
nered | +0.460 |
sum | +0.417 |
pric | +0.406 |
Neg logit contributions | |
Greek | -0.457 |
Elias | -0.452 |
ascript | -0.437 |
abal | -0.433 |
'). | -0.404 |
Token | on |
Token ID | 261 |
Feature activation | -2.47e-03 |
Pos logit contributions | |
uberty | +0.221 |
taboola | +0.216 |
nered | +0.211 |
sum | +0.191 |
pric | +0.187 |
Neg logit contributions | |
Greek | -0.241 |
Elias | -0.239 |
abal | -0.233 |
ascript | -0.232 |
'). | -0.216 |
Token | planned |
Token ID | 6027 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
Greek | +0.007 |
Elias | +0.007 |
abal | +0.007 |
ascript | +0.007 |
'). | +0.007 |
Neg logit contributions | |
uberty | -0.006 |
taboola | -0.005 |
nered | -0.005 |
sum | -0.005 |
pric | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
Greek | +0.057 |
Elias | +0.056 |
abal | +0.055 |
ascript | +0.054 |
'). | +0.051 |
Neg logit contributions | |
uberty | -0.048 |
taboola | -0.047 |
nered | -0.046 |
sum | -0.041 |
pric | -0.040 |
Token | start |
Token ID | 923 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
uberty | +0.084 |
taboola | +0.082 |
nered | +0.081 |
sum | +0.073 |
pric | +0.071 |
Neg logit contributions | |
Greek | -0.108 |
Elias | -0.107 |
abal | -0.105 |
ascript | -0.105 |
'). | -0.098 |
Token | opposite |
Token ID | 6697 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
Greek | +0.102 |
Elias | +0.101 |
abal | +0.098 |
ascript | +0.098 |
'). | +0.091 |
Neg logit contributions | |
uberty | -0.110 |
taboola | -0.108 |
nered | -0.106 |
sum | -0.096 |
pric | -0.095 |
Token | Dar |
Token ID | 7491 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
Greek | +0.101 |
Elias | +0.100 |
abal | +0.097 |
ascript | +0.097 |
'). | +0.090 |
Neg logit contributions | |
uberty | -0.102 |
taboola | -0.099 |
nered | -0.098 |
sum | -0.089 |
pric | -0.087 |
Token | rel |
Token ID | 2411 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
Greek | +0.067 |
Elias | +0.067 |
abal | +0.065 |
ascript | +0.065 |
'). | +0.060 |
Neg logit contributions | |
uberty | -0.064 |
taboola | -0.062 |
nered | -0.061 |
sum | -0.055 |
pric | -0.054 |
Token | le |
Token ID | 293 |
Feature activation | +5.92e-02 |
Pos logit contributions | |
uberty | +0.132 |
taboola | +0.126 |
nered | +0.125 |
sum | +0.112 |
pric | +0.110 |
Neg logit contributions | |
Greek | -0.186 |
Elias | -0.183 |
ascript | -0.182 |
abal | -0.181 |
'). | -0.167 |
Token | Revis |
Token ID | 46146 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
uberty | +0.178 |
nered | +0.170 |
taboola | +0.169 |
sum | +0.162 |
pric | +0.157 |
Neg logit contributions | |
Greek | -0.133 |
ascript | -0.131 |
Elias | -0.130 |
abal | -0.125 |
'). | -0.113 |
Token | , |
Token ID | 11 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
Greek | +0.969 |
Elias | +0.967 |
abal | +0.929 |
ascript | +0.919 |
'). | +0.850 |
Neg logit contributions | |
uberty | -1.371 |
taboola | -1.342 |
nered | -1.312 |
sum | -1.207 |
pric | -1.194 |
Token | collected |
Token ID | 7723 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
uberty | +0.083 |
taboola | +0.080 |
nered | +0.079 |
sum | +0.071 |
pric | +0.069 |
Neg logit contributions | |
Greek | -0.096 |
Elias | -0.096 |
abal | -0.093 |
ascript | -0.093 |
'). | -0.087 |
Token | seven |
Token ID | 3598 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
uberty | +0.409 |
taboola | +0.396 |
nered | +0.390 |
sum | +0.355 |
pric | +0.346 |
Neg logit contributions | |
Greek | -0.493 |
Elias | -0.486 |
ascript | -0.477 |
abal | -0.476 |
'). | -0.444 |
Token | more |
Token ID | 517 |
Feature activation | +8.12e-03 |
Pos logit contributions | |
uberty | +0.035 |
taboola | +0.034 |
nered | +0.034 |
sum | +0.031 |
pric | +0.030 |
Neg logit contributions | |
Greek | -0.036 |
Elias | -0.035 |
abal | -0.035 |
ascript | -0.035 |
'). | -0.032 |
Token | tackles |
Token ID | 18034 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
uberty | +0.021 |
taboola | +0.021 |
nered | +0.020 |
sum | +0.019 |
pric | +0.018 |
Neg logit contributions | |
Greek | -0.022 |
Elias | -0.021 |
ascript | -0.021 |
abal | -0.021 |
'). | -0.019 |
Token | : |
Token ID | 25 |
Feature activation | -9.31e-02 |
Pos logit contributions | |
Greek | +0.037 |
Elias | +0.037 |
ascript | +0.037 |
abal | +0.036 |
'). | +0.033 |
Neg logit contributions | |
uberty | -0.046 |
taboola | -0.046 |
nered | -0.045 |
sum | -0.042 |
pric | -0.041 |
Token | 47 |
Token ID | 2857 |
Feature activation | +3.92e-03 |
Pos logit contributions | |
Greek | +0.230 |
Elias | +0.229 |
abal | +0.222 |
ascript | +0.221 |
'). | +0.204 |
Neg logit contributions | |
uberty | -0.259 |
taboola | -0.253 |
nered | -0.248 |
sum | -0.227 |
pric | -0.223 |
Token | ] |
Token ID | 60 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
uberty | +0.013 |
taboola | +0.013 |
nered | +0.013 |
sum | +0.012 |
pric | +0.012 |
Neg logit contributions | |
Greek | -0.007 |
Elias | -0.007 |
ascript | -0.007 |
abal | -0.007 |
'). | -0.006 |
Token | < |
Token ID | 1279 |
Feature activation | -3.19e-03 |
Pos logit contributions | |
Greek | +0.023 |
Elias | +0.022 |
abal | +0.021 |
ascript | +0.021 |
'). | +0.019 |
Neg logit contributions | |
uberty | -0.045 |
taboola | -0.044 |
nered | -0.044 |
sum | -0.041 |
pric | -0.040 |
Token | sn |
Token ID | 16184 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Greek | +0.009 |
Elias | +0.009 |
abal | +0.008 |
ascript | +0.008 |
'). | +0.008 |
Neg logit contributions | |
uberty | -0.008 |
taboola | -0.008 |
nered | -0.008 |
sum | -0.007 |
pric | -0.007 |
Token | iping |
Token ID | 34690 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
uberty | +0.353 |
taboola | +0.343 |
nered | +0.339 |
sum | +0.309 |
pric | +0.304 |
Neg logit contributions | |
Greek | -0.294 |
Elias | -0.292 |
abal | -0.281 |
ascript | -0.280 |
'). | -0.259 |
Token | 117 |
Token ID | 17657 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
Greek | +1.126 |
Elias | +1.115 |
abal | +1.086 |
ascript | +1.079 |
'). | +1.001 |
Neg logit contributions | |
uberty | -1.187 |
taboola | -1.158 |
nered | -1.133 |
sum | -1.034 |
pric | -1.017 |
Token | > |
Token ID | 29 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
Greek | +0.254 |
Elias | +0.253 |
abal | +0.243 |
ascript | +0.243 |
'). | +0.224 |
Neg logit contributions | |
uberty | -0.296 |
taboola | -0.290 |
nered | -0.285 |
sum | -0.261 |
pric | -0.256 |
Token | H |
Token ID | 367 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
Greek | +0.456 |
Elias | +0.454 |
abal | +0.440 |
ascript | +0.436 |
'). | +0.409 |
Neg logit contributions | |
uberty | -0.443 |
taboola | -0.433 |
nered | -0.423 |
sum | -0.380 |
pric | -0.375 |
Token | aha |
Token ID | 12236 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
Greek | +0.043 |
Elias | +0.043 |
abal | +0.041 |
ascript | +0.041 |
'). | +0.038 |
Neg logit contributions | |
uberty | -0.055 |
taboola | -0.053 |
nered | -0.052 |
sum | -0.048 |
pric | -0.047 |
Token | [ |
Token ID | 685 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
Greek | +0.485 |
Elias | +0.482 |
abal | +0.468 |
ascript | +0.464 |
'). | +0.432 |
Neg logit contributions | |
uberty | -0.515 |
taboola | -0.504 |
nered | -0.492 |
sum | -0.446 |
pric | -0.439 |
Token | taken |
Token ID | 2077 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
Greek | +0.081 |
Elias | +0.080 |
abal | +0.079 |
ascript | +0.079 |
'). | +0.073 |
Neg logit contributions | |
uberty | -0.060 |
taboola | -0.058 |
nered | -0.057 |
sum | -0.052 |
pric | -0.051 |
Token | and |
Token ID | 290 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
uberty | +0.053 |
taboola | +0.053 |
nered | +0.052 |
sum | +0.048 |
pric | +0.046 |
Neg logit contributions | |
Greek | -0.058 |
Elias | -0.058 |
ascript | -0.056 |
abal | -0.056 |
'). | -0.052 |
Token | that |
Token ID | 326 |
Feature activation | -4.97e-02 |
Pos logit contributions | |
Greek | +0.033 |
Elias | +0.033 |
abal | +0.032 |
ascript | +0.032 |
'). | +0.030 |
Neg logit contributions | |
uberty | -0.025 |
taboola | -0.024 |
nered | -0.024 |
sum | -0.022 |
pric | -0.021 |
Token | such |
Token ID | 884 |
Feature activation | -8.44e-02 |
Pos logit contributions | |
Greek | +0.145 |
Elias | +0.144 |
ascript | +0.141 |
abal | +0.140 |
'). | +0.131 |
Neg logit contributions | |
uberty | -0.115 |
taboola | -0.113 |
nered | -0.110 |
sum | -0.101 |
pric | -0.098 |
Token | adjud |
Token ID | 33719 |
Feature activation | +7.52e-02 |
Pos logit contributions | |
Greek | +0.255 |
Elias | +0.253 |
ascript | +0.246 |
abal | +0.246 |
'). | +0.231 |
Neg logit contributions | |
uberty | -0.187 |
taboola | -0.183 |
nered | -0.178 |
sum | -0.162 |
pric | -0.157 |
Token | ication |
Token ID | 3299 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
uberty | +0.198 |
taboola | +0.193 |
nered | +0.189 |
sum | +0.172 |
pric | +0.169 |
Neg logit contributions | |
Greek | -0.197 |
Elias | -0.196 |
abal | -0.190 |
ascript | -0.189 |
'). | -0.176 |
Token | can |
Token ID | 460 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
Greek | +1.321 |
Elias | +1.312 |
abal | +1.279 |
ascript | +1.274 |
'). | +1.197 |
Neg logit contributions | |
uberty | -0.992 |
taboola | -0.964 |
nered | -0.941 |
sum | -0.840 |
pric | -0.821 |
Token | be |
Token ID | 307 |
Feature activation | +1.19e-04 |
Pos logit contributions | |
uberty | +0.039 |
taboola | +0.038 |
nered | +0.038 |
sum | +0.034 |
pric | +0.033 |
Neg logit contributions | |
Greek | -0.053 |
Elias | -0.053 |
ascript | -0.051 |
abal | -0.051 |
'). | -0.048 |
Token | acceptable |
Token ID | 10909 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
uberty | +0.000 |
taboola | +0.000 |
nered | +0.000 |
sum | +0.000 |
pric | +0.000 |
Neg logit contributions | |
Greek | -0.000 |
Elias | -0.000 |
abal | -0.000 |
ascript | -0.000 |
'). | -0.000 |
Token | in |
Token ID | 287 |
Feature activation | -3.62e-02 |
Pos logit contributions | |
Greek | +0.091 |
Elias | +0.090 |
ascript | +0.087 |
abal | +0.087 |
'). | +0.081 |
Neg logit contributions | |
uberty | -0.096 |
taboola | -0.095 |
nered | -0.093 |
sum | -0.085 |
pric | -0.083 |
Token | terms |
Token ID | 2846 |
Feature activation | -3.50e-02 |
Pos logit contributions | |
Greek | +0.104 |
Elias | +0.103 |
ascript | +0.100 |
abal | +0.100 |
'). | +0.093 |
Neg logit contributions | |
uberty | -0.086 |
taboola | -0.084 |
nered | -0.082 |
sum | -0.076 |
pric | -0.073 |
Token | MORE |
Token ID | 12011 |
Feature activation | +8.99e-02 |
Pos logit contributions | |
Greek | +0.153 |
ascript | +0.152 |
Elias | +0.150 |
abal | +0.149 |
λ | +0.139 |
Neg logit contributions | |
uberty | -0.112 |
nered | -0.105 |
taboola | -0.102 |
sum | -0.098 |
pric | -0.090 |
Token | and |
Token ID | 290 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
uberty | +0.247 |
taboola | +0.242 |
nered | +0.239 |
sum | +0.218 |
pric | +0.214 |
Neg logit contributions | |
Greek | -0.224 |
Elias | -0.222 |
abal | -0.215 |
ascript | -0.215 |
'). | -0.199 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
Elias | +0.262 |
Greek | +0.262 |
abal | +0.252 |
ascript | +0.251 |
'). | +0.232 |
Neg logit contributions | |
uberty | -0.302 |
taboola | -0.295 |
nered | -0.289 |
sum | -0.264 |
pric | -0.259 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
Elias | +0.440 |
Greek | +0.438 |
abal | +0.421 |
ascript | +0.415 |
'). | +0.388 |
Neg logit contributions | |
uberty | -0.512 |
taboola | -0.499 |
nered | -0.487 |
sum | -0.444 |
pric | -0.439 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
Greek | +0.358 |
Elias | +0.352 |
ascript | +0.340 |
abal | +0.340 |
'). | +0.309 |
Neg logit contributions | |
uberty | -0.548 |
taboola | -0.538 |
nered | -0.530 |
sum | -0.491 |
pric | -0.483 |
Token | Diane |
Token ID | 26542 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
Greek | +0.271 |
Elias | +0.268 |
ascript | +0.266 |
abal | +0.262 |
'). | +0.238 |
Neg logit contributions | |
uberty | -0.395 |
taboola | -0.389 |
nered | -0.382 |
sum | -0.355 |
pric | -0.349 |
Token | Rodham |
Token ID | 41848 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
Greek | +0.768 |
Elias | +0.759 |
abal | +0.718 |
ascript | +0.712 |
'). | +0.645 |
Neg logit contributions | |
uberty | -1.528 |
taboola | -1.499 |
nered | -1.477 |
sum | -1.372 |
pric | -1.356 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -8.20e-02 |
Pos logit contributions | |
Greek | +0.151 |
Elias | +0.150 |
ascript | +0.148 |
abal | +0.147 |
'). | +0.135 |
Neg logit contributions | |
uberty | -0.153 |
taboola | -0.149 |
nered | -0.145 |
sum | -0.134 |
pric | -0.131 |
Token | Sanders |
Token ID | 26747 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Elias | +0.208 |
Greek | +0.205 |
ascript | +0.204 |
abal | +0.201 |
'). | +0.184 |
Neg logit contributions | |
uberty | -0.222 |
taboola | -0.218 |
nered | -0.213 |
sum | -0.194 |
pric | -0.190 |
Token | : |
Token ID | 25 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
Greek | +0.332 |
Elias | +0.330 |
ascript | +0.324 |
abal | +0.322 |
'). | +0.294 |
Neg logit contributions | |
uberty | -0.391 |
taboola | -0.383 |
nered | -0.374 |
sum | -0.345 |
pric | -0.339 |
Token | ' |
Token ID | 705 |
Feature activation | -4.64e-02 |
Pos logit contributions | |
uberty | +0.039 |
taboola | +0.038 |
nered | +0.038 |
sum | +0.035 |
pric | +0.034 |
Neg logit contributions | |
Greek | -0.025 |
Elias | -0.024 |
abal | -0.023 |
ascript | -0.023 |
'). | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
Greek | +0.259 |
Elias | +0.257 |
abal | +0.250 |
ascript | +0.249 |
'). | +0.234 |
Neg logit contributions | |
uberty | -0.197 |
taboola | -0.191 |
nered | -0.186 |
sum | -0.166 |
pric | -0.162 |
Token | look |
Token ID | 804 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
Greek | +0.105 |
Elias | +0.104 |
abal | +0.101 |
ascript | +0.101 |
'). | +0.095 |
Neg logit contributions | |
uberty | -0.080 |
taboola | -0.078 |
nered | -0.076 |
sum | -0.067 |
pric | -0.066 |
Token | at |
Token ID | 379 |
Feature activation | -9.90e-02 |
Pos logit contributions | |
Greek | +0.052 |
Elias | +0.051 |
abal | +0.050 |
ascript | +0.050 |
'). | +0.046 |
Neg logit contributions | |
uberty | -0.052 |
taboola | -0.050 |
nered | -0.049 |
sum | -0.044 |
pric | -0.044 |
Token | a |
Token ID | 257 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
Greek | +0.281 |
Elias | +0.279 |
abal | +0.271 |
ascript | +0.270 |
'). | +0.253 |
Neg logit contributions | |
uberty | -0.239 |
taboola | -0.233 |
nered | -0.228 |
sum | -0.205 |
pric | -0.200 |
Token | strange |
Token ID | 6283 |
Feature activation | +6.11e-02 |
Pos logit contributions | |
Greek | +0.112 |
Elias | +0.111 |
abal | +0.108 |
ascript | +0.108 |
'). | +0.101 |
Neg logit contributions | |
uberty | -0.088 |
taboola | -0.086 |
nered | -0.084 |
sum | -0.075 |
pric | -0.073 |
Token | appar |
Token ID | 17956 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
uberty | +0.144 |
taboola | +0.140 |
nered | +0.138 |
sum | +0.124 |
pric | +0.121 |
Neg logit contributions | |
Greek | -0.176 |
Elias | -0.175 |
abal | -0.170 |
ascript | -0.170 |
'). | -0.159 |
Token | ition |
Token ID | 653 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
Greek | +1.078 |
Elias | +1.064 |
abal | +1.055 |
ascript | +1.040 |
'). | +0.956 |
Neg logit contributions | |
uberty | -1.183 |
taboola | -1.172 |
nered | -1.130 |
sum | -1.026 |
pric | -1.014 |
Token | standing |
Token ID | 5055 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Greek | +0.524 |
Elias | +0.522 |
abal | +0.506 |
ascript | +0.502 |
'). | +0.469 |
Neg logit contributions | |
uberty | -0.502 |
taboola | -0.488 |
nered | -0.476 |
sum | -0.429 |
pric | -0.422 |
Token | in |
Token ID | 287 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
uberty | +0.314 |
taboola | +0.306 |
nered | +0.300 |
sum | +0.272 |
pric | +0.266 |
Neg logit contributions | |
Greek | -0.354 |
Elias | -0.351 |
abal | -0.342 |
ascript | -0.341 |
'). | -0.318 |
Token | the |
Token ID | 262 |
Feature activation | +1.42e-03 |
Pos logit contributions | |
uberty | +0.031 |
taboola | +0.030 |
nered | +0.029 |
sum | +0.027 |
pric | +0.026 |
Neg logit contributions | |
Greek | -0.038 |
Elias | -0.038 |
ascript | -0.037 |
abal | -0.037 |
'). | -0.035 |
Token | security |
Token ID | 2324 |
Feature activation | -7.06e-02 |
Pos logit contributions | |
uberty | +0.003 |
taboola | +0.003 |
nered | +0.003 |
sum | +0.002 |
pric | +0.002 |
Neg logit contributions | |
Greek | -0.004 |
Elias | -0.004 |
abal | -0.004 |
ascript | -0.004 |
'). | -0.004 |
Token | from |
Token ID | 422 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
uberty | +0.104 |
taboola | +0.102 |
nered | +0.100 |
sum | +0.089 |
pric | +0.087 |
Neg logit contributions | |
Greek | -0.136 |
Elias | -0.134 |
abal | -0.131 |
ascript | -0.131 |
'). | -0.122 |
Token | the |
Token ID | 262 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
Greek | +0.074 |
Elias | +0.074 |
abal | +0.072 |
ascript | +0.071 |
'). | +0.067 |
Neg logit contributions | |
uberty | -0.069 |
taboola | -0.067 |
nered | -0.065 |
sum | -0.059 |
pric | -0.058 |
Token | Anaheim |
Token ID | 31100 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
Elias | +0.074 |
Greek | +0.074 |
abal | +0.071 |
ascript | +0.071 |
'). | +0.067 |
Neg logit contributions | |
uberty | -0.065 |
taboola | -0.063 |
nered | -0.062 |
sum | -0.055 |
pric | -0.054 |
Token | and |
Token ID | 290 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
uberty | +0.066 |
taboola | +0.064 |
nered | +0.063 |
sum | +0.058 |
pric | +0.057 |
Neg logit contributions | |
Greek | -0.061 |
Elias | -0.060 |
abal | -0.058 |
ascript | -0.058 |
'). | -0.054 |
Token | Santa |
Token ID | 8909 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
Greek | +0.125 |
Elias | +0.124 |
abal | +0.120 |
ascript | +0.120 |
'). | +0.112 |
Neg logit contributions | |
uberty | -0.117 |
taboola | -0.114 |
nered | -0.112 |
sum | -0.101 |
pric | -0.099 |
Token | Ana |
Token ID | 17639 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
uberty | +0.036 |
taboola | +0.035 |
nered | +0.034 |
sum | +0.032 |
pric | +0.032 |
Neg logit contributions | |
Greek | -0.020 |
Elias | -0.020 |
abal | -0.019 |
ascript | -0.019 |
'). | -0.017 |
Token | police |
Token ID | 1644 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
Elias | +1.233 |
Greek | +1.224 |
abal | +1.193 |
ascript | +1.173 |
'). | +1.113 |
Neg logit contributions | |
uberty | -1.033 |
taboola | -1.001 |
nered | -0.978 |
sum | -0.856 |
pric | -0.846 |
Token | departments |
Token ID | 13346 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
Greek | +0.198 |
Elias | +0.197 |
abal | +0.193 |
ascript | +0.191 |
'). | +0.181 |
Neg logit contributions | |
uberty | -0.119 |
taboola | -0.115 |
nered | -0.111 |
sum | -0.097 |
pric | -0.095 |
Token | attempted |
Token ID | 7482 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
uberty | +0.057 |
taboola | +0.055 |
nered | +0.054 |
sum | +0.049 |
pric | +0.047 |
Neg logit contributions | |
Greek | -0.074 |
Elias | -0.073 |
abal | -0.072 |
ascript | -0.071 |
'). | -0.067 |
Token | to |
Token ID | 284 |
Feature activation | -6.91e-02 |
Pos logit contributions | |
uberty | +0.264 |
taboola | +0.257 |
nered | +0.251 |
sum | +0.225 |
pric | +0.221 |
Neg logit contributions | |
Greek | -0.325 |
Elias | -0.323 |
abal | -0.315 |
ascript | -0.314 |
'). | -0.294 |
Token | apprehend |
Token ID | 30200 |
Feature activation | +8.75e-02 |
Pos logit contributions | |
Greek | +0.220 |
Elias | +0.219 |
abal | +0.214 |
ascript | +0.213 |
'). | +0.201 |
Neg logit contributions | |
uberty | -0.143 |
taboola | -0.138 |
nered | -0.135 |
sum | -0.119 |
pric | -0.116 |
Token | goal |
Token ID | 3061 |
Feature activation | -6.95e-02 |
Pos logit contributions | |
uberty | +0.045 |
taboola | +0.044 |
nered | +0.043 |
sum | +0.039 |
pric | +0.038 |
Neg logit contributions | |
Greek | -0.055 |
Elias | -0.055 |
ascript | -0.053 |
abal | -0.053 |
'). | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | +9.59e-03 |
Pos logit contributions | |
Greek | +0.151 |
Elias | +0.150 |
abal | +0.145 |
ascript | +0.144 |
'). | +0.132 |
Neg logit contributions | |
uberty | -0.214 |
taboola | -0.209 |
nered | -0.206 |
sum | -0.190 |
pric | -0.187 |
Token |
|
Token ID | 198 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
uberty | +0.025 |
taboola | +0.025 |
nered | +0.024 |
sum | +0.022 |
pric | +0.021 |
Neg logit contributions | |
Greek | -0.025 |
Elias | -0.025 |
ascript | -0.024 |
abal | -0.024 |
'). | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
Greek | +0.043 |
Elias | +0.043 |
abal | +0.041 |
ascript | +0.041 |
'). | +0.038 |
Neg logit contributions | |
uberty | -0.046 |
taboola | -0.045 |
nered | -0.045 |
sum | -0.041 |
pric | -0.040 |
Token | Gu |
Token ID | 8205 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
Greek | +0.062 |
Elias | +0.062 |
ascript | +0.060 |
abal | +0.060 |
'). | +0.055 |
Neg logit contributions | |
uberty | -0.069 |
taboola | -0.067 |
nered | -0.066 |
sum | -0.060 |
pric | -0.059 |
Token | il |
Token ID | 346 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
uberty | +0.107 |
taboola | +0.104 |
nered | +0.102 |
sum | +0.095 |
pric | +0.093 |
Neg logit contributions | |
Greek | -0.071 |
Elias | -0.070 |
abal | -0.068 |
ascript | -0.067 |
'). | -0.062 |
Token | her |
Token ID | 372 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
Greek | +1.362 |
Elias | +1.354 |
abal | +1.325 |
ascript | +1.317 |
'). | +1.244 |
Neg logit contributions | |
uberty | -0.898 |
taboola | -0.868 |
nered | -0.848 |
sum | -0.749 |
pric | -0.734 |
Token | me |
Token ID | 1326 |
Feature activation | -7.66e-02 |
Pos logit contributions | |
Greek | +0.344 |
Elias | +0.341 |
abal | +0.332 |
ascript | +0.329 |
'). | +0.310 |
Neg logit contributions | |
uberty | -0.295 |
taboola | -0.284 |
nered | -0.278 |
sum | -0.250 |
pric | -0.247 |
Token | and |
Token ID | 290 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
Greek | +0.196 |
Elias | +0.195 |
abal | +0.189 |
ascript | +0.188 |
'). | +0.175 |
Neg logit contributions | |
uberty | -0.206 |
taboola | -0.201 |
nered | -0.197 |
sum | -0.180 |
pric | -0.177 |
Token | I |
Token ID | 314 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
Greek | +0.046 |
Elias | +0.045 |
abal | +0.044 |
ascript | +0.044 |
'). | +0.040 |
Neg logit contributions | |
uberty | -0.067 |
taboola | -0.066 |
nered | -0.065 |
sum | -0.060 |
pric | -0.059 |
Token | worked |
Token ID | 3111 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
Greek | +0.078 |
Elias | +0.078 |
abal | +0.076 |
ascript | +0.076 |
'). | +0.071 |
Neg logit contributions | |
uberty | -0.064 |
taboola | -0.062 |
nered | -0.061 |
sum | -0.054 |
pric | -0.053 |
Token | in |
Token ID | 287 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
uberty | +0.118 |
taboola | +0.115 |
nered | +0.113 |
sum | +0.103 |
pric | +0.100 |
Neg logit contributions | |
Greek | -0.123 |
Elias | -0.122 |
abal | -0.118 |
ascript | -0.118 |
'). | -0.110 |
Token | the |
Token ID | 262 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
Greek | +0.133 |
Elias | +0.133 |
abal | +0.129 |
ascript | +0.128 |
'). | +0.120 |
Neg logit contributions | |
uberty | -0.115 |
taboola | -0.112 |
nered | -0.109 |
sum | -0.098 |
pric | -0.096 |
Token | South |
Token ID | 2520 |
Feature activation | +7.65e-03 |
Pos logit contributions | |
Greek | +0.111 |
Elias | +0.110 |
abal | +0.107 |
ascript | +0.107 |
'). | +0.100 |
Neg logit contributions | |
uberty | -0.087 |
taboola | -0.085 |
nered | -0.083 |
sum | -0.074 |
pric | -0.072 |
Token | . |
Token ID | 13 |
Feature activation | -8.17e-02 |
Pos logit contributions | |
uberty | +0.024 |
taboola | +0.023 |
nered | +0.023 |
sum | +0.021 |
pric | +0.021 |
Neg logit contributions | |
Greek | -0.016 |
Elias | -0.016 |
abal | -0.016 |
ascript | -0.016 |
'). | -0.014 |
Token | ( |
Token ID | 357 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
Greek | +0.191 |
Elias | +0.189 |
ascript | +0.184 |
abal | +0.183 |
'). | +0.168 |
Neg logit contributions | |
uberty | -0.238 |
taboola | -0.233 |
nered | -0.228 |
sum | -0.210 |
pric | -0.206 |
Token | Photo |
Token ID | 6191 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
Greek | +0.265 |
Elias | +0.265 |
abal | +0.257 |
ascript | +0.257 |
'). | +0.234 |
Neg logit contributions | |
uberty | -0.370 |
taboola | -0.368 |
nered | -0.358 |
sum | -0.330 |
pric | -0.324 |
Token | By |
Token ID | 2750 |
Feature activation | +6.58e-03 |
Pos logit contributions | |
Greek | +1.261 |
Elias | +1.260 |
abal | +1.216 |
ascript | +1.213 |
'). | +1.137 |
Neg logit contributions | |
uberty | -1.001 |
taboola | -0.964 |
nered | -0.946 |
sum | -0.841 |
pric | -0.826 |
Token | Bill |
Token ID | 3941 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
uberty | +0.019 |
taboola | +0.019 |
nered | +0.019 |
sum | +0.017 |
pric | +0.017 |
Neg logit contributions | |
Greek | -0.015 |
Elias | -0.015 |
abal | -0.015 |
ascript | -0.015 |
'). | -0.013 |
Token | Clark |
Token ID | 11264 |
Feature activation | +9.02e-02 |
Pos logit contributions | |
uberty | +0.456 |
taboola | +0.445 |
nered | +0.435 |
sum | +0.396 |
pric | +0.388 |
Neg logit contributions | |
Greek | -0.482 |
Elias | -0.477 |
ascript | -0.466 |
abal | -0.466 |
'). | -0.432 |
Token | / |
Token ID | 14 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
uberty | +0.242 |
taboola | +0.236 |
nered | +0.231 |
sum | +0.211 |
pric | +0.207 |
Neg logit contributions | |
Greek | -0.232 |
Elias | -0.229 |
abal | -0.223 |
ascript | -0.222 |
'). | -0.206 |
Token | C |
Token ID | 34 |
Feature activation | +2.78e-03 |
Pos logit contributions | |
uberty | +0.087 |
taboola | +0.086 |
nered | +0.084 |
sum | +0.077 |
pric | +0.076 |
Neg logit contributions | |
Greek | -0.064 |
Elias | -0.064 |
ascript | -0.062 |
abal | -0.062 |
'). | -0.056 |
Token | by |
Token ID | 416 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
Greek | +0.230 |
Elias | +0.229 |
abal | +0.222 |
ascript | +0.222 |
'). | +0.208 |
Neg logit contributions | |
uberty | -0.185 |
taboola | -0.180 |
nered | -0.175 |
sum | -0.157 |
pric | -0.154 |
Token | NBC |
Token ID | 9716 |
Feature activation | +5.08e-03 |
Pos logit contributions | |
Elias | +0.066 |
Greek | +0.066 |
abal | +0.064 |
ascript | +0.064 |
'). | +0.060 |
Neg logit contributions | |
uberty | -0.061 |
taboola | -0.059 |
nered | -0.058 |
sum | -0.052 |
pric | -0.051 |
Token | News |
Token ID | 3000 |
Feature activation | -7.79e-02 |
Pos logit contributions | |
uberty | +0.013 |
taboola | +0.013 |
nered | +0.013 |
sum | +0.011 |
pric | +0.011 |
Neg logit contributions | |
Greek | -0.014 |
Elias | -0.013 |
abal | -0.013 |
ascript | -0.013 |
'). | -0.012 |
Token | ' |
Token ID | 6 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Greek | +0.213 |
Elias | +0.212 |
abal | +0.206 |
ascript | +0.205 |
'). | +0.192 |
Neg logit contributions | |
uberty | -0.196 |
taboola | -0.191 |
nered | -0.187 |
sum | -0.169 |
pric | -0.165 |
Token | Savannah |
Token ID | 40695 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
Greek | +0.275 |
Elias | +0.274 |
abal | +0.265 |
ascript | +0.264 |
'). | +0.246 |
Neg logit contributions | |
uberty | -0.279 |
taboola | -0.273 |
nered | -0.267 |
sum | -0.242 |
pric | -0.238 |
Token | Guth |
Token ID | 44003 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
Elias | +0.238 |
Greek | +0.235 |
abal | +0.226 |
ascript | +0.220 |
'). | +0.205 |
Neg logit contributions | |
uberty | -0.366 |
taboola | -0.356 |
nered | -0.347 |
sum | -0.317 |
pric | -0.316 |
Token | rie |
Token ID | 5034 |
Feature activation | -5.77e-02 |
Pos logit contributions | |
Greek | +0.779 |
Elias | +0.769 |
abal | +0.757 |
ascript | +0.733 |
'). | +0.669 |
Neg logit contributions | |
uberty | -1.480 |
taboola | -1.439 |
nered | -1.405 |
sum | -1.317 |
pric | -1.310 |
Token | ( |
Token ID | 357 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
Greek | +0.165 |
Elias | +0.164 |
abal | +0.160 |
ascript | +0.159 |
'). | +0.149 |
Neg logit contributions | |
uberty | -0.138 |
taboola | -0.134 |
nered | -0.131 |
sum | -0.118 |
pric | -0.115 |
Token | right |
Token ID | 3506 |
Feature activation | -1.03e-03 |
Pos logit contributions | |
Greek | +0.061 |
Elias | +0.061 |
abal | +0.059 |
ascript | +0.059 |
'). | +0.055 |
Neg logit contributions | |
uberty | -0.046 |
taboola | -0.045 |
nered | -0.044 |
sum | -0.039 |
pric | -0.038 |
Token | ) |
Token ID | 8 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
Greek | +0.002 |
Elias | +0.002 |
abal | +0.002 |
ascript | +0.002 |
'). | +0.001 |
Neg logit contributions | |
uberty | -0.004 |
taboola | -0.004 |
nered | -0.004 |
sum | -0.003 |
pric | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | +7.30e-03 |
Pos logit contributions | |
Greek | +0.352 |
Elias | +0.351 |
abal | +0.341 |
ascript | +0.340 |
'). | +0.318 |
Neg logit contributions | |
uberty | -0.291 |
taboola | -0.282 |
nered | -0.274 |
sum | -0.245 |
pric | -0.242 |
Token | - |
Token ID | 12 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
Greek | +0.175 |
Elias | +0.175 |
abal | +0.169 |
ascript | +0.168 |
'). | +0.159 |
Neg logit contributions | |
uberty | -0.139 |
taboola | -0.136 |
nered | -0.131 |
sum | -0.117 |
pric | -0.115 |
Token | year |
Token ID | 1941 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
Greek | +0.429 |
Elias | +0.424 |
abal | +0.413 |
ascript | +0.412 |
'). | +0.390 |
Neg logit contributions | |
uberty | -0.268 |
taboola | -0.259 |
nered | -0.252 |
sum | -0.222 |
pric | -0.217 |
Token | player |
Token ID | 2137 |
Feature activation | -9.68e-02 |
Pos logit contributions | |
Greek | +0.060 |
Elias | +0.059 |
ascript | +0.058 |
abal | +0.058 |
'). | +0.054 |
Neg logit contributions | |
uberty | -0.048 |
taboola | -0.046 |
nered | -0.045 |
sum | -0.041 |
pric | -0.040 |
Token | Patrick |
Token ID | 9925 |
Feature activation | +4.88e-02 |
Pos logit contributions | |
Greek | +0.232 |
Elias | +0.226 |
ascript | +0.222 |
abal | +0.222 |
'). | +0.204 |
Neg logit contributions | |
uberty | -0.277 |
taboola | -0.270 |
nered | -0.267 |
sum | -0.246 |
pric | -0.240 |
Token | Lip |
Token ID | 24701 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
uberty | +0.125 |
taboola | +0.122 |
nered | +0.119 |
sum | +0.108 |
pric | +0.106 |
Neg logit contributions | |
Greek | -0.131 |
Elias | -0.131 |
abal | -0.127 |
ascript | -0.126 |
'). | -0.118 |
Token | inski |
Token ID | 21141 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
Greek | +0.073 |
Elias | +0.073 |
abal | +0.071 |
ascript | +0.070 |
'). | +0.065 |
Neg logit contributions | |
uberty | -0.083 |
taboola | -0.081 |
nered | -0.079 |
sum | -0.072 |
pric | -0.071 |
Token | will |
Token ID | 481 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
Greek | +1.184 |
Elias | +1.177 |
abal | +1.144 |
ascript | +1.138 |
'). | +1.064 |
Neg logit contributions | |
uberty | -1.055 |
taboola | -1.027 |
nered | -1.004 |
sum | -0.905 |
pric | -0.888 |
Token | require |
Token ID | 2421 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
Greek | +0.134 |
Elias | +0.133 |
ascript | +0.130 |
abal | +0.129 |
'). | +0.122 |
Neg logit contributions | |
uberty | -0.090 |
taboola | -0.087 |
nered | -0.086 |
sum | -0.077 |
pric | -0.074 |
Token | surgery |
Token ID | 8185 |
Feature activation | +6.59e-02 |
Pos logit contributions | |
Greek | +0.089 |
Elias | +0.088 |
abal | +0.086 |
ascript | +0.086 |
'). | +0.081 |
Neg logit contributions | |
uberty | -0.066 |
taboola | -0.063 |
nered | -0.062 |
sum | -0.056 |
pric | -0.055 |
Token | after |
Token ID | 706 |
Feature activation | -3.17e-03 |
Pos logit contributions | |
uberty | +0.159 |
taboola | +0.155 |
nered | +0.152 |
sum | +0.139 |
pric | +0.134 |
Neg logit contributions | |
Greek | -0.187 |
Elias | -0.184 |
ascript | -0.180 |
abal | -0.180 |
'). | -0.168 |
Token | suffering |
Token ID | 7195 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
Greek | +0.010 |
Elias | +0.010 |
abal | +0.009 |
ascript | +0.009 |
'). | +0.009 |
Neg logit contributions | |
uberty | -0.007 |
taboola | -0.007 |
nered | -0.007 |
sum | -0.006 |
pric | -0.006 |
Token | MORE |
Token ID | 12011 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
Greek | +0.075 |
Elias | +0.074 |
ascript | +0.072 |
abal | +0.072 |
'). | +0.067 |
Neg logit contributions | |
uberty | -0.066 |
taboola | -0.064 |
nered | -0.063 |
sum | -0.056 |
pric | -0.055 |
Token | and |
Token ID | 290 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
Greek | +0.043 |
Elias | +0.043 |
abal | +0.041 |
ascript | +0.041 |
'). | +0.038 |
Neg logit contributions | |
uberty | -0.060 |
taboola | -0.059 |
nered | -0.058 |
sum | -0.053 |
pric | -0.052 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
Greek | +0.438 |
Elias | +0.436 |
abal | +0.423 |
ascript | +0.421 |
'). | +0.394 |
Neg logit contributions | |
uberty | -0.404 |
taboola | -0.393 |
nered | -0.385 |
sum | -0.348 |
pric | -0.341 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
Greek | +0.458 |
Elias | +0.454 |
abal | +0.439 |
ascript | +0.435 |
'). | +0.404 |
Neg logit contributions | |
uberty | -0.521 |
taboola | -0.510 |
nered | -0.499 |
sum | -0.455 |
pric | -0.448 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
Greek | +0.343 |
Elias | +0.339 |
abal | +0.327 |
ascript | +0.326 |
'). | +0.296 |
Neg logit contributions | |
uberty | -0.534 |
taboola | -0.524 |
nered | -0.515 |
sum | -0.478 |
pric | -0.470 |
Token | Diane |
Token ID | 26542 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
Greek | +0.297 |
Elias | +0.295 |
ascript | +0.287 |
abal | +0.285 |
'). | +0.258 |
Neg logit contributions | |
uberty | -0.460 |
taboola | -0.451 |
nered | -0.444 |
sum | -0.412 |
pric | -0.406 |
Token | Rodham |
Token ID | 41848 |
Feature activation | -9.08e-02 |
Pos logit contributions | |
Greek | +0.746 |
Elias | +0.737 |
abal | +0.696 |
ascript | +0.691 |
'). | +0.627 |
Neg logit contributions | |
uberty | -1.495 |
taboola | -1.466 |
nered | -1.446 |
sum | -1.341 |
pric | -1.327 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -9.31e-02 |
Pos logit contributions | |
Greek | +0.236 |
Elias | +0.234 |
ascript | +0.231 |
abal | +0.229 |
'). | +0.210 |
Neg logit contributions | |
uberty | -0.239 |
taboola | -0.234 |
nered | -0.228 |
sum | -0.210 |
pric | -0.205 |
Token | Sanders |
Token ID | 26747 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Elias | +0.233 |
Greek | +0.230 |
ascript | +0.229 |
abal | +0.226 |
'). | +0.206 |
Neg logit contributions | |
uberty | -0.255 |
taboola | -0.250 |
nered | -0.244 |
sum | -0.223 |
pric | -0.219 |
Token | : |
Token ID | 25 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
Greek | +0.242 |
Elias | +0.241 |
ascript | +0.236 |
abal | +0.235 |
'). | +0.213 |
Neg logit contributions | |
uberty | -0.311 |
taboola | -0.305 |
nered | -0.297 |
sum | -0.276 |
pric | -0.271 |
Token | ' |
Token ID | 705 |
Feature activation | -9.33e-02 |
Pos logit contributions | |
Greek | +0.046 |
Elias | +0.046 |
abal | +0.044 |
ascript | +0.042 |
'). | +0.040 |
Neg logit contributions | |
uberty | -0.077 |
taboola | -0.075 |
nered | -0.075 |
sum | -0.068 |
pric | -0.068 |
Token | after |
Token ID | 706 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
uberty | +0.149 |
taboola | +0.146 |
nered | +0.143 |
sum | +0.133 |
pric | +0.130 |
Neg logit contributions | |
Greek | -0.104 |
Elias | -0.102 |
ascript | -0.099 |
abal | -0.099 |
'). | -0.091 |
Token | a |
Token ID | 257 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
Greek | +0.111 |
Elias | +0.110 |
abal | +0.107 |
ascript | +0.107 |
'). | +0.100 |
Neg logit contributions | |
uberty | -0.097 |
taboola | -0.094 |
nered | -0.092 |
sum | -0.083 |
pric | -0.081 |
Token | period |
Token ID | 2278 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
Greek | +0.120 |
Elias | +0.119 |
abal | +0.116 |
ascript | +0.116 |
'). | +0.108 |
Neg logit contributions | |
uberty | -0.094 |
taboola | -0.091 |
nered | -0.089 |
sum | -0.080 |
pric | -0.078 |
Token | for |
Token ID | 329 |
Feature activation | -6.03e-02 |
Pos logit contributions | |
Greek | +0.526 |
Elias | +0.523 |
abal | +0.507 |
ascript | +0.505 |
'). | +0.469 |
Neg logit contributions | |
uberty | -0.534 |
taboola | -0.521 |
nered | -0.510 |
sum | -0.463 |
pric | -0.455 |
Token | adjud |
Token ID | 33719 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
Greek | +0.176 |
Elias | +0.174 |
abal | +0.170 |
ascript | +0.170 |
'). | +0.160 |
Neg logit contributions | |
uberty | -0.140 |
taboola | -0.136 |
nered | -0.133 |
sum | -0.120 |
pric | -0.117 |
Token | ication |
Token ID | 3299 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
Greek | +0.031 |
Elias | +0.031 |
abal | +0.030 |
ascript | +0.030 |
'). | +0.027 |
Neg logit contributions | |
uberty | -0.035 |
taboola | -0.035 |
nered | -0.034 |
sum | -0.031 |
pric | -0.031 |
Token | of |
Token ID | 286 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
Greek | +1.002 |
Elias | +0.994 |
abal | +0.962 |
ascript | +0.958 |
'). | +0.884 |
Neg logit contributions | |
uberty | -1.198 |
taboola | -1.171 |
nered | -1.149 |
sum | -1.053 |
pric | -1.035 |
Token | complaints |
Token ID | 9687 |
Feature activation | -5.77e-02 |
Pos logit contributions | |
Greek | +0.110 |
Elias | +0.108 |
ascript | +0.106 |
abal | +0.106 |
'). | +0.099 |
Neg logit contributions | |
uberty | -0.093 |
taboola | -0.090 |
nered | -0.088 |
sum | -0.081 |
pric | -0.079 |
Token | . |
Token ID | 13 |
Feature activation | -6.52e-02 |
Pos logit contributions | |
Greek | +0.143 |
Elias | +0.140 |
ascript | +0.137 |
abal | +0.137 |
'). | +0.126 |
Neg logit contributions | |
uberty | -0.160 |
taboola | -0.157 |
nered | -0.154 |
sum | -0.142 |
pric | -0.139 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
Greek | +0.150 |
Elias | +0.148 |
ascript | +0.145 |
abal | +0.144 |
'). | +0.133 |
Neg logit contributions | |
uberty | -0.191 |
taboola | -0.187 |
nered | -0.183 |
sum | -0.169 |
pric | -0.165 |
Token |
|
Token ID | 198 |
Feature activation | -9.82e-02 |
Pos logit contributions | |
Greek | +0.276 |
Elias | +0.274 |
ascript | +0.268 |
abal | +0.266 |
'). | +0.245 |
Neg logit contributions | |
uberty | -0.286 |
taboola | -0.281 |
nered | -0.275 |
sum | -0.252 |
pric | -0.245 |
Token | ensure |
Token ID | 4155 |
Feature activation | +3.15e-03 |
Pos logit contributions | |
Greek | +0.039 |
Elias | +0.039 |
abal | +0.038 |
ascript | +0.038 |
'). | +0.035 |
Neg logit contributions | |
uberty | -0.030 |
taboola | -0.029 |
nered | -0.028 |
sum | -0.025 |
pric | -0.025 |
Token | he |
Token ID | 339 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
uberty | +0.008 |
taboola | +0.008 |
nered | +0.007 |
sum | +0.007 |
pric | +0.007 |
Neg logit contributions | |
Greek | -0.009 |
Elias | -0.009 |
abal | -0.008 |
ascript | -0.008 |
'). | -0.008 |
Token | reg |
Token ID | 842 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
uberty | +0.042 |
taboola | +0.041 |
nered | +0.040 |
sum | +0.035 |
pric | +0.034 |
Neg logit contributions | |
Greek | -0.059 |
Elias | -0.059 |
abal | -0.057 |
ascript | -0.057 |
'). | -0.054 |
Token | ains |
Token ID | 1299 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
Greek | +0.103 |
Elias | +0.102 |
abal | +0.100 |
ascript | +0.099 |
'). | +0.093 |
Neg logit contributions | |
uberty | -0.082 |
taboola | -0.079 |
nered | -0.077 |
sum | -0.070 |
pric | -0.068 |
Token | some |
Token ID | 617 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
uberty | +0.148 |
taboola | +0.143 |
nered | +0.142 |
sum | +0.129 |
pric | +0.124 |
Neg logit contributions | |
Greek | -0.190 |
Elias | -0.187 |
ascript | -0.183 |
abal | -0.183 |
'). | -0.171 |
Token | continuity |
Token ID | 24216 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
uberty | +0.044 |
taboola | +0.043 |
nered | +0.042 |
sum | +0.038 |
pric | +0.037 |
Neg logit contributions | |
Greek | -0.048 |
Elias | -0.047 |
abal | -0.046 |
ascript | -0.046 |
'). | -0.043 |
Token | in |
Token ID | 287 |
Feature activation | +7.81e-03 |
Pos logit contributions | |
Greek | +1.046 |
Elias | +1.041 |
abal | +1.009 |
ascript | +1.002 |
'). | +0.928 |
Neg logit contributions | |
uberty | -1.154 |
taboola | -1.124 |
nered | -1.100 |
sum | -1.001 |
pric | -0.988 |
Token | his |
Token ID | 465 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
uberty | +0.019 |
taboola | +0.018 |
nered | +0.018 |
sum | +0.016 |
pric | +0.016 |
Neg logit contributions | |
Greek | -0.022 |
Elias | -0.022 |
abal | -0.022 |
ascript | -0.022 |
'). | -0.020 |
Token | training |
Token ID | 3047 |
Feature activation | -6.37e-02 |
Pos logit contributions | |
uberty | +0.076 |
taboola | +0.074 |
nered | +0.072 |
sum | +0.065 |
pric | +0.063 |
Neg logit contributions | |
Greek | -0.101 |
Elias | -0.100 |
abal | -0.098 |
ascript | -0.097 |
'). | -0.091 |
Token | . |
Token ID | 13 |
Feature activation | +7.33e-02 |
Pos logit contributions | |
Greek | +0.158 |
Elias | +0.156 |
abal | +0.152 |
ascript | +0.151 |
'). | +0.140 |
Neg logit contributions | |
uberty | -0.177 |
taboola | -0.173 |
nered | -0.170 |
sum | -0.157 |
pric | -0.152 |
Token |
|
Token ID | 198 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
uberty | +0.169 |
taboola | +0.164 |
nered | +0.161 |
sum | +0.144 |
pric | +0.141 |
Neg logit contributions | |
Greek | -0.216 |
Elias | -0.214 |
abal | -0.209 |
ascript | -0.208 |
'). | -0.195 |
Token | while |
Token ID | 981 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
Greek | +0.460 |
Elias | +0.457 |
abal | +0.443 |
ascript | +0.441 |
'). | +0.409 |
Neg logit contributions | |
uberty | -0.504 |
taboola | -0.492 |
nered | -0.482 |
sum | -0.440 |
pric | -0.432 |
Token | the |
Token ID | 262 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
Greek | +0.055 |
Elias | +0.055 |
abal | +0.053 |
ascript | +0.053 |
'). | +0.050 |
Neg logit contributions | |
uberty | -0.040 |
taboola | -0.039 |
nered | -0.038 |
sum | -0.034 |
pric | -0.033 |
Token | patient |
Token ID | 5827 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
uberty | +0.027 |
taboola | +0.027 |
nered | +0.026 |
sum | +0.023 |
pric | +0.023 |
Neg logit contributions | |
Greek | -0.039 |
Elias | -0.038 |
abal | -0.037 |
ascript | -0.037 |
'). | -0.035 |
Token | was |
Token ID | 373 |
Feature activation | +4.73e-02 |
Pos logit contributions | |
uberty | +0.373 |
taboola | +0.364 |
nered | +0.356 |
sum | +0.321 |
pric | +0.313 |
Neg logit contributions | |
Greek | -0.455 |
Elias | -0.452 |
abal | -0.439 |
ascript | -0.438 |
'). | -0.410 |
Token | fully |
Token ID | 3938 |
Feature activation | +7.89e-02 |
Pos logit contributions | |
uberty | +0.108 |
taboola | +0.105 |
nered | +0.103 |
sum | +0.092 |
pric | +0.090 |
Neg logit contributions | |
Greek | -0.140 |
Elias | -0.139 |
abal | -0.136 |
ascript | -0.135 |
'). | -0.127 |
Token | conscious |
Token ID | 6921 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
uberty | +0.178 |
taboola | +0.172 |
nered | +0.170 |
sum | +0.153 |
pric | +0.148 |
Neg logit contributions | |
Greek | -0.236 |
Elias | -0.234 |
abal | -0.228 |
ascript | -0.228 |
'). | -0.213 |
Token | . |
Token ID | 13 |
Feature activation | +5.71e-02 |
Pos logit contributions | |
Greek | +0.882 |
Elias | +0.877 |
abal | +0.845 |
ascript | +0.839 |
'). | +0.766 |
Neg logit contributions | |
uberty | -1.310 |
taboola | -1.280 |
nered | -1.253 |
sum | -1.158 |
pric | -1.148 |
Token | When |
Token ID | 1649 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
uberty | +0.148 |
taboola | +0.145 |
nered | +0.141 |
sum | +0.129 |
pric | +0.125 |
Neg logit contributions | |
Greek | -0.151 |
Elias | -0.150 |
ascript | -0.147 |
abal | -0.146 |
'). | -0.136 |
Token | the |
Token ID | 262 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
Greek | +0.047 |
Elias | +0.047 |
abal | +0.046 |
ascript | +0.045 |
'). | +0.042 |
Neg logit contributions | |
uberty | -0.040 |
taboola | -0.039 |
nered | -0.038 |
sum | -0.035 |
pric | -0.034 |
Token | advent |
Token ID | 19980 |
Feature activation | +8.05e-02 |
Pos logit contributions | |
uberty | +0.067 |
taboola | +0.065 |
nered | +0.064 |
sum | +0.058 |
pric | +0.057 |
Neg logit contributions | |
Greek | -0.076 |
Elias | -0.075 |
ascript | -0.074 |
abal | -0.074 |
'). | -0.069 |
Token | of |
Token ID | 286 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
uberty | +0.214 |
taboola | +0.209 |
nered | +0.205 |
sum | +0.186 |
pric | +0.183 |
Neg logit contributions | |
Greek | -0.209 |
Elias | -0.207 |
abal | -0.201 |
ascript | -0.200 |
'). | -0.186 |
Token | group |
Token ID | 1448 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Elias | +0.958 |
Greek | +0.955 |
abal | +0.925 |
ascript | +0.911 |
'). | +0.853 |
Neg logit contributions | |
uberty | -0.942 |
taboola | -0.925 |
nered | -0.896 |
sum | -0.809 |
pric | -0.800 |
Token | Raqqa |
Token ID | 30391 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
Greek | +0.284 |
Elias | +0.282 |
abal | +0.272 |
ascript | +0.271 |
'). | +0.249 |
Neg logit contributions | |
uberty | -0.367 |
taboola | -0.359 |
nered | -0.352 |
sum | -0.324 |
pric | -0.318 |
Token | is |
Token ID | 318 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
uberty | +0.045 |
taboola | +0.044 |
nered | +0.043 |
sum | +0.039 |
pric | +0.038 |
Neg logit contributions | |
Greek | -0.041 |
Elias | -0.040 |
abal | -0.039 |
ascript | -0.039 |
'). | -0.036 |
Token | Being |
Token ID | 11204 |
Feature activation | -5.59e-02 |
Pos logit contributions | |
Greek | +0.066 |
Elias | +0.065 |
ascript | +0.063 |
abal | +0.063 |
'). | +0.058 |
Neg logit contributions | |
uberty | -0.071 |
taboola | -0.069 |
nered | -0.068 |
sum | -0.062 |
pric | -0.061 |
Token | Sl |
Token ID | 3454 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
Greek | +0.158 |
Elias | +0.158 |
abal | +0.152 |
ascript | +0.151 |
'). | +0.143 |
Neg logit contributions | |
uberty | -0.137 |
taboola | -0.134 |
nered | -0.129 |
sum | -0.116 |
pric | -0.115 |
Token | aughtered |
Token ID | 32734 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
Greek | +0.125 |
Elias | +0.124 |
abal | +0.121 |
ascript | +0.121 |
'). | +0.115 |
Neg logit contributions | |
uberty | -0.062 |
taboola | -0.060 |
nered | -0.058 |
sum | -0.050 |
pric | -0.048 |
Token | Sil |
Token ID | 4243 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
Greek | +0.999 |
Elias | +0.992 |
abal | +0.959 |
ascript | +0.955 |
'). | +0.882 |
Neg logit contributions | |
uberty | -1.199 |
taboola | -1.173 |
nered | -1.151 |
sum | -1.054 |
pric | -1.036 |
Token | ently |
Token ID | 1473 |
Feature activation | +8.52e-02 |
Pos logit contributions | |
Greek | +0.114 |
Elias | +0.113 |
ascript | +0.109 |
abal | +0.109 |
'). | +0.101 |
Neg logit contributions | |
uberty | -0.111 |
taboola | -0.108 |
nered | -0.105 |
sum | -0.095 |
pric | -0.094 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
uberty | +0.271 |
taboola | +0.266 |
nered | +0.261 |
sum | +0.242 |
pric | +0.238 |
Neg logit contributions | |
Greek | -0.176 |
Elias | -0.175 |
abal | -0.168 |
ascript | -0.167 |
'). | -0.152 |
Token |
|
Token ID | 198 |
Feature activation | -6.54e-02 |
Pos logit contributions | |
Greek | +0.283 |
Elias | +0.281 |
abal | +0.273 |
ascript | +0.272 |
'). | +0.252 |
Neg logit contributions | |
uberty | -0.309 |
taboola | -0.302 |
nered | -0.296 |
sum | -0.270 |
pric | -0.265 |
Token |
|
Token ID | 198 |
Feature activation | -5.43e-02 |
Pos logit contributions | |
Greek | +0.166 |
Elias | +0.165 |
ascript | +0.161 |
abal | +0.160 |
'). | +0.148 |
Neg logit contributions | |
uberty | -0.176 |
taboola | -0.173 |
nered | -0.169 |
sum | -0.155 |
pric | -0.151 |
Token | | |
Token ID | 930 |
Feature activation | -8.47e-02 |
Pos logit contributions | |
Greek | +0.266 |
Elias | +0.264 |
abal | +0.257 |
ascript | +0.256 |
'). | +0.239 |
Neg logit contributions | |
uberty | -0.245 |
taboola | -0.239 |
nered | -0.234 |
sum | -0.211 |
pric | -0.207 |
Token | 9 |
Token ID | 860 |
Feature activation | -7.21e-02 |
Pos logit contributions | |
Greek | +0.230 |
Elias | +0.227 |
ascript | +0.221 |
abal | +0.220 |
'). | +0.206 |
Neg logit contributions | |
uberty | -0.213 |
taboola | -0.210 |
nered | -0.205 |
sum | -0.188 |
pric | -0.184 |
Token | | |
Token ID | 930 |
Feature activation | -8.42e-02 |
Pos logit contributions | |
Greek | +0.200 |
Elias | +0.199 |
ascript | +0.195 |
abal | +0.194 |
'). | +0.180 |
Neg logit contributions | |
uberty | -0.176 |
taboola | -0.173 |
nered | -0.169 |
sum | -0.153 |
pric | -0.149 |
Token | org |
Token ID | 8745 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
Greek | +0.223 |
Elias | +0.222 |
abal | +0.216 |
ascript | +0.215 |
'). | +0.200 |
Neg logit contributions | |
uberty | -0.219 |
taboola | -0.213 |
nered | -0.209 |
sum | -0.189 |
pric | -0.186 |
Token | . |
Token ID | 764 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
uberty | +0.360 |
taboola | +0.357 |
nered | +0.350 |
sum | +0.327 |
pric | +0.318 |
Neg logit contributions | |
Greek | -0.234 |
Elias | -0.232 |
ascript | -0.225 |
abal | -0.222 |
'). | -0.200 |
Token | cl |
Token ID | 537 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
Elias | +0.389 |
Greek | +0.389 |
abal | +0.380 |
ascript | +0.376 |
'). | +0.357 |
Neg logit contributions | |
uberty | -0.256 |
taboola | -0.246 |
nered | -0.239 |
sum | -0.207 |
pric | -0.204 |
Token | ojure |
Token ID | 32511 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
uberty | +0.733 |
taboola | +0.715 |
nered | +0.705 |
sum | +0.647 |
pric | +0.631 |
Neg logit contributions | |
Greek | -0.570 |
Elias | -0.566 |
ascript | -0.541 |
abal | -0.538 |
'). | -0.499 |
Token | / |
Token ID | 1220 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
Greek | +0.096 |
Elias | +0.095 |
abal | +0.092 |
ascript | +0.092 |
'). | +0.085 |
Neg logit contributions | |
uberty | -0.104 |
taboola | -0.102 |
nered | -0.100 |
sum | -0.091 |
pric | -0.089 |
Token | tools |
Token ID | 4899 |
Feature activation | +8.59e-02 |
Pos logit contributions | |
uberty | +0.046 |
taboola | +0.045 |
nered | +0.044 |
sum | +0.040 |
pric | +0.039 |
Neg logit contributions | |
Greek | -0.052 |
Elias | -0.052 |
abal | -0.050 |
ascript | -0.050 |
'). | -0.047 |
Token | . |
Token ID | 764 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
uberty | +0.278 |
taboola | +0.273 |
nered | +0.268 |
sum | +0.250 |
pric | +0.245 |
Neg logit contributions | |
Greek | -0.173 |
Elias | -0.171 |
abal | -0.164 |
ascript | -0.162 |
'). | -0.148 |
Token | namespace |
Token ID | 25745 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
Greek | +0.434 |
Elias | +0.433 |
abal | +0.421 |
ascript | +0.419 |
'). | +0.393 |
Neg logit contributions | |
uberty | -0.362 |
taboola | -0.351 |
nered | -0.344 |
sum | -0.307 |
pric | -0.301 |
Token | 5 |
Token ID | 642 |
Feature activation | +8.98e-02 |
Pos logit contributions | |
uberty | +0.436 |
taboola | +0.425 |
nered | +0.416 |
sum | +0.379 |
pric | +0.371 |
Neg logit contributions | |
Greek | -0.435 |
Elias | -0.432 |
abal | -0.419 |
ascript | -0.418 |
'). | -0.388 |
Token | min |
Token ID | 949 |
Feature activation | -6.36e-02 |
Pos logit contributions | |
uberty | +0.253 |
taboola | +0.247 |
nered | +0.242 |
sum | +0.222 |
pric | +0.218 |
Neg logit contributions | |
Greek | -0.219 |
Elias | -0.217 |
abal | -0.210 |
ascript | -0.209 |
'). | -0.194 |
Token | . |
Token ID | 13 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
Greek | +0.162 |
Elias | +0.160 |
abal | +0.156 |
ascript | +0.155 |
'). | +0.144 |
Neg logit contributions | |
uberty | -0.173 |
taboola | -0.169 |
nered | -0.165 |
sum | -0.151 |
pric | -0.148 |
Token | walk |
Token ID | 2513 |
Feature activation | +7.36e-02 |
Pos logit contributions | |
Greek | +0.042 |
Elias | +0.042 |
abal | +0.040 |
ascript | +0.040 |
'). | +0.037 |
Neg logit contributions | |
uberty | -0.046 |
taboola | -0.045 |
nered | -0.044 |
sum | -0.040 |
pric | -0.039 |
Token | from |
Token ID | 422 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
uberty | +0.218 |
taboola | +0.214 |
nered | +0.210 |
sum | +0.193 |
pric | +0.190 |
Neg logit contributions | |
Greek | -0.168 |
Elias | -0.167 |
abal | -0.161 |
ascript | -0.161 |
'). | -0.148 |
Token | Hung |
Token ID | 12149 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
uberty | +0.096 |
taboola | +0.093 |
nered | +0.092 |
sum | +0.084 |
pric | +0.082 |
Neg logit contributions | |
Greek | -0.101 |
Elias | -0.100 |
ascript | -0.098 |
abal | -0.097 |
'). | -0.091 |
Token | Hom |
Token ID | 8074 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
uberty | +0.800 |
taboola | +0.777 |
nered | +0.760 |
sum | +0.695 |
pric | +0.680 |
Neg logit contributions | |
Greek | -0.872 |
Elias | -0.863 |
ascript | -0.843 |
abal | -0.834 |
'). | -0.781 |
Token | M |
Token ID | 337 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
uberty | +0.102 |
taboola | +0.100 |
nered | +0.098 |
sum | +0.090 |
pric | +0.089 |
Neg logit contributions | |
Greek | -0.084 |
Elias | -0.083 |
ascript | -0.080 |
abal | -0.080 |
'). | -0.074 |
Token | TR |
Token ID | 5446 |
Feature activation | +7.26e-02 |
Pos logit contributions | |
Greek | +0.079 |
Elias | +0.078 |
abal | +0.076 |
ascript | +0.075 |
'). | +0.070 |
Neg logit contributions | |
uberty | -0.099 |
taboola | -0.097 |
nered | -0.095 |
sum | -0.087 |
pric | -0.086 |
Token | Station |
Token ID | 9327 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
uberty | +0.209 |
taboola | +0.204 |
nered | +0.201 |
sum | +0.185 |
pric | +0.181 |
Neg logit contributions | |
Greek | -0.172 |
Elias | -0.171 |
abal | -0.165 |
ascript | -0.165 |
'). | -0.152 |
Token | ( |
Token ID | 357 |
Feature activation | +5.58e-03 |
Pos logit contributions | |
uberty | +0.543 |
taboola | +0.531 |
nered | +0.523 |
sum | +0.484 |
pric | +0.475 |
Neg logit contributions | |
Greek | -0.384 |
Elias | -0.381 |
ascript | -0.367 |
abal | -0.366 |
'). | -0.334 |
Token | of |
Token ID | 286 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
uberty | +0.051 |
taboola | +0.049 |
nered | +0.048 |
sum | +0.044 |
pric | +0.043 |
Neg logit contributions | |
Greek | -0.053 |
Elias | -0.052 |
abal | -0.051 |
ascript | -0.051 |
'). | -0.047 |
Token | concepts |
Token ID | 10838 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
Greek | +0.114 |
Elias | +0.113 |
abal | +0.110 |
ascript | +0.110 |
'). | +0.103 |
Neg logit contributions | |
uberty | -0.087 |
taboola | -0.085 |
nered | -0.083 |
sum | -0.074 |
pric | -0.072 |
Token | that |
Token ID | 326 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
Greek | +0.058 |
Elias | +0.057 |
abal | +0.056 |
ascript | +0.056 |
'). | +0.052 |
Neg logit contributions | |
uberty | -0.055 |
taboola | -0.054 |
nered | -0.053 |
sum | -0.048 |
pric | -0.047 |
Token | accept |
Token ID | 2453 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
uberty | +0.063 |
taboola | +0.061 |
nered | +0.060 |
sum | +0.055 |
pric | +0.052 |
Neg logit contributions | |
Greek | -0.091 |
Elias | -0.089 |
abal | -0.088 |
ascript | -0.088 |
'). | -0.083 |
Token | Bitcoin |
Token ID | 6185 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
uberty | +0.276 |
taboola | +0.272 |
nered | +0.266 |
sum | +0.245 |
pric | +0.239 |
Neg logit contributions | |
Greek | -0.330 |
Elias | -0.324 |
ascript | -0.318 |
abal | -0.318 |
'). | -0.297 |
Token | micro |
Token ID | 4580 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
uberty | +0.054 |
taboola | +0.053 |
nered | +0.052 |
sum | +0.048 |
pric | +0.047 |
Neg logit contributions | |
Greek | -0.049 |
Elias | -0.048 |
ascript | -0.047 |
abal | -0.047 |
'). | -0.044 |
Token | - |
Token ID | 12 |
Feature activation | +9.10e-02 |
Pos logit contributions | |
uberty | +1.006 |
taboola | +0.998 |
nered | +0.971 |
sum | +0.908 |
pric | +0.879 |
Neg logit contributions | |
Greek | -0.927 |
Elias | -0.925 |
abal | -0.896 |
ascript | -0.893 |
'). | -0.825 |
Token | trans |
Token ID | 7645 |
Feature activation | +9.41e-02 |
Pos logit contributions | |
uberty | +0.251 |
taboola | +0.248 |
nered | +0.242 |
sum | +0.224 |
pric | +0.218 |
Neg logit contributions | |
Elias | -0.222 |
Greek | -0.222 |
abal | -0.215 |
ascript | -0.214 |
'). | -0.198 |
Token | actions |
Token ID | 4658 |
Feature activation | +9.72e-02 |
Pos logit contributions | |
uberty | +0.254 |
taboola | +0.248 |
nered | +0.245 |
sum | +0.225 |
pric | +0.220 |
Neg logit contributions | |
Elias | -0.238 |
Greek | -0.237 |
ascript | -0.228 |
abal | -0.228 |
'). | -0.211 |
Token | . |
Token ID | 13 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
uberty | +0.265 |
taboola | +0.261 |
nered | +0.256 |
sum | +0.236 |
pric | +0.230 |
Neg logit contributions | |
Greek | -0.244 |
Elias | -0.240 |
abal | -0.235 |
ascript | -0.234 |
'). | -0.216 |
Token | We |
Token ID | 775 |
Feature activation | +8.65e-02 |
Pos logit contributions | |
Greek | +0.038 |
Elias | +0.037 |
ascript | +0.037 |
abal | +0.036 |
'). | +0.034 |
Neg logit contributions | |
uberty | -0.035 |
taboola | -0.034 |
nered | -0.034 |
sum | -0.031 |
pric | -0.030 |
Token | known |
Token ID | 4002 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
Greek | +0.134 |
Elias | +0.132 |
abal | +0.129 |
ascript | +0.128 |
'). | +0.120 |
Neg logit contributions | |
uberty | -0.116 |
taboola | -0.112 |
nered | -0.109 |
sum | -0.098 |
pric | -0.096 |
Token | mail |
Token ID | 6920 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
Greek | +0.305 |
Elias | +0.303 |
abal | +0.295 |
ascript | +0.294 |
'). | +0.276 |
Neg logit contributions | |
uberty | -0.233 |
taboola | -0.226 |
nered | -0.221 |
sum | -0.198 |
pric | -0.193 |
Token | order |
Token ID | 1502 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
uberty | +0.273 |
taboola | +0.265 |
nered | +0.259 |
sum | +0.232 |
pric | +0.226 |
Neg logit contributions | |
Greek | -0.367 |
Elias | -0.365 |
abal | -0.355 |
ascript | -0.355 |
'). | -0.333 |
Token | catalog |
Token ID | 18388 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
uberty | +0.209 |
taboola | +0.202 |
nered | +0.198 |
sum | +0.177 |
pric | +0.172 |
Neg logit contributions | |
Greek | -0.326 |
Elias | -0.323 |
abal | -0.316 |
ascript | -0.316 |
'). | -0.297 |
Token | ues |
Token ID | 947 |
Feature activation | +4.35e-02 |
Pos logit contributions | |
uberty | +0.083 |
taboola | +0.080 |
nered | +0.079 |
sum | +0.070 |
pric | +0.069 |
Neg logit contributions | |
Greek | -0.107 |
Elias | -0.106 |
abal | -0.103 |
ascript | -0.103 |
'). | -0.096 |
Token | apologised |
Token ID | 46397 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
uberty | +0.109 |
taboola | +0.107 |
nered | +0.105 |
sum | +0.095 |
pric | +0.093 |
Neg logit contributions | |
Greek | -0.119 |
Elias | -0.118 |
ascript | -0.115 |
abal | -0.114 |
'). | -0.106 |
Token | today |
Token ID | 1909 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
uberty | +0.544 |
taboola | +0.531 |
nered | +0.521 |
sum | +0.472 |
pric | +0.461 |
Neg logit contributions | |
Greek | -0.643 |
Elias | -0.638 |
ascript | -0.621 |
abal | -0.620 |
'). | -0.580 |
Token | after |
Token ID | 706 |
Feature activation | +5.98e-02 |
Pos logit contributions | |
uberty | +0.366 |
taboola | +0.356 |
nered | +0.349 |
sum | +0.316 |
pric | +0.310 |
Neg logit contributions | |
Greek | -0.385 |
Elias | -0.383 |
abal | -0.372 |
ascript | -0.370 |
'). | -0.345 |
Token | web |
Token ID | 3992 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
uberty | +0.139 |
taboola | +0.135 |
nered | +0.132 |
sum | +0.119 |
pric | +0.116 |
Neg logit contributions | |
Greek | -0.175 |
Elias | -0.173 |
ascript | -0.169 |
abal | -0.169 |
'). | -0.158 |
Token | users |
Token ID | 2985 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
uberty | +0.243 |
taboola | +0.236 |
nered | +0.230 |
sum | +0.205 |
pric | +0.200 |
Neg logit contributions | |
Greek | -0.332 |
Elias | -0.330 |
abal | -0.322 |
ascript | -0.321 |
'). | -0.302 |
Token | noticed |
Token ID | 6810 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
Greek | +0.043 |
Elias | +0.043 |
abal | +0.041 |
ascript | +0.041 |
'). | +0.038 |
Neg logit contributions | |
uberty | -0.036 |
taboola | -0.035 |
nered | -0.034 |
sum | -0.031 |
pric | -0.030 |
Token | angle |
Token ID | 9248 |
Feature activation | -9.00e-02 |
Pos logit contributions | |
Greek | +0.022 |
Elias | +0.022 |
abal | +0.020 |
ascript | +0.020 |
'). | +0.017 |
Neg logit contributions | |
uberty | -0.079 |
taboola | -0.078 |
nered | -0.077 |
sum | -0.073 |
pric | -0.071 |
Token | F |
Token ID | 37 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
Greek | +0.196 |
Elias | +0.195 |
abal | +0.188 |
ascript | +0.187 |
'). | +0.171 |
Neg logit contributions | |
uberty | -0.274 |
taboola | -0.271 |
nered | -0.266 |
sum | -0.246 |
pric | -0.241 |
Token | ( |
Token ID | 357 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
uberty | +0.085 |
taboola | +0.083 |
nered | +0.082 |
sum | +0.074 |
pric | +0.073 |
Neg logit contributions | |
Greek | -0.080 |
Elias | -0.079 |
abal | -0.077 |
ascript | -0.077 |
'). | -0.071 |
Token | 0 |
Token ID | 15 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
uberty | +0.036 |
taboola | +0.036 |
nered | +0.035 |
sum | +0.033 |
pric | +0.032 |
Neg logit contributions | |
Greek | -0.030 |
Elias | -0.030 |
abal | -0.029 |
ascript | -0.028 |
'). | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | +5.47e-02 |
Pos logit contributions | |
uberty | +0.117 |
taboola | +0.116 |
nered | +0.113 |
sum | +0.106 |
pric | +0.103 |
Neg logit contributions | |
Greek | -0.084 |
Elias | -0.084 |
ascript | -0.081 |
abal | -0.080 |
'). | -0.073 |
Token | ($ |
Token ID | 16763 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
uberty | +0.132 |
taboola | +0.130 |
nered | +0.127 |
sum | +0.115 |
pric | +0.112 |
Neg logit contributions | |
Greek | -0.154 |
Elias | -0.153 |
abal | -0.149 |
ascript | -0.148 |
'). | -0.138 |
Token | s |
Token ID | 82 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
uberty | +0.750 |
taboola | +0.744 |
nered | +0.730 |
sum | +0.668 |
pric | +0.654 |
Neg logit contributions | |
Elias | -0.587 |
Greek | -0.584 |
ascript | -0.562 |
abal | -0.562 |
'). | -0.513 |
Token | z |
Token ID | 89 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
Greek | +0.049 |
Elias | +0.048 |
abal | +0.047 |
ascript | +0.047 |
'). | +0.043 |
Neg logit contributions | |
uberty | -0.053 |
taboola | -0.052 |
nered | -0.051 |
sum | -0.047 |
pric | -0.046 |
Token | 1 |
Token ID | 16 |
Feature activation | +8.83e-03 |
Pos logit contributions | |
Greek | +0.537 |
Elias | +0.535 |
abal | +0.521 |
ascript | +0.519 |
'). | +0.486 |
Neg logit contributions | |
uberty | -0.381 |
taboola | -0.372 |
nered | -0.362 |
sum | -0.324 |
pric | -0.314 |
Token | . |
Token ID | 13 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
uberty | +0.028 |
taboola | +0.028 |
nered | +0.027 |
sum | +0.025 |
pric | +0.025 |
Neg logit contributions | |
Greek | -0.018 |
Elias | -0.018 |
abal | -0.017 |
ascript | -0.017 |
'). | -0.016 |
Token | Height |
Token ID | 23106 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
uberty | +0.043 |
taboola | +0.043 |
nered | +0.042 |
sum | +0.038 |
pric | +0.037 |
Neg logit contributions | |
Elias | -0.051 |
Greek | -0.051 |
ascript | -0.050 |
abal | -0.049 |
'). | -0.046 |
Token | complying |
Token ID | 39076 |
Feature activation | +9.58e-02 |
Pos logit contributions | |
Greek | +0.046 |
Elias | +0.045 |
ascript | +0.044 |
abal | +0.044 |
'). | +0.042 |
Neg logit contributions | |
uberty | -0.032 |
taboola | -0.031 |
nered | -0.030 |
sum | -0.027 |
pric | -0.026 |
Token | with |
Token ID | 351 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
uberty | +0.246 |
taboola | +0.240 |
nered | +0.236 |
sum | +0.214 |
pric | +0.209 |
Neg logit contributions | |
Greek | -0.257 |
Elias | -0.255 |
abal | -0.248 |
ascript | -0.247 |
'). | -0.231 |
Token | the |
Token ID | 262 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
uberty | +0.097 |
taboola | +0.094 |
nered | +0.092 |
sum | +0.084 |
pric | +0.082 |
Neg logit contributions | |
Greek | -0.112 |
Elias | -0.110 |
abal | -0.108 |
ascript | -0.108 |
'). | -0.101 |
Token | courts |
Token ID | 8028 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
Greek | +0.059 |
Elias | +0.059 |
ascript | +0.057 |
abal | +0.057 |
'). | +0.053 |
Neg logit contributions | |
uberty | -0.050 |
taboola | -0.049 |
nered | -0.048 |
sum | -0.043 |
pric | -0.042 |
Token | without |
Token ID | 1231 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
uberty | +0.083 |
taboola | +0.081 |
nered | +0.080 |
sum | +0.074 |
pric | +0.073 |
Neg logit contributions | |
Greek | -0.058 |
Elias | -0.058 |
abal | -0.056 |
ascript | -0.055 |
'). | -0.051 |
Token | bankrupt |
Token ID | 13158 |
Feature activation | +6.02e-02 |
Pos logit contributions | |
uberty | +0.082 |
taboola | +0.080 |
nered | +0.078 |
sum | +0.070 |
pric | +0.068 |
Neg logit contributions | |
Greek | -0.108 |
Elias | -0.107 |
ascript | -0.104 |
abal | -0.104 |
'). | -0.098 |
Token | ing |
Token ID | 278 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
uberty | +0.144 |
taboola | +0.141 |
nered | +0.138 |
sum | +0.126 |
pric | +0.122 |
Neg logit contributions | |
Greek | -0.171 |
Elias | -0.170 |
ascript | -0.165 |
abal | -0.165 |
'). | -0.154 |
Token | the |
Token ID | 262 |
Feature activation | +7.49e-03 |
Pos logit contributions | |
Greek | +0.079 |
Elias | +0.078 |
ascript | +0.076 |
abal | +0.076 |
'). | +0.071 |
Neg logit contributions | |
uberty | -0.071 |
taboola | -0.069 |
nered | -0.068 |
sum | -0.062 |
pric | -0.061 |
Token | city |
Token ID | 1748 |
Feature activation | +6.11e-02 |
Pos logit contributions | |
uberty | +0.015 |
taboola | +0.015 |
nered | +0.014 |
sum | +0.013 |
pric | +0.013 |
Neg logit contributions | |
Greek | -0.024 |
Elias | -0.024 |
ascript | -0.023 |
abal | -0.023 |
'). | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | -3.96e-02 |
Pos logit contributions | |
uberty | +0.183 |
taboola | +0.179 |
nered | +0.176 |
sum | +0.162 |
pric | +0.159 |
Neg logit contributions | |
Greek | -0.138 |
Elias | -0.137 |
abal | -0.132 |
ascript | -0.132 |
'). | -0.121 |
Token | only |
Token ID | 691 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
Greek | +0.113 |
Elias | +0.112 |
abal | +0.109 |
ascript | +0.109 |
'). | +0.102 |
Neg logit contributions | |
uberty | -0.095 |
taboola | -0.093 |
nered | -0.091 |
sum | -0.082 |
pric | -0.080 |
Token | the |
Token ID | 262 |
Feature activation | +8.11e-04 |
Pos logit contributions | |
uberty | +0.098 |
taboola | +0.096 |
nered | +0.094 |
sum | +0.085 |
pric | +0.083 |
Neg logit contributions | |
Greek | -0.122 |
Elias | -0.120 |
abal | -0.117 |
ascript | -0.117 |
'). | -0.110 |
Token | No |
Token ID | 1400 |
Feature activation | -2.18e-03 |
Pos logit contributions | |
uberty | +0.002 |
taboola | +0.002 |
nered | +0.002 |
sum | +0.002 |
pric | +0.002 |
Neg logit contributions | |
Greek | -0.002 |
Elias | -0.002 |
abal | -0.002 |
ascript | -0.002 |
'). | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
Greek | +0.004 |
Elias | +0.004 |
abal | +0.004 |
ascript | +0.004 |
'). | +0.004 |
Neg logit contributions | |
uberty | -0.007 |
taboola | -0.007 |
nered | -0.007 |
sum | -0.006 |
pric | -0.006 |
Token | 39 |
Token ID | 5014 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
uberty | +0.118 |
taboola | +0.115 |
nered | +0.113 |
sum | +0.103 |
pric | +0.100 |
Neg logit contributions | |
Greek | -0.125 |
Elias | -0.124 |
abal | -0.121 |
ascript | -0.121 |
'). | -0.112 |
Token | Gra |
Token ID | 7037 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
uberty | +0.149 |
taboola | +0.145 |
nered | +0.142 |
sum | +0.130 |
pric | +0.127 |
Neg logit contributions | |
Greek | -0.155 |
Elias | -0.154 |
abal | -0.150 |
ascript | -0.149 |
'). | -0.139 |
Token | ff |
Token ID | 487 |
Feature activation | +9.21e-02 |
Pos logit contributions | |
uberty | +0.327 |
taboola | +0.318 |
nered | +0.317 |
sum | +0.291 |
pric | +0.284 |
Neg logit contributions | |
Greek | -0.242 |
Elias | -0.239 |
ascript | -0.230 |
abal | -0.229 |
'). | -0.211 |
Token | car |
Token ID | 1097 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
uberty | +0.244 |
taboola | +0.238 |
nered | +0.234 |
sum | +0.213 |
pric | +0.208 |
Neg logit contributions | |
Greek | -0.240 |
Elias | -0.238 |
abal | -0.231 |
ascript | -0.230 |
'). | -0.214 |
Token | of |
Token ID | 286 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
uberty | +0.039 |
taboola | +0.038 |
nered | +0.038 |
sum | +0.035 |
pric | +0.034 |
Neg logit contributions | |
Greek | -0.037 |
Elias | -0.037 |
ascript | -0.036 |
abal | -0.036 |
'). | -0.033 |
Token | En |
Token ID | 2039 |
Feature activation | +4.00e-02 |
Pos logit contributions | |
uberty | +0.039 |
taboola | +0.038 |
nered | +0.038 |
sum | +0.035 |
pric | +0.034 |
Neg logit contributions | |
Greek | -0.036 |
Elias | -0.035 |
abal | -0.034 |
ascript | -0.034 |
'). | -0.032 |
Token | zo |
Token ID | 10872 |
Feature activation | +9.07e-02 |
Pos logit contributions | |
uberty | +0.107 |
taboola | +0.105 |
nered | +0.103 |
sum | +0.094 |
pric | +0.092 |
Neg logit contributions | |
Greek | -0.103 |
Elias | -0.102 |
abal | -0.099 |
ascript | -0.099 |
'). | -0.092 |
Token | Gu |
Token ID | 1962 |
Feature activation | -4.63e-03 |
Pos logit contributions | |
uberty | +0.245 |
taboola | +0.239 |
nered | +0.236 |
sum | +0.216 |
pric | +0.211 |
Neg logit contributions | |
Greek | -0.231 |
Elias | -0.225 |
ascript | -0.221 |
abal | -0.220 |
'). | -0.205 |
Token | mentality |
Token ID | 21332 |
Feature activation | +6.46e-02 |
Pos logit contributions | |
uberty | +0.302 |
taboola | +0.293 |
nered | +0.286 |
sum | +0.255 |
pric | +0.248 |
Neg logit contributions | |
Greek | -0.453 |
Elias | -0.450 |
abal | -0.440 |
ascript | -0.440 |
'). | -0.413 |
Token | running |
Token ID | 2491 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
uberty | +0.181 |
taboola | +0.177 |
nered | +0.174 |
sum | +0.159 |
pric | +0.156 |
Neg logit contributions | |
Greek | -0.158 |
Elias | -0.157 |
abal | -0.152 |
ascript | -0.152 |
'). | -0.140 |
Token | things |
Token ID | 1243 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
uberty | +0.065 |
taboola | +0.063 |
nered | +0.061 |
sum | +0.055 |
pric | +0.054 |
Neg logit contributions | |
Greek | -0.074 |
Elias | -0.073 |
abal | -0.071 |
ascript | -0.071 |
'). | -0.067 |
Token | as |
Token ID | 355 |
Feature activation | +4.27e-02 |
Pos logit contributions | |
uberty | +0.118 |
taboola | +0.115 |
nered | +0.113 |
sum | +0.104 |
pric | +0.102 |
Neg logit contributions | |
Greek | -0.102 |
Elias | -0.101 |
abal | -0.098 |
ascript | -0.098 |
'). | -0.090 |
Token | if |
Token ID | 611 |
Feature activation | +7.27e-02 |
Pos logit contributions | |
uberty | +0.098 |
taboola | +0.095 |
nered | +0.093 |
sum | +0.083 |
pric | +0.081 |
Neg logit contributions | |
Greek | -0.127 |
Elias | -0.126 |
abal | -0.123 |
ascript | -0.122 |
'). | -0.115 |
Token | we |
Token ID | 356 |
Feature activation | +6.46e-02 |
Pos logit contributions | |
uberty | +0.167 |
taboola | +0.162 |
nered | +0.158 |
sum | +0.142 |
pric | +0.139 |
Neg logit contributions | |
Greek | -0.215 |
Elias | -0.214 |
abal | -0.208 |
ascript | -0.207 |
'). | -0.195 |
Token | cannot |
Token ID | 2314 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
uberty | +0.134 |
taboola | +0.129 |
nered | +0.126 |
sum | +0.112 |
pric | +0.109 |
Neg logit contributions | |
Greek | -0.206 |
Elias | -0.204 |
abal | -0.199 |
ascript | -0.199 |
'). | -0.188 |
Token | have |
Token ID | 423 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
uberty | +0.081 |
taboola | +0.078 |
nered | +0.076 |
sum | +0.068 |
pric | +0.066 |
Neg logit contributions | |
Greek | -0.121 |
Elias | -0.120 |
abal | -0.117 |
ascript | -0.117 |
'). | -0.110 |
Token | common |
Token ID | 2219 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Greek | +0.113 |
Elias | +0.112 |
abal | +0.109 |
ascript | +0.108 |
'). | +0.102 |
Neg logit contributions | |
uberty | -0.090 |
taboola | -0.088 |
nered | -0.086 |
sum | -0.077 |
pric | -0.075 |
Token | sense |
Token ID | 2565 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
uberty | +0.259 |
taboola | +0.255 |
nered | +0.254 |
sum | +0.230 |
pric | +0.223 |
Neg logit contributions | |
Greek | -0.290 |
Elias | -0.289 |
abal | -0.282 |
ascript | -0.281 |
'). | -0.261 |
Token | enough |
Token ID | 1576 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
uberty | +0.083 |
taboola | +0.081 |
nered | +0.080 |
sum | +0.073 |
pric | +0.072 |
Neg logit contributions | |
Greek | -0.069 |
Elias | -0.068 |
abal | -0.066 |
ascript | -0.065 |
'). | -0.061 |
Token | by |
Token ID | 416 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
Greek | +0.122 |
Elias | +0.121 |
abal | +0.117 |
ascript | +0.117 |
'). | +0.109 |
Neg logit contributions | |
uberty | -0.116 |
taboola | -0.113 |
nered | -0.111 |
sum | -0.100 |
pric | -0.098 |
Token | the |
Token ID | 262 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
Greek | +0.039 |
Elias | +0.038 |
abal | +0.037 |
ascript | +0.037 |
'). | +0.035 |
Neg logit contributions | |
uberty | -0.032 |
taboola | -0.031 |
nered | -0.031 |
sum | -0.028 |
pric | -0.027 |
Token | attack |
Token ID | 1368 |
Feature activation | +4.21e-02 |
Pos logit contributions | |
Greek | +0.066 |
Elias | +0.066 |
abal | +0.064 |
ascript | +0.064 |
'). | +0.059 |
Neg logit contributions | |
uberty | -0.060 |
taboola | -0.058 |
nered | -0.057 |
sum | -0.051 |
pric | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
uberty | +0.132 |
taboola | +0.129 |
nered | +0.126 |
sum | +0.117 |
pric | +0.115 |
Neg logit contributions | |
Greek | -0.090 |
Elias | -0.089 |
abal | -0.086 |
ascript | -0.085 |
'). | -0.078 |
Token |
|
Token ID | 198 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
Greek | +0.075 |
Elias | +0.074 |
ascript | +0.073 |
abal | +0.073 |
'). | +0.067 |
Neg logit contributions | |
uberty | -0.078 |
taboola | -0.077 |
nered | -0.075 |
sum | -0.068 |
pric | -0.067 |
Token |
|
Token ID | 198 |
Feature activation | -7.65e-03 |
Pos logit contributions | |
Greek | +0.051 |
Elias | +0.050 |
ascript | +0.049 |
abal | +0.049 |
'). | +0.045 |
Neg logit contributions | |
uberty | -0.053 |
taboola | -0.052 |
nered | -0.051 |
sum | -0.046 |
pric | -0.045 |
Token | Whatever |
Token ID | 21875 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
Elias | +0.018 |
Greek | +0.018 |
abal | +0.018 |
ascript | +0.018 |
'). | +0.016 |
Neg logit contributions | |
uberty | -0.022 |
taboola | -0.022 |
nered | -0.021 |
sum | -0.019 |
pric | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
Greek | +0.135 |
Elias | +0.134 |
abal | +0.131 |
ascript | +0.130 |
'). | +0.122 |
Neg logit contributions | |
uberty | -0.113 |
taboola | -0.110 |
nered | -0.108 |
sum | -0.097 |
pric | -0.095 |
Token | United |
Token ID | 1578 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
Greek | +0.095 |
Elias | +0.095 |
abal | +0.092 |
ascript | +0.092 |
'). | +0.086 |
Neg logit contributions | |
uberty | -0.071 |
taboola | -0.069 |
nered | -0.067 |
sum | -0.059 |
pric | -0.058 |
Token | States |
Token ID | 1829 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
uberty | +0.458 |
taboola | +0.440 |
nered | +0.430 |
sum | +0.382 |
pric | +0.377 |
Neg logit contributions | |
Greek | -0.586 |
Elias | -0.582 |
abal | -0.566 |
ascript | -0.564 |
'). | -0.531 |
Token | can |
Token ID | 460 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
Greek | +0.521 |
Elias | +0.517 |
abal | +0.503 |
ascript | +0.502 |
'). | +0.468 |
Neg logit contributions | |
uberty | -0.456 |
taboola | -0.445 |
nered | -0.435 |
sum | -0.394 |
pric | -0.385 |
Token | a |
Token ID | 257 |
Feature activation | -7.75e-03 |
Pos logit contributions | |
Greek | +0.491 |
Elias | +0.490 |
abal | +0.475 |
ascript | +0.473 |
'). | +0.444 |
Neg logit contributions | |
uberty | -0.400 |
taboola | -0.390 |
nered | -0.379 |
sum | -0.339 |
pric | -0.333 |
Token | break |
Token ID | 2270 |
Feature activation | -6.94e-02 |
Pos logit contributions | |
Greek | +0.023 |
Elias | +0.023 |
abal | +0.022 |
ascript | +0.022 |
'). | +0.021 |
Neg logit contributions | |
uberty | -0.018 |
taboola | -0.017 |
nered | -0.017 |
sum | -0.015 |
pric | -0.015 |
Token | for |
Token ID | 329 |
Feature activation | +5.29e-03 |
Pos logit contributions | |
Greek | +0.182 |
Elias | +0.180 |
abal | +0.175 |
ascript | +0.174 |
'). | +0.162 |
Neg logit contributions | |
uberty | -0.183 |
taboola | -0.178 |
nered | -0.175 |
sum | -0.159 |
pric | -0.156 |
Token | it |
Token ID | 340 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
uberty | +0.013 |
taboola | +0.013 |
nered | +0.012 |
sum | +0.011 |
pric | +0.011 |
Neg logit contributions | |
Greek | -0.015 |
Elias | -0.015 |
abal | -0.014 |
ascript | -0.014 |
'). | -0.013 |
Token | ( |
Token ID | 357 |
Feature activation | -6.49e-02 |
Pos logit contributions | |
Greek | +0.030 |
Elias | +0.030 |
abal | +0.029 |
ascript | +0.029 |
'). | +0.027 |
Neg logit contributions | |
uberty | -0.035 |
taboola | -0.034 |
nered | -0.033 |
sum | -0.030 |
pric | -0.030 |
Token | 3 |
Token ID | 18 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
Greek | +0.167 |
Elias | +0.167 |
ascript | +0.162 |
abal | +0.162 |
'). | +0.149 |
Neg logit contributions | |
uberty | -0.172 |
taboola | -0.169 |
nered | -0.165 |
sum | -0.150 |
pric | -0.147 |
Token | ) |
Token ID | 8 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
uberty | +0.101 |
taboola | +0.100 |
nered | +0.098 |
sum | +0.092 |
pric | +0.090 |
Neg logit contributions | |
Greek | -0.048 |
Elias | -0.047 |
ascript | -0.045 |
abal | -0.045 |
'). | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
Greek | +0.261 |
Elias | +0.259 |
abal | +0.251 |
ascript | +0.250 |
'). | +0.231 |
Neg logit contributions | |
uberty | -0.286 |
taboola | -0.279 |
nered | -0.274 |
sum | -0.250 |
pric | -0.245 |
Token |
|
Token ID | 198 |
Feature activation | -5.76e-02 |
Pos logit contributions | |
Greek | +0.164 |
Elias | +0.163 |
ascript | +0.159 |
abal | +0.158 |
'). | +0.146 |
Neg logit contributions | |
uberty | -0.171 |
taboola | -0.168 |
nered | -0.164 |
sum | -0.150 |
pric | -0.147 |
Token | Press |
Token ID | 13800 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
Elias | +0.142 |
Greek | +0.141 |
ascript | +0.137 |
abal | +0.137 |
'). | +0.126 |
Neg logit contributions | |
uberty | -0.159 |
taboola | -0.157 |
nered | -0.153 |
sum | -0.140 |
pric | -0.137 |
Token | the |
Token ID | 262 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
Greek | +0.412 |
Elias | +0.409 |
abal | +0.398 |
ascript | +0.397 |
'). | +0.369 |
Neg logit contributions | |
uberty | -0.379 |
taboola | -0.369 |
nered | -0.363 |
sum | -0.329 |
pric | -0.321 |
Token | ?" |
Token ID | 1701 |
Feature activation | +5.20e-03 |
Pos logit contributions | |
Greek | +0.263 |
Elias | +0.262 |
abal | +0.251 |
ascript | +0.249 |
'). | +0.227 |
Neg logit contributions | |
uberty | -0.418 |
taboola | -0.410 |
nered | -0.403 |
sum | -0.373 |
pric | -0.368 |
Token | I |
Token ID | 314 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
uberty | +0.015 |
taboola | +0.014 |
nered | +0.014 |
sum | +0.013 |
pric | +0.013 |
Neg logit contributions | |
Greek | -0.013 |
Elias | -0.013 |
abal | -0.012 |
ascript | -0.012 |
'). | -0.011 |
Token | stood |
Token ID | 6204 |
Feature activation | -3.70e-02 |
Pos logit contributions | |
Greek | +0.389 |
Elias | +0.387 |
abal | +0.377 |
ascript | +0.376 |
'). | +0.354 |
Neg logit contributions | |
uberty | -0.265 |
taboola | -0.257 |
nered | -0.250 |
sum | -0.222 |
pric | -0.216 |
Token | still |
Token ID | 991 |
Feature activation | -5.79e-02 |
Pos logit contributions | |
Greek | +0.103 |
Elias | +0.101 |
abal | +0.099 |
ascript | +0.099 |
'). | +0.092 |
Neg logit contributions | |
uberty | -0.092 |
taboola | -0.089 |
nered | -0.088 |
sum | -0.080 |
pric | -0.078 |
Token | . |
Token ID | 13 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
Greek | +0.148 |
Elias | +0.146 |
abal | +0.142 |
ascript | +0.142 |
'). | +0.131 |
Neg logit contributions | |
uberty | -0.156 |
taboola | -0.153 |
nered | -0.150 |
sum | -0.137 |
pric | -0.134 |
Token |
|
Token ID | 198 |
Feature activation | -7.45e-02 |
Pos logit contributions | |
Greek | +0.041 |
Elias | +0.040 |
abal | +0.039 |
ascript | +0.039 |
'). | +0.036 |
Neg logit contributions | |
uberty | -0.046 |
taboola | -0.045 |
nered | -0.044 |
sum | -0.040 |
pric | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | -8.03e-02 |
Pos logit contributions | |
Greek | +0.187 |
Elias | +0.186 |
abal | +0.180 |
ascript | +0.179 |
'). | +0.167 |
Neg logit contributions | |
uberty | -0.204 |
taboola | -0.199 |
nered | -0.195 |
sum | -0.178 |
pric | -0.175 |
Token | My |
Token ID | 3666 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
Elias | +0.188 |
Greek | +0.188 |
ascript | +0.182 |
abal | +0.182 |
'). | +0.167 |
Neg logit contributions | |
uberty | -0.231 |
taboola | -0.227 |
nered | -0.223 |
sum | -0.204 |
pric | -0.200 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
Greek | +0.419 |
Elias | +0.417 |
abal | +0.407 |
ascript | +0.405 |
'). | +0.383 |
Neg logit contributions | |
uberty | -0.259 |
taboola | -0.251 |
nered | -0.244 |
sum | -0.214 |
pric | -0.209 |
Token | hugs |
Token ID | 40657 |
Feature activation | -8.60e-02 |
Pos logit contributions | |
Greek | +0.313 |
Elias | +0.311 |
abal | +0.303 |
ascript | +0.302 |
'). | +0.282 |
Neg logit contributions | |
uberty | -0.258 |
taboola | -0.251 |
nered | -0.245 |
sum | -0.220 |
pric | -0.216 |
Token | me |
Token ID | 502 |
Feature activation | +7.37e-03 |
Pos logit contributions | |
Greek | +0.252 |
Elias | +0.249 |
abal | +0.244 |
ascript | +0.244 |
'). | +0.228 |
Neg logit contributions | |
uberty | -0.200 |
taboola | -0.193 |
nered | -0.190 |
sum | -0.171 |
pric | -0.167 |
Token | as |
Token ID | 355 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
uberty | +0.068 |
taboola | +0.066 |
nered | +0.065 |
sum | +0.059 |
pric | +0.057 |
Neg logit contributions | |
Greek | -0.085 |
Elias | -0.084 |
ascript | -0.082 |
abal | -0.082 |
'). | -0.077 |
Token | if |
Token ID | 611 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
Greek | +0.050 |
Elias | +0.049 |
ascript | +0.048 |
abal | +0.048 |
'). | +0.045 |
Neg logit contributions | |
uberty | -0.038 |
taboola | -0.037 |
nered | -0.036 |
sum | -0.033 |
pric | -0.032 |
Token | there |
Token ID | 612 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
uberty | +0.094 |
taboola | +0.092 |
nered | +0.090 |
sum | +0.082 |
pric | +0.080 |
Neg logit contributions | |
Greek | -0.101 |
Elias | -0.100 |
ascript | -0.098 |
abal | -0.098 |
'). | -0.091 |
Token | isn |
Token ID | 2125 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
uberty | +0.054 |
taboola | +0.052 |
nered | +0.051 |
sum | +0.045 |
pric | +0.044 |
Neg logit contributions | |
Greek | -0.081 |
Elias | -0.081 |
abal | -0.079 |
ascript | -0.079 |
'). | -0.074 |
Token | � |
Token ID | 447 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
Greek | +0.103 |
Elias | +0.102 |
abal | +0.099 |
ascript | +0.099 |
'). | +0.093 |
Neg logit contributions | |
uberty | -0.069 |
taboola | -0.067 |
nered | -0.065 |
sum | -0.058 |
pric | -0.056 |
Token | � |
Token ID | 247 |
Feature activation | -5.97e-02 |
Pos logit contributions | |
Greek | +0.100 |
Elias | +0.099 |
abal | +0.096 |
ascript | +0.096 |
'). | +0.089 |
Neg logit contributions | |
uberty | -0.094 |
taboola | -0.091 |
nered | -0.089 |
sum | -0.081 |
pric | -0.079 |
Token | t |
Token ID | 83 |
Feature activation | -5.36e-02 |
Pos logit contributions | |
Greek | +0.190 |
Elias | +0.189 |
abal | +0.185 |
ascript | +0.184 |
'). | +0.174 |
Neg logit contributions | |
uberty | -0.123 |
taboola | -0.119 |
nered | -0.116 |
sum | -0.102 |
pric | -0.100 |
Token | a |
Token ID | 257 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
Greek | +0.151 |
Elias | +0.149 |
ascript | +0.146 |
abal | +0.145 |
'). | +0.136 |
Neg logit contributions | |
uberty | -0.131 |
taboola | -0.127 |
nered | -0.125 |
sum | -0.114 |
pric | -0.111 |
Token | group |
Token ID | 1448 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
uberty | +0.051 |
taboola | +0.050 |
nered | +0.049 |
sum | +0.045 |
pric | +0.043 |
Neg logit contributions | |
Greek | -0.061 |
Elias | -0.061 |
ascript | -0.059 |
abal | -0.059 |
'). | -0.055 |
Token | of |
Token ID | 286 |
Feature activation | -4.96e-02 |
Pos logit contributions | |
Greek | +0.281 |
Elias | +0.279 |
abal | +0.271 |
ascript | +0.270 |
'). | +0.251 |
Neg logit contributions | |
uberty | -0.275 |
taboola | -0.268 |
nered | -0.263 |
sum | -0.239 |
pric | -0.234 |
Token | Israelis |
Token ID | 21137 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
Greek | +0.132 |
Elias | +0.130 |
ascript | +0.127 |
abal | +0.127 |
'). | +0.118 |
Neg logit contributions | |
uberty | -0.128 |
taboola | -0.125 |
nered | -0.123 |
sum | -0.112 |
pric | -0.110 |
Token |
|
Token ID | 198 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
Greek | +0.092 |
Elias | +0.091 |
abal | +0.088 |
ascript | +0.088 |
'). | +0.081 |
Neg logit contributions | |
uberty | -0.115 |
taboola | -0.113 |
nered | -0.111 |
sum | -0.102 |
pric | -0.100 |
Token |
|
Token ID | 198 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
uberty | +0.156 |
taboola | +0.154 |
nered | +0.151 |
sum | +0.138 |
pric | +0.134 |
Neg logit contributions | |
Greek | -0.151 |
Elias | -0.150 |
ascript | -0.146 |
abal | -0.145 |
'). | -0.134 |
Token | 1 |
Token ID | 16 |
Feature activation | +7.77e-02 |
Pos logit contributions | |
uberty | +0.056 |
taboola | +0.055 |
nered | +0.054 |
sum | +0.048 |
pric | +0.047 |
Neg logit contributions | |
Greek | -0.073 |
Elias | -0.073 |
abal | -0.071 |
ascript | -0.071 |
'). | -0.066 |
Token | a |
Token ID | 64 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
uberty | +0.223 |
taboola | +0.219 |
nered | +0.215 |
sum | +0.197 |
pric | +0.193 |
Neg logit contributions | |
Greek | -0.185 |
Elias | -0.184 |
abal | -0.177 |
ascript | -0.177 |
'). | -0.163 |
Token | 1 |
Token ID | 352 |
Feature activation | +4.35e-02 |
Pos logit contributions | |
Greek | +0.037 |
Elias | +0.037 |
abal | +0.036 |
ascript | +0.036 |
'). | +0.034 |
Neg logit contributions | |
uberty | -0.026 |
taboola | -0.025 |
nered | -0.025 |
sum | -0.022 |
pric | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -7.05e-02 |
Pos logit contributions | |
uberty | +0.142 |
taboola | +0.139 |
nered | +0.137 |
sum | +0.127 |
pric | +0.125 |
Neg logit contributions | |
Greek | -0.086 |
Elias | -0.086 |
abal | -0.082 |
ascript | -0.082 |
'). | -0.074 |
Token | Sw |
Token ID | 2451 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
Greek | +0.179 |
Elias | +0.178 |
abal | +0.173 |
ascript | +0.172 |
'). | +0.160 |
Neg logit contributions | |
uberty | -0.191 |
taboola | -0.186 |
nered | -0.183 |
sum | -0.167 |
pric | -0.164 |
Token | immer |
Token ID | 10957 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
uberty | +0.286 |
taboola | +0.278 |
nered | +0.274 |
sum | +0.249 |
pric | +0.244 |
Neg logit contributions | |
Greek | -0.272 |
Elias | -0.271 |
ascript | -0.262 |
abal | -0.261 |
'). | -0.242 |
Token | means |
Token ID | 1724 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
Greek | +0.282 |
Elias | +0.280 |
abal | +0.272 |
ascript | +0.271 |
'). | +0.253 |
Neg logit contributions | |
uberty | -0.253 |
taboola | -0.246 |
nered | -0.241 |
sum | -0.217 |
pric | -0.213 |
Token | to |
Token ID | 284 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
Greek | +0.178 |
Elias | +0.177 |
abal | +0.172 |
ascript | +0.171 |
'). | +0.161 |
Neg logit contributions | |
uberty | -0.149 |
taboola | -0.145 |
nered | -0.142 |
sum | -0.127 |
pric | -0.124 |
Token | keep |
Token ID | 1394 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
uberty | +0.041 |
taboola | +0.040 |
nered | +0.039 |
sum | +0.035 |
pric | +0.034 |
Neg logit contributions | |
Greek | -0.054 |
Elias | -0.054 |
ascript | -0.053 |
abal | -0.053 |
'). | -0.049 |
Token | all |
Token ID | 477 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
uberty | +0.119 |
taboola | +0.116 |
nered | +0.114 |
sum | +0.103 |
pric | +0.099 |
Neg logit contributions | |
Greek | -0.150 |
Elias | -0.148 |
ascript | -0.145 |
abal | -0.145 |
'). | -0.136 |
Token | rights |
Token ID | 2489 |
Feature activation | +7.05e-03 |
Pos logit contributions | |
uberty | +0.098 |
taboola | +0.096 |
nered | +0.094 |
sum | +0.086 |
pric | +0.083 |
Neg logit contributions | |
Greek | -0.118 |
Elias | -0.116 |
abal | -0.114 |
ascript | -0.114 |
'). | -0.106 |
Token | should |
Token ID | 815 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
uberty | +0.015 |
taboola | +0.015 |
nered | +0.015 |
sum | +0.013 |
pric | +0.013 |
Neg logit contributions | |
Greek | -0.021 |
Elias | -0.021 |
ascript | -0.021 |
abal | -0.021 |
'). | -0.020 |
Token | be |
Token ID | 307 |
Feature activation | -9.89e-03 |
Pos logit contributions | |
uberty | +0.055 |
taboola | +0.053 |
nered | +0.052 |
sum | +0.047 |
pric | +0.046 |
Neg logit contributions | |
Greek | -0.067 |
Elias | -0.066 |
abal | -0.065 |
ascript | -0.064 |
'). | -0.060 |
Token | utterly |
Token ID | 15950 |
Feature activation | -8.56e-02 |
Pos logit contributions | |
Greek | +0.029 |
Elias | +0.029 |
abal | +0.028 |
ascript | +0.028 |
'). | +0.026 |
Neg logit contributions | |
uberty | -0.023 |
taboola | -0.022 |
nered | -0.022 |
sum | -0.019 |
pric | -0.019 |
Token | unacceptable |
Token ID | 18010 |
Feature activation | -8.87e-02 |
Pos logit contributions | |
Greek | +0.276 |
Elias | +0.275 |
abal | +0.268 |
ascript | +0.267 |
'). | +0.252 |
Neg logit contributions | |
uberty | -0.173 |
taboola | -0.168 |
nered | -0.163 |
sum | -0.143 |
pric | -0.140 |
Token | bears |
Token ID | 13062 |
Feature activation | +6.90e-02 |
Pos logit contributions | |
Greek | +0.216 |
Elias | +0.214 |
abal | +0.208 |
ascript | +0.206 |
'). | +0.191 |
Neg logit contributions | |
uberty | -0.250 |
taboola | -0.244 |
nered | -0.239 |
sum | -0.219 |
pric | -0.216 |
Token | any |
Token ID | 597 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
uberty | +0.151 |
taboola | +0.147 |
nered | +0.144 |
sum | +0.129 |
pric | +0.125 |
Neg logit contributions | |
Greek | -0.210 |
Elias | -0.209 |
abal | -0.204 |
ascript | -0.203 |
'). | -0.191 |
Token | relation |
Token ID | 8695 |
Feature activation | +9.69e-02 |
Pos logit contributions | |
Greek | +0.335 |
Elias | +0.332 |
ascript | +0.323 |
abal | +0.323 |
'). | +0.303 |
Neg logit contributions | |
uberty | -0.248 |
taboola | -0.241 |
nered | -0.236 |
sum | -0.214 |
pric | -0.208 |
Token | to |
Token ID | 284 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
uberty | +0.227 |
taboola | +0.221 |
nered | +0.217 |
sum | +0.195 |
pric | +0.190 |
Neg logit contributions | |
Greek | -0.282 |
Elias | -0.280 |
abal | -0.272 |
ascript | -0.272 |
'). | -0.255 |
Token | Brexit |
Token ID | 11435 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
Greek | +0.150 |
Elias | +0.148 |
ascript | +0.145 |
abal | +0.144 |
'). | +0.135 |
Neg logit contributions | |
uberty | -0.131 |
taboola | -0.127 |
nered | -0.125 |
sum | -0.114 |
pric | -0.111 |
Token | olph |
Token ID | 10196 |
Feature activation | -2.77e-03 |
Pos logit contributions | |
uberty | +0.066 |
taboola | +0.065 |
nered | +0.064 |
sum | +0.060 |
pric | +0.059 |
Neg logit contributions | |
Greek | -0.037 |
Elias | -0.036 |
ascript | -0.035 |
abal | -0.035 |
'). | -0.031 |
Token | us |
Token ID | 385 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
Greek | +0.007 |
Elias | +0.006 |
ascript | +0.006 |
abal | +0.006 |
'). | +0.006 |
Neg logit contributions | |
uberty | -0.008 |
taboola | -0.008 |
nered | -0.008 |
sum | -0.007 |
pric | -0.007 |
Token | Bus |
Token ID | 5869 |
Feature activation | -8.09e-02 |
Pos logit contributions | |
Greek | +0.050 |
Elias | +0.049 |
abal | +0.048 |
ascript | +0.048 |
'). | +0.044 |
Neg logit contributions | |
uberty | -0.046 |
taboola | -0.045 |
nered | -0.044 |
sum | -0.040 |
pric | -0.039 |
Token | ch |
Token ID | 354 |
Feature activation | +7.15e-02 |
Pos logit contributions | |
Greek | +0.250 |
Elias | +0.248 |
abal | +0.242 |
ascript | +0.241 |
'). | +0.227 |
Neg logit contributions | |
uberty | -0.175 |
taboola | -0.170 |
nered | -0.166 |
sum | -0.147 |
pric | -0.144 |
Token | III |
Token ID | 6711 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
uberty | +0.181 |
taboola | +0.176 |
nered | +0.174 |
sum | +0.158 |
pric | +0.154 |
Neg logit contributions | |
Greek | -0.194 |
Elias | -0.191 |
abal | -0.187 |
ascript | -0.187 |
'). | -0.174 |
Token | surprised |
Token ID | 6655 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
uberty | +0.102 |
taboola | +0.099 |
nered | +0.098 |
sum | +0.089 |
pric | +0.087 |
Neg logit contributions | |
Greek | -0.115 |
Elias | -0.113 |
abal | -0.111 |
ascript | -0.111 |
'). | -0.103 |
Token | their |
Token ID | 511 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
Greek | +0.096 |
Elias | +0.095 |
abal | +0.093 |
ascript | +0.093 |
'). | +0.086 |
Neg logit contributions | |
uberty | -0.083 |
taboola | -0.081 |
nered | -0.079 |
sum | -0.072 |
pric | -0.070 |
Token | father |
Token ID | 2988 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
Greek | +0.037 |
Elias | +0.037 |
abal | +0.036 |
ascript | +0.036 |
'). | +0.034 |
Neg logit contributions | |
uberty | -0.028 |
taboola | -0.027 |
nered | -0.026 |
sum | -0.024 |
pric | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +8.21e-03 |
Pos logit contributions | |
uberty | +0.502 |
taboola | +0.491 |
nered | +0.480 |
sum | +0.439 |
pric | +0.432 |
Neg logit contributions | |
Greek | -0.447 |
Elias | -0.445 |
abal | -0.431 |
ascript | -0.428 |
'). | -0.396 |
Token | August |
Token ID | 2932 |
Feature activation | -6.53e-02 |
Pos logit contributions | |
uberty | +0.022 |
taboola | +0.022 |
nered | +0.021 |
sum | +0.019 |
pric | +0.019 |
Neg logit contributions | |
Greek | -0.021 |
Elias | -0.021 |
abal | -0.020 |
ascript | -0.020 |
'). | -0.019 |
Token | A |
Token ID | 317 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
Greek | +0.154 |
Elias | +0.151 |
ascript | +0.149 |
abal | +0.147 |
'). | +0.136 |
Neg logit contributions | |
uberty | -0.188 |
taboola | -0.184 |
nered | -0.182 |
sum | -0.167 |
pric | -0.163 |
Token | involving |
Token ID | 7411 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
uberty | +0.007 |
taboola | +0.007 |
nered | +0.007 |
sum | +0.006 |
pric | +0.006 |
Neg logit contributions | |
Greek | -0.008 |
Elias | -0.008 |
abal | -0.008 |
ascript | -0.008 |
'). | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
Greek | +0.084 |
Elias | +0.083 |
abal | +0.081 |
ascript | +0.081 |
'). | +0.076 |
Neg logit contributions | |
uberty | -0.063 |
taboola | -0.061 |
nered | -0.060 |
sum | -0.054 |
pric | -0.053 |
Token | entire |
Token ID | 2104 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
Greek | +0.047 |
Elias | +0.046 |
abal | +0.045 |
ascript | +0.045 |
'). | +0.042 |
Neg logit contributions | |
uberty | -0.035 |
taboola | -0.034 |
nered | -0.033 |
sum | -0.030 |
pric | -0.029 |
Token | palm |
Token ID | 18057 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
Greek | +0.072 |
Elias | +0.072 |
abal | +0.070 |
ascript | +0.070 |
'). | +0.066 |
Neg logit contributions | |
uberty | -0.049 |
taboola | -0.047 |
nered | -0.046 |
sum | -0.041 |
pric | -0.040 |
Token | opl |
Token ID | 20106 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
uberty | +0.038 |
taboola | +0.037 |
nered | +0.036 |
sum | +0.032 |
pric | +0.031 |
Neg logit contributions | |
Greek | -0.052 |
Elias | -0.052 |
abal | -0.050 |
ascript | -0.050 |
'). | -0.047 |
Token | ant |
Token ID | 415 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
uberty | +0.322 |
taboola | +0.311 |
nered | +0.307 |
sum | +0.280 |
pric | +0.273 |
Neg logit contributions | |
Greek | -0.312 |
Elias | -0.311 |
ascript | -0.299 |
abal | -0.298 |
'). | -0.278 |
Token | ar |
Token ID | 283 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
Greek | +0.733 |
Elias | +0.726 |
abal | +0.701 |
ascript | +0.698 |
'). | +0.641 |
Neg logit contributions | |
uberty | -0.981 |
taboola | -0.960 |
nered | -0.944 |
sum | -0.869 |
pric | -0.854 |
Token | surfaces |
Token ID | 16649 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
Greek | +0.761 |
Elias | +0.758 |
abal | +0.743 |
ascript | +0.741 |
'). | +0.707 |
Neg logit contributions | |
uberty | -0.258 |
taboola | -0.245 |
nered | -0.235 |
sum | -0.190 |
pric | -0.182 |
Token | . |
Token ID | 13 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
Greek | +0.064 |
Elias | +0.064 |
abal | +0.062 |
ascript | +0.062 |
'). | +0.056 |
Neg logit contributions | |
uberty | -0.086 |
taboola | -0.083 |
nered | -0.083 |
sum | -0.076 |
pric | -0.075 |
Token | [ |
Token ID | 685 |
Feature activation | +5.98e-02 |
Pos logit contributions | |
Greek | +0.064 |
Elias | +0.063 |
abal | +0.062 |
ascript | +0.061 |
'). | +0.057 |
Neg logit contributions | |
uberty | -0.065 |
taboola | -0.064 |
nered | -0.062 |
sum | -0.057 |
pric | -0.056 |
Token | 1 |
Token ID | 16 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
uberty | +0.162 |
taboola | +0.158 |
nered | +0.155 |
sum | +0.141 |
pric | +0.138 |
Neg logit contributions | |
Greek | -0.152 |
Elias | -0.151 |
abal | -0.147 |
ascript | -0.147 |
'). | -0.136 |
Token | to |
Token ID | 284 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
uberty | +0.027 |
taboola | +0.026 |
nered | +0.025 |
sum | +0.023 |
pric | +0.022 |
Neg logit contributions | |
Greek | -0.033 |
Elias | -0.032 |
abal | -0.032 |
ascript | -0.032 |
'). | -0.030 |
Token | combine |
Token ID | 12082 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
Greek | +0.090 |
Elias | +0.090 |
ascript | +0.087 |
abal | +0.087 |
'). | +0.082 |
Neg logit contributions | |
uberty | -0.067 |
taboola | -0.065 |
nered | -0.064 |
sum | -0.058 |
pric | -0.056 |
Token | the |
Token ID | 262 |
Feature activation | +9.38e-03 |
Pos logit contributions | |
uberty | +0.063 |
taboola | +0.061 |
nered | +0.061 |
sum | +0.055 |
pric | +0.053 |
Neg logit contributions | |
Greek | -0.080 |
Elias | -0.079 |
abal | -0.077 |
ascript | -0.077 |
'). | -0.072 |
Token | brand |
Token ID | 4508 |
Feature activation | +7.76e-02 |
Pos logit contributions | |
uberty | +0.021 |
taboola | +0.021 |
nered | +0.020 |
sum | +0.018 |
pric | +0.018 |
Neg logit contributions | |
Greek | -0.028 |
Elias | -0.028 |
abal | -0.027 |
ascript | -0.027 |
'). | -0.025 |
Token | - |
Token ID | 12 |
Feature activation | +3.26e-03 |
Pos logit contributions | |
uberty | +0.194 |
taboola | +0.188 |
nered | +0.186 |
sum | +0.167 |
pric | +0.164 |
Neg logit contributions | |
Greek | -0.214 |
Elias | -0.212 |
abal | -0.207 |
ascript | -0.206 |
'). | -0.193 |
Token | new |
Token ID | 3605 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
uberty | +0.009 |
taboola | +0.009 |
nered | +0.009 |
sum | +0.008 |
pric | +0.008 |
Neg logit contributions | |
Greek | -0.008 |
Elias | -0.008 |
abal | -0.008 |
ascript | -0.008 |
'). | -0.007 |
Token | trick |
Token ID | 6908 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Greek | +0.843 |
Elias | +0.837 |
abal | +0.813 |
ascript | +0.810 |
'). | +0.754 |
Neg logit contributions | |
uberty | -0.813 |
taboola | -0.792 |
nered | -0.776 |
sum | -0.704 |
pric | -0.690 |
Token | of |
Token ID | 286 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
uberty | +0.283 |
taboola | +0.275 |
nered | +0.272 |
sum | +0.246 |
pric | +0.241 |
Neg logit contributions | |
Greek | -0.293 |
Elias | -0.290 |
abal | -0.281 |
ascript | -0.281 |
'). | -0.262 |
Token | horizontal |
Token ID | 16021 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
Greek | +0.044 |
Elias | +0.043 |
abal | +0.042 |
ascript | +0.042 |
'). | +0.040 |
Neg logit contributions | |
uberty | -0.033 |
taboola | -0.032 |
nered | -0.031 |
sum | -0.028 |
pric | -0.027 |
Token | drilling |
Token ID | 19747 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
Greek | +0.474 |
Elias | +0.472 |
abal | +0.459 |
ascript | +0.457 |
'). | +0.430 |
Neg logit contributions | |
uberty | -0.365 |
taboola | -0.355 |
nered | -0.345 |
sum | -0.307 |
pric | -0.301 |
Token | with |
Token ID | 351 |
Feature activation | +5.53e-02 |
Pos logit contributions | |
Greek | +0.065 |
Elias | +0.065 |
abal | +0.063 |
ascript | +0.063 |
'). | +0.059 |
Neg logit contributions | |
uberty | -0.062 |
taboola | -0.060 |
nered | -0.059 |
sum | -0.054 |
pric | -0.053 |
Token | me |
Token ID | 502 |
Feature activation | -4.67e-02 |
Pos logit contributions | |
Greek | +0.154 |
Elias | +0.152 |
abal | +0.147 |
ascript | +0.146 |
'). | +0.135 |
Neg logit contributions | |
uberty | -0.200 |
taboola | -0.195 |
nered | -0.192 |
sum | -0.176 |
pric | -0.173 |
Token | count |
Token ID | 954 |
Feature activation | +7.27e-03 |
Pos logit contributions | |
Greek | +0.143 |
Elias | +0.142 |
ascript | +0.138 |
abal | +0.138 |
'). | +0.129 |
Neg logit contributions | |
uberty | -0.102 |
taboola | -0.099 |
nered | -0.097 |
sum | -0.088 |
pric | -0.085 |
Token | quickly |
Token ID | 2952 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
uberty | +0.019 |
taboola | +0.018 |
nered | +0.018 |
sum | +0.017 |
pric | +0.016 |
Neg logit contributions | |
Greek | -0.019 |
Elias | -0.019 |
ascript | -0.018 |
abal | -0.018 |
'). | -0.017 |
Token | ." |
Token ID | 526 |
Feature activation | -5.59e-02 |
Pos logit contributions | |
Greek | +0.103 |
Elias | +0.102 |
abal | +0.098 |
ascript | +0.098 |
'). | +0.088 |
Neg logit contributions | |
uberty | -0.168 |
taboola | -0.165 |
nered | -0.163 |
sum | -0.152 |
pric | -0.149 |
Token | P |
Token ID | 350 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
Greek | +0.142 |
Elias | +0.140 |
ascript | +0.138 |
abal | +0.137 |
'). | +0.126 |
Neg logit contributions | |
uberty | -0.151 |
taboola | -0.147 |
nered | -0.144 |
sum | -0.133 |
pric | -0.129 |
Token | ause |
Token ID | 682 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
Greek | +0.052 |
Elias | +0.052 |
abal | +0.051 |
ascript | +0.050 |
'). | +0.047 |
Neg logit contributions | |
uberty | -0.048 |
taboola | -0.047 |
nered | -0.045 |
sum | -0.041 |
pric | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -5.90e-02 |
Pos logit contributions | |
Greek | +0.705 |
Elias | +0.700 |
abal | +0.675 |
ascript | +0.674 |
'). | +0.617 |
Neg logit contributions | |
uberty | -0.953 |
taboola | -0.933 |
nered | -0.914 |
sum | -0.840 |
pric | -0.829 |
Token | " |
Token ID | 366 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
Greek | +0.151 |
Elias | +0.149 |
ascript | +0.146 |
abal | +0.145 |
'). | +0.135 |
Neg logit contributions | |
uberty | -0.158 |
taboola | -0.154 |
nered | -0.152 |
sum | -0.139 |
pric | -0.135 |
Token | O |
Token ID | 46 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
uberty | +0.035 |
taboola | +0.035 |
nered | +0.034 |
sum | +0.031 |
pric | +0.030 |
Neg logit contributions | |
Elias | -0.031 |
Greek | -0.031 |
ascript | -0.030 |
abal | -0.030 |
'). | -0.028 |
Token | uch |
Token ID | 794 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
uberty | +0.085 |
taboola | +0.083 |
nered | +0.081 |
sum | +0.074 |
pric | +0.073 |
Neg logit contributions | |
Greek | -0.073 |
Elias | -0.073 |
abal | -0.070 |
ascript | -0.070 |
'). | -0.065 |
Token | , |
Token ID | 11 |
Feature activation | -3.93e-02 |
Pos logit contributions | |
uberty | +0.422 |
taboola | +0.413 |
nered | +0.407 |
sum | +0.377 |
pric | +0.371 |
Neg logit contributions | |
Greek | -0.271 |
Elias | -0.268 |
abal | -0.259 |
ascript | -0.257 |
'). | -0.234 |
Token | which |
Token ID | 543 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
uberty | +0.060 |
taboola | +0.059 |
nered | +0.058 |
sum | +0.052 |
pric | +0.051 |
Neg logit contributions | |
Greek | -0.071 |
Elias | -0.070 |
abal | -0.068 |
ascript | -0.068 |
'). | -0.064 |
Token | is |
Token ID | 318 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
Greek | +0.080 |
Elias | +0.079 |
ascript | +0.078 |
abal | +0.078 |
'). | +0.073 |
Neg logit contributions | |
uberty | -0.061 |
taboola | -0.059 |
nered | -0.058 |
sum | -0.052 |
pric | -0.051 |
Token | a |
Token ID | 257 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
Greek | +0.041 |
Elias | +0.041 |
abal | +0.040 |
ascript | +0.040 |
'). | +0.037 |
Neg logit contributions | |
uberty | -0.030 |
taboola | -0.029 |
nered | -0.029 |
sum | -0.026 |
pric | -0.025 |
Token | super |
Token ID | 2208 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
uberty | +0.025 |
taboola | +0.024 |
nered | +0.024 |
sum | +0.021 |
pric | +0.020 |
Neg logit contributions | |
Greek | -0.036 |
Elias | -0.036 |
abal | -0.035 |
ascript | -0.035 |
'). | -0.033 |
Token | higher |
Token ID | 2440 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
Greek | +0.407 |
Elias | +0.406 |
abal | +0.395 |
ascript | +0.393 |
'). | +0.372 |
Neg logit contributions | |
uberty | -0.263 |
taboola | -0.252 |
nered | -0.246 |
sum | -0.213 |
pric | -0.208 |
Token | resolution |
Token ID | 6323 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
Greek | +0.368 |
Elias | +0.366 |
abal | +0.356 |
ascript | +0.355 |
'). | +0.334 |
Neg logit contributions | |
uberty | -0.264 |
taboola | -0.255 |
nered | -0.249 |
sum | -0.220 |
pric | -0.215 |
Token | that |
Token ID | 326 |
Feature activation | -5.06e-02 |
Pos logit contributions | |
Greek | +0.901 |
Elias | +0.895 |
abal | +0.869 |
ascript | +0.866 |
'). | +0.806 |
Neg logit contributions | |
uberty | -0.884 |
taboola | -0.862 |
nered | -0.845 |
sum | -0.768 |
pric | -0.753 |
Token | I |
Token ID | 314 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
Greek | +0.146 |
Elias | +0.145 |
abal | +0.141 |
ascript | +0.141 |
'). | +0.132 |
Neg logit contributions | |
uberty | -0.120 |
taboola | -0.117 |
nered | -0.114 |
sum | -0.103 |
pric | -0.101 |
Token | effectively |
Token ID | 6840 |
Feature activation | +5.42e-02 |
Pos logit contributions | |
Greek | +0.159 |
Elias | +0.158 |
ascript | +0.154 |
abal | +0.154 |
'). | +0.143 |
Neg logit contributions | |
uberty | -0.119 |
taboola | -0.116 |
nered | -0.114 |
sum | -0.104 |
pric | -0.100 |
Token | can |
Token ID | 460 |
Feature activation | -8.13e-03 |
Pos logit contributions | |
uberty | +0.114 |
taboola | +0.111 |
nered | +0.108 |
sum | +0.098 |
pric | +0.094 |
Neg logit contributions | |
Greek | -0.170 |
Elias | -0.168 |
ascript | -0.165 |
abal | -0.165 |
'). | -0.154 |
Token | not |
Token ID | 407 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
Greek | +0.025 |
Elias | +0.025 |
abal | +0.024 |
ascript | +0.024 |
'). | +0.023 |
Neg logit contributions | |
uberty | -0.018 |
taboola | -0.017 |
nered | -0.017 |
sum | -0.015 |
pric | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
uberty | +0.232 |
taboola | +0.227 |
nered | +0.222 |
sum | +0.204 |
pric | +0.200 |
Neg logit contributions | |
Greek | -0.218 |
Elias | -0.216 |
abal | -0.210 |
ascript | -0.210 |
'). | -0.194 |
Token | 2013 |
Token ID | 2211 |
Feature activation | -8.40e-03 |
Pos logit contributions | |
uberty | +0.041 |
taboola | +0.040 |
nered | +0.039 |
sum | +0.036 |
pric | +0.036 |
Neg logit contributions | |
Greek | -0.035 |
Elias | -0.034 |
ascript | -0.033 |
abal | -0.033 |
'). | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | -6.64e-02 |
Pos logit contributions | |
Greek | +0.021 |
Elias | +0.020 |
ascript | +0.020 |
abal | +0.020 |
'). | +0.018 |
Neg logit contributions | |
uberty | -0.023 |
taboola | -0.023 |
nered | -0.022 |
sum | -0.021 |
pric | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -5.53e-02 |
Pos logit contributions | |
Greek | +0.172 |
Elias | +0.171 |
ascript | +0.167 |
abal | +0.165 |
'). | +0.153 |
Neg logit contributions | |
uberty | -0.175 |
taboola | -0.172 |
nered | -0.169 |
sum | -0.154 |
pric | -0.150 |
Token | Pe |
Token ID | 6435 |
Feature activation | +7.22e-02 |
Pos logit contributions | |
Elias | +0.133 |
Greek | +0.131 |
ascript | +0.130 |
abal | +0.128 |
'). | +0.117 |
Neg logit contributions | |
uberty | -0.156 |
taboola | -0.154 |
nered | -0.150 |
sum | -0.137 |
pric | -0.135 |
Token | ak |
Token ID | 461 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
uberty | +0.212 |
taboola | +0.208 |
nered | +0.203 |
sum | +0.187 |
pric | +0.184 |
Neg logit contributions | |
Greek | -0.167 |
Elias | -0.166 |
abal | -0.160 |
ascript | -0.159 |
'). | -0.147 |
Token | price |
Token ID | 2756 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
Greek | +0.846 |
Elias | +0.841 |
abal | +0.817 |
ascript | +0.808 |
'). | +0.761 |
Neg logit contributions | |
uberty | -0.752 |
taboola | -0.729 |
nered | -0.713 |
sum | -0.637 |
pric | -0.627 |
Token | : |
Token ID | 25 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
Greek | +0.068 |
Elias | +0.068 |
abal | +0.066 |
ascript | +0.066 |
'). | +0.061 |
Neg logit contributions | |
uberty | -0.065 |
taboola | -0.064 |
nered | -0.062 |
sum | -0.057 |
pric | -0.055 |
Token | $ |
Token ID | 720 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
Greek | +0.056 |
Elias | +0.056 |
abal | +0.054 |
ascript | +0.054 |
'). | +0.050 |
Neg logit contributions | |
uberty | -0.054 |
taboola | -0.053 |
nered | -0.052 |
sum | -0.047 |
pric | -0.046 |
Token | 266 |
Token ID | 25540 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
uberty | +0.043 |
taboola | +0.042 |
nered | +0.042 |
sum | +0.038 |
pric | +0.037 |
Neg logit contributions | |
Greek | -0.041 |
Elias | -0.041 |
ascript | -0.040 |
abal | -0.040 |
'). | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
uberty | +0.354 |
taboola | +0.348 |
nered | +0.341 |
sum | +0.315 |
pric | +0.310 |
Neg logit contributions | |
Greek | -0.278 |
Elias | -0.275 |
abal | -0.267 |
ascript | -0.265 |
'). | -0.245 |