Token | Daily |
Token ID | 6714 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
)", | +0.244 |
uyomi | +0.212 |
glers | +0.211 |
ingo | +0.210 |
harm | +0.201 |
Neg logit contributions | |
smoot | -0.225 |
fres | -0.210 |
Pac | -0.206 |
ans | -0.205 |
chev | -0.200 |
Token | Dispatch |
Token ID | 35934 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
)", | +0.092 |
ingo | +0.078 |
glers | +0.077 |
uyomi | +0.076 |
harm | +0.075 |
Neg logit contributions | |
smoot | -0.104 |
fres | -0.098 |
ans | -0.097 |
Pac | -0.095 |
chev | -0.094 |
Token | and |
Token ID | 290 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
smoot | +0.007 |
fres | +0.007 |
ans | +0.007 |
Pac | +0.007 |
Spur | +0.007 |
Neg logit contributions | |
)", | -0.009 |
uyomi | -0.008 |
ingo | -0.008 |
glers | -0.008 |
harm | -0.007 |
Token | Editor |
Token ID | 12058 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
)", | +0.091 |
ingo | +0.078 |
uyomi | +0.077 |
glers | +0.077 |
harm | +0.074 |
Neg logit contributions | |
smoot | -0.092 |
fres | -0.087 |
ans | -0.086 |
Pac | -0.084 |
chev | -0.083 |
Token | 's |
Token ID | 338 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
)", | +0.035 |
uyomi | +0.030 |
ingo | +0.030 |
glers | +0.030 |
harm | +0.029 |
Neg logit contributions | |
smoot | -0.025 |
fres | -0.023 |
ans | -0.023 |
Pac | -0.022 |
Spur | -0.022 |
Token | Picks |
Token ID | 33957 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
)", | +0.277 |
uyomi | +0.237 |
ingo | +0.235 |
glers | +0.235 |
emale | +0.228 |
Neg logit contributions | |
smoot | -0.273 |
fres | -0.259 |
ans | -0.255 |
Pac | -0.251 |
Spur | -0.247 |
Token | . |
Token ID | 13 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
)", | +1.368 |
ingo | +1.193 |
uyomi | +1.181 |
glers | +1.171 |
harm | +1.141 |
Neg logit contributions | |
smoot | -1.185 |
fres | -1.114 |
ans | -1.095 |
Pac | -1.079 |
Spur | -1.064 |
Token |
|
Token ID | 198 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
)", | +0.043 |
glers | +0.038 |
uyomi | +0.038 |
ingo | +0.038 |
harm | +0.037 |
Neg logit contributions | |
smoot | -0.027 |
fres | -0.025 |
ans | -0.025 |
Pac | -0.024 |
bolted | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
)", | +0.012 |
ingo | +0.010 |
glers | +0.010 |
uyomi | +0.010 |
harm | +0.010 |
Neg logit contributions | |
smoot | -0.009 |
fres | -0.008 |
ans | -0.008 |
Pac | -0.008 |
Spur | -0.008 |
Token | Much |
Token ID | 20045 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
)", | +0.011 |
ingo | +0.009 |
glers | +0.009 |
uyomi | +0.009 |
harm | +0.009 |
Neg logit contributions | |
smoot | -0.013 |
fres | -0.012 |
ans | -0.012 |
Pac | -0.012 |
Spur | -0.012 |
Token | of |
Token ID | 286 |
Feature activation | +6.57e-03 |
Pos logit contributions | |
smoot | +0.119 |
fres | +0.112 |
ans | +0.110 |
Pac | +0.109 |
Spur | +0.106 |
Neg logit contributions | |
)", | -0.155 |
glers | -0.135 |
ingo | -0.135 |
uyomi | -0.134 |
harm | -0.131 |
Token | Daily |
Token ID | 6714 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
)", | +0.258 |
uyomi | +0.225 |
glers | +0.223 |
ingo | +0.223 |
emale | +0.214 |
Neg logit contributions | |
smoot | -0.223 |
fres | -0.209 |
ans | -0.204 |
Pac | -0.203 |
chev | -0.198 |
Token | Dispatch |
Token ID | 35934 |
Feature activation | -4.66e-02 |
Pos logit contributions | |
)", | +0.094 |
ingo | +0.079 |
glers | +0.079 |
uyomi | +0.078 |
harm | +0.076 |
Neg logit contributions | |
smoot | -0.103 |
fres | -0.097 |
ans | -0.097 |
Pac | -0.095 |
chev | -0.094 |
Token | and |
Token ID | 290 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
smoot | +0.031 |
fres | +0.030 |
ans | +0.029 |
Pac | +0.028 |
Spur | +0.028 |
Neg logit contributions | |
)", | -0.039 |
uyomi | -0.034 |
ingo | -0.033 |
glers | -0.033 |
emale | -0.032 |
Token | Editor |
Token ID | 12058 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
)", | +0.122 |
ingo | +0.104 |
uyomi | +0.103 |
glers | +0.103 |
harm | +0.099 |
Neg logit contributions | |
smoot | -0.122 |
fres | -0.115 |
ans | -0.114 |
Pac | -0.112 |
chev | -0.111 |
Token | 's |
Token ID | 338 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
smoot | +0.006 |
fres | +0.006 |
ans | +0.006 |
Pac | +0.006 |
Spur | +0.006 |
Neg logit contributions | |
)", | -0.009 |
uyomi | -0.008 |
ingo | -0.008 |
glers | -0.008 |
harm | -0.008 |
Token | Picks |
Token ID | 33957 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
)", | +0.221 |
uyomi | +0.189 |
ingo | +0.188 |
glers | +0.188 |
emale | +0.183 |
Neg logit contributions | |
smoot | -0.214 |
fres | -0.202 |
ans | -0.199 |
Pac | -0.196 |
Spur | -0.193 |
Token | . |
Token ID | 13 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
)", | +1.230 |
ingo | +1.069 |
uyomi | +1.062 |
glers | +1.052 |
harm | +1.026 |
Neg logit contributions | |
smoot | -1.049 |
fres | -0.987 |
ans | -0.968 |
Pac | -0.955 |
Spur | -0.941 |
Token |
|
Token ID | 198 |
Feature activation | -7.75e-02 |
Pos logit contributions | |
smoot | +0.013 |
fres | +0.012 |
ans | +0.012 |
Pac | +0.012 |
bolted | +0.012 |
Neg logit contributions | |
)", | -0.021 |
uyomi | -0.019 |
glers | -0.019 |
ingo | -0.019 |
emale | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
smoot | +0.050 |
fres | +0.047 |
ans | +0.046 |
Pac | +0.045 |
Spur | +0.044 |
Neg logit contributions | |
)", | -0.067 |
ingo | -0.058 |
glers | -0.058 |
uyomi | -0.058 |
harm | -0.056 |
Token | The |
Token ID | 464 |
Feature activation | -4.05e-03 |
Pos logit contributions | |
smoot | +0.086 |
fres | +0.082 |
ans | +0.079 |
Fedora | +0.078 |
Spur | +0.078 |
Neg logit contributions | |
)", | -0.073 |
ingo | -0.061 |
glers | -0.060 |
uyomi | -0.060 |
harm | -0.059 |
Token | seeds |
Token ID | 11904 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
smoot | +0.003 |
fres | +0.002 |
ans | +0.002 |
Pac | +0.002 |
chev | +0.002 |
Neg logit contributions | |
)", | -0.003 |
uyomi | -0.003 |
ingo | -0.003 |
glers | -0.003 |
emale | -0.003 |
Token | 8 |
Token ID | 807 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
smoot | +0.026 |
fres | +0.025 |
ans | +0.024 |
Pac | +0.024 |
Spur | +0.024 |
Neg logit contributions | |
)", | -0.030 |
uyomi | -0.026 |
ingo | -0.026 |
glers | -0.026 |
emale | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
)", | +0.011 |
uyomi | +0.010 |
ingo | +0.009 |
glers | +0.009 |
emale | +0.009 |
Neg logit contributions | |
smoot | -0.010 |
fres | -0.009 |
ans | -0.009 |
Pac | -0.009 |
Spur | -0.009 |
Token | 2015 |
Token ID | 1853 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
smoot | +0.016 |
fres | +0.015 |
ans | +0.015 |
Pac | +0.015 |
Spur | +0.014 |
Neg logit contributions | |
)", | -0.022 |
uyomi | -0.019 |
ingo | -0.019 |
glers | -0.019 |
emale | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
)", | +0.019 |
uyomi | +0.016 |
ingo | +0.016 |
glers | +0.016 |
emale | +0.016 |
Neg logit contributions | |
smoot | -0.016 |
fres | -0.015 |
ans | -0.015 |
Pac | -0.015 |
Spur | -0.015 |
Token | synd |
Token ID | 11150 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
)", | +0.036 |
uyomi | +0.031 |
ingo | +0.031 |
glers | +0.031 |
emale | +0.030 |
Neg logit contributions | |
smoot | -0.029 |
fres | -0.028 |
ans | -0.027 |
Pac | -0.027 |
Spur | -0.026 |
Token | icated |
Token ID | 3474 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
)", | +0.540 |
uyomi | +0.463 |
ingo | +0.461 |
glers | +0.457 |
emale | +0.450 |
Neg logit contributions | |
smoot | -0.527 |
fres | -0.498 |
ans | -0.487 |
Pac | -0.480 |
Spur | -0.476 |
Token | col |
Token ID | 951 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
)", | +1.151 |
ingo | +0.977 |
uyomi | +0.971 |
glers | +0.967 |
emale | +0.947 |
Neg logit contributions | |
smoot | -1.085 |
fres | -1.024 |
ans | -1.016 |
Pac | -1.006 |
chev | -0.986 |
Token | um |
Token ID | 388 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
smoot | +0.287 |
fres | +0.274 |
ans | +0.270 |
Pac | +0.265 |
Spur | +0.262 |
Neg logit contributions | |
)", | -0.235 |
uyomi | -0.198 |
ingo | -0.197 |
glers | -0.195 |
emale | -0.190 |
Token | ... |
Token ID | 986 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
)", | +0.173 |
ingo | +0.149 |
glers | +0.149 |
uyomi | +0.148 |
emale | +0.145 |
Neg logit contributions | |
smoot | -0.167 |
fres | -0.158 |
ans | -0.154 |
Pac | -0.152 |
Spur | -0.150 |
Token |
|
Token ID | 198 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
smoot | +0.090 |
fres | +0.084 |
ans | +0.082 |
Pac | +0.082 |
chev | +0.080 |
Neg logit contributions | |
)", | -0.104 |
uyomi | -0.090 |
ingo | -0.090 |
glers | -0.089 |
emale | -0.088 |
Token |
|
Token ID | 198 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
)", | +0.158 |
ingo | +0.138 |
uyomi | +0.137 |
glers | +0.137 |
harm | +0.134 |
Neg logit contributions | |
smoot | -0.119 |
fres | -0.111 |
ans | -0.108 |
Pac | -0.105 |
Spur | -0.104 |
Token | ( |
Token ID | 357 |
Feature activation | -9.12e-02 |
Pos logit contributions | |
)", | +0.023 |
uyomi | +0.020 |
ingo | +0.020 |
glers | +0.020 |
emale | +0.020 |
Neg logit contributions | |
smoot | -0.016 |
fres | -0.015 |
ans | -0.015 |
Pac | -0.014 |
Spur | -0.014 |
Token | 13 |
Token ID | 1485 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
smoot | +0.045 |
fres | +0.042 |
ans | +0.039 |
Pac | +0.038 |
Spur | +0.038 |
Neg logit contributions | |
)", | -0.092 |
ingo | -0.082 |
uyomi | -0.081 |
glers | -0.081 |
harm | -0.081 |
Token | , |
Token ID | 11 |
Feature activation | +9.82e-03 |
Pos logit contributions | |
)", | +0.299 |
ingo | +0.253 |
uyomi | +0.252 |
glers | +0.252 |
harm | +0.244 |
Neg logit contributions | |
smoot | -0.284 |
fres | -0.269 |
ans | -0.262 |
Pac | -0.256 |
Spur | -0.255 |
Token | 5 |
Token ID | 642 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
)", | +0.007 |
uyomi | +0.006 |
ingo | +0.006 |
glers | +0.006 |
emale | +0.006 |
Neg logit contributions | |
smoot | -0.008 |
fres | -0.008 |
ans | -0.007 |
Pac | -0.007 |
Spur | -0.007 |
Token | )) |
Token ID | 4008 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
)", | +0.130 |
uyomi | +0.116 |
ingo | +0.114 |
glers | +0.113 |
emale | +0.112 |
Neg logit contributions | |
smoot | -0.121 |
fres | -0.115 |
ans | -0.113 |
Pac | -0.111 |
Spur | -0.108 |
Token | sq |
Token ID | 19862 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
smoot | +0.102 |
fres | +0.097 |
ans | +0.095 |
Pac | +0.095 |
Spur | +0.093 |
Neg logit contributions | |
)", | -0.105 |
uyomi | -0.089 |
ingo | -0.089 |
glers | -0.086 |
emale | -0.086 |
Token | K |
Token ID | 42 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
)", | +0.963 |
ingo | +0.794 |
glers | +0.783 |
uyomi | +0.764 |
harm | +0.757 |
Neg logit contributions | |
smoot | -1.284 |
fres | -1.227 |
ans | -1.179 |
bolted | -1.165 |
cooling | -1.159 |
Token | ernel |
Token ID | 7948 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
)", | +0.067 |
uyomi | +0.056 |
ingo | +0.055 |
glers | +0.055 |
emale | +0.053 |
Neg logit contributions | |
smoot | -0.093 |
fres | -0.089 |
ans | -0.088 |
Pac | -0.086 |
Spur | -0.086 |
Token | = |
Token ID | 796 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
)", | +0.532 |
ingo | +0.465 |
uyomi | +0.463 |
glers | +0.462 |
harm | +0.450 |
Neg logit contributions | |
smoot | -0.359 |
fres | -0.337 |
ans | -0.326 |
Pac | -0.318 |
Spur | -0.315 |
Token | c |
Token ID | 269 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
)", | +0.266 |
uyomi | +0.228 |
ingo | +0.227 |
glers | +0.226 |
emale | +0.219 |
Neg logit contributions | |
smoot | -0.251 |
fres | -0.237 |
ans | -0.234 |
Pac | -0.230 |
Spur | -0.227 |
Token | v |
Token ID | 85 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
)", | +0.112 |
ingo | +0.099 |
glers | +0.098 |
uyomi | +0.097 |
harm | +0.096 |
Neg logit contributions | |
smoot | -0.072 |
fres | -0.067 |
ans | -0.064 |
Pac | -0.063 |
Spur | -0.063 |
Token | find |
Token ID | 1064 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
)", | +0.025 |
uyomi | +0.022 |
ingo | +0.022 |
glers | +0.022 |
emale | +0.021 |
Neg logit contributions | |
smoot | -0.024 |
fres | -0.022 |
ans | -0.022 |
Pac | -0.022 |
Spur | -0.021 |
Token | refuge |
Token ID | 5473 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
)", | +0.046 |
uyomi | +0.040 |
glers | +0.040 |
ingo | +0.040 |
harm | +0.039 |
Neg logit contributions | |
smoot | -0.035 |
fres | -0.033 |
ans | -0.032 |
Pac | -0.031 |
Spur | -0.031 |
Token | in |
Token ID | 287 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
smoot | +0.008 |
fres | +0.008 |
ans | +0.007 |
Pac | +0.007 |
Spur | +0.007 |
Neg logit contributions | |
)", | -0.009 |
uyomi | -0.008 |
ingo | -0.008 |
glers | -0.008 |
harm | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +4.83e-02 |
Pos logit contributions | |
)", | +0.190 |
uyomi | +0.166 |
glers | +0.165 |
ingo | +0.165 |
emale | +0.161 |
Neg logit contributions | |
smoot | -0.138 |
fres | -0.129 |
ans | -0.128 |
Pac | -0.125 |
Spur | -0.122 |
Token | Elven |
Token ID | 40748 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
)", | +0.037 |
uyomi | +0.031 |
ingo | +0.031 |
glers | +0.031 |
emale | +0.030 |
Neg logit contributions | |
smoot | -0.036 |
fres | -0.034 |
ans | -0.033 |
Pac | -0.033 |
chev | -0.032 |
Token | forest |
Token ID | 8222 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
)", | +0.167 |
uyomi | +0.142 |
ingo | +0.141 |
glers | +0.140 |
emale | +0.137 |
Neg logit contributions | |
smoot | -0.185 |
fres | -0.176 |
ans | -0.173 |
Pac | -0.170 |
Spur | -0.167 |
Token | of |
Token ID | 286 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
)", | +1.183 |
uyomi | +1.031 |
glers | +1.020 |
ingo | +1.020 |
harm | +0.993 |
Neg logit contributions | |
smoot | -1.006 |
fres | -0.946 |
ans | -0.928 |
Pac | -0.922 |
chev | -0.902 |
Token | L |
Token ID | 406 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
smoot | +0.014 |
fres | +0.013 |
ans | +0.013 |
Pac | +0.013 |
Spur | +0.013 |
Neg logit contributions | |
)", | -0.015 |
uyomi | -0.013 |
ingo | -0.013 |
glers | -0.013 |
emale | -0.013 |
Token | oth |
Token ID | 849 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
)", | +0.507 |
ingo | +0.434 |
glers | +0.430 |
uyomi | +0.427 |
harm | +0.421 |
Neg logit contributions | |
smoot | -0.513 |
fres | -0.483 |
ans | -0.470 |
Pac | -0.470 |
Spur | -0.462 |
Token | l |
Token ID | 75 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
)", | +0.153 |
uyomi | +0.129 |
ingo | +0.129 |
glers | +0.128 |
emale | +0.124 |
Neg logit contributions | |
smoot | -0.178 |
fres | -0.169 |
ans | -0.167 |
Pac | -0.164 |
Spur | -0.162 |
Token | รณ |
Token ID | 10205 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
)", | +0.213 |
uyomi | +0.180 |
ingo | +0.179 |
glers | +0.177 |
emale | +0.173 |
Neg logit contributions | |
smoot | -0.250 |
fres | -0.237 |
ans | -0.232 |
Pac | -0.231 |
Spur | -0.227 |
Token | ( |
Token ID | 357 |
Feature activation | -3.97e-02 |
Pos logit contributions | |
smoot | +0.042 |
fres | +0.039 |
ans | +0.038 |
Pac | +0.038 |
Spur | +0.037 |
Neg logit contributions | |
)", | -0.051 |
uyomi | -0.044 |
ingo | -0.044 |
glers | -0.043 |
harm | -0.043 |
Token | 13 |
Token ID | 1485 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
smoot | +0.025 |
fres | +0.024 |
ans | +0.023 |
Pac | +0.022 |
Fedora | +0.022 |
Neg logit contributions | |
)", | -0.035 |
ingo | -0.030 |
uyomi | -0.029 |
glers | -0.029 |
harm | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | -5.96e-02 |
Pos logit contributions | |
)", | +0.209 |
ingo | +0.175 |
uyomi | +0.175 |
glers | +0.174 |
emale | +0.169 |
Neg logit contributions | |
smoot | -0.192 |
fres | -0.182 |
ans | -0.177 |
Pac | -0.175 |
Spur | -0.173 |
Token | 5 |
Token ID | 642 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
smoot | +0.041 |
fres | +0.038 |
ans | +0.038 |
Pac | +0.037 |
Spur | +0.036 |
Neg logit contributions | |
)", | -0.049 |
ingo | -0.041 |
uyomi | -0.041 |
glers | -0.041 |
emale | -0.040 |
Token | )) |
Token ID | 4008 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
)", | +0.102 |
ingo | +0.083 |
uyomi | +0.083 |
glers | +0.083 |
emale | +0.081 |
Neg logit contributions | |
smoot | -0.121 |
fres | -0.115 |
ans | -0.113 |
Pac | -0.111 |
Spur | -0.110 |
Token | sq |
Token ID | 19862 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
smoot | +0.141 |
fres | +0.132 |
ans | +0.130 |
Pac | +0.128 |
Spur | +0.125 |
Neg logit contributions | |
)", | -0.234 |
ingo | -0.206 |
uyomi | -0.206 |
glers | -0.204 |
harm | -0.200 |
Token | K |
Token ID | 42 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
)", | +1.070 |
ingo | +0.922 |
glers | +0.915 |
uyomi | +0.914 |
emale | +0.899 |
Neg logit contributions | |
smoot | -1.008 |
fres | -0.953 |
ans | -0.916 |
Spur | -0.906 |
scoop | -0.906 |
Token | ernel |
Token ID | 7948 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
)", | +0.081 |
uyomi | +0.068 |
ingo | +0.067 |
glers | +0.066 |
emale | +0.064 |
Neg logit contributions | |
smoot | -0.112 |
fres | -0.107 |
ans | -0.105 |
Pac | -0.104 |
Spur | -0.103 |
Token | = |
Token ID | 796 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
)", | +0.429 |
uyomi | +0.377 |
ingo | +0.376 |
glers | +0.373 |
emale | +0.365 |
Neg logit contributions | |
smoot | -0.319 |
fres | -0.300 |
ans | -0.291 |
Pac | -0.284 |
Spur | -0.284 |
Token | c |
Token ID | 269 |
Feature activation | +9.94e-02 |
Pos logit contributions | |
)", | +0.273 |
uyomi | +0.233 |
ingo | +0.233 |
glers | +0.229 |
emale | +0.225 |
Neg logit contributions | |
smoot | -0.244 |
fres | -0.230 |
ans | -0.228 |
Pac | -0.225 |
chev | -0.219 |
Token | v |
Token ID | 85 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
)", | +0.091 |
ingo | +0.080 |
glers | +0.079 |
uyomi | +0.078 |
harm | +0.078 |
Neg logit contributions | |
smoot | -0.059 |
fres | -0.055 |
ans | -0.052 |
Spur | -0.052 |
Pac | -0.052 |
Token | with |
Token ID | 351 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
)", | +0.056 |
uyomi | +0.048 |
ingo | +0.048 |
glers | +0.047 |
harm | +0.046 |
Neg logit contributions | |
smoot | -0.051 |
fres | -0.048 |
ans | -0.048 |
Pac | -0.047 |
Spur | -0.046 |
Token | their |
Token ID | 511 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
)", | +0.117 |
ingo | +0.103 |
uyomi | +0.103 |
glers | +0.101 |
harm | +0.099 |
Neg logit contributions | |
smoot | -0.090 |
fres | -0.084 |
ans | -0.084 |
Pac | -0.082 |
chev | -0.080 |
Token | own |
Token ID | 898 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
smoot | +0.130 |
fres | +0.122 |
ans | +0.121 |
Pac | +0.119 |
chev | +0.117 |
Neg logit contributions | |
)", | -0.158 |
ingo | -0.137 |
uyomi | -0.137 |
glers | -0.135 |
emale | -0.133 |
Token | ideological |
Token ID | 15735 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
)", | +0.088 |
uyomi | +0.076 |
ingo | +0.076 |
glers | +0.075 |
harm | +0.073 |
Neg logit contributions | |
smoot | -0.076 |
fres | -0.071 |
ans | -0.071 |
Pac | -0.070 |
Spur | -0.068 |
Token | pre |
Token ID | 662 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
)", | +0.114 |
uyomi | +0.099 |
ingo | +0.098 |
glers | +0.098 |
harm | +0.095 |
Neg logit contributions | |
smoot | -0.096 |
fres | -0.091 |
ans | -0.090 |
Pac | -0.088 |
Spur | -0.086 |
Token | occup |
Token ID | 19596 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
)", | +0.348 |
ingo | +0.274 |
uyomi | +0.273 |
glers | +0.270 |
harm | +0.261 |
Neg logit contributions | |
smoot | -0.686 |
fres | -0.656 |
ans | -0.643 |
Pac | -0.636 |
Spur | -0.634 |
Token | ations |
Token ID | 602 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
)", | +0.908 |
ingo | +0.764 |
uyomi | +0.752 |
glers | +0.749 |
harm | +0.734 |
Neg logit contributions | |
smoot | -1.160 |
fres | -1.100 |
ans | -1.073 |
Pac | -1.062 |
Spur | -1.055 |
Token | , |
Token ID | 11 |
Feature activation | +8.11e-02 |
Pos logit contributions | |
)", | +0.282 |
uyomi | +0.245 |
ingo | +0.244 |
glers | +0.241 |
harm | +0.235 |
Neg logit contributions | |
smoot | -0.250 |
fres | -0.237 |
ans | -0.233 |
Pac | -0.229 |
Spur | -0.226 |
Token | so |
Token ID | 523 |
Feature activation | +7.34e-02 |
Pos logit contributions | |
)", | +0.065 |
ingo | +0.056 |
uyomi | +0.056 |
glers | +0.056 |
harm | +0.054 |
Neg logit contributions | |
smoot | -0.056 |
fres | -0.052 |
ans | -0.052 |
Pac | -0.051 |
Spur | -0.050 |
Token | that |
Token ID | 326 |
Feature activation | +1.23e-03 |
Pos logit contributions | |
)", | +0.061 |
ingo | +0.053 |
uyomi | +0.053 |
glers | +0.053 |
harm | +0.051 |
Neg logit contributions | |
smoot | -0.048 |
fres | -0.045 |
ans | -0.045 |
Pac | -0.044 |
Spur | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | +9.79e-02 |
Pos logit contributions | |
)", | +0.001 |
ingo | +0.001 |
uyomi | +0.001 |
glers | +0.001 |
emale | +0.001 |
Neg logit contributions | |
smoot | -0.001 |
fres | -0.001 |
ans | -0.001 |
Pac | -0.001 |
chev | -0.001 |
Token | Lo |
Token ID | 6706 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
)", | +0.065 |
uyomi | +0.056 |
ingo | +0.055 |
glers | +0.055 |
emale | +0.054 |
Neg logit contributions | |
smoot | -0.067 |
fres | -0.063 |
ans | -0.062 |
Pac | -0.061 |
Spur | -0.060 |
Token | a |
Token ID | 64 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
smoot | +0.198 |
fres | +0.183 |
ans | +0.178 |
Pac | +0.174 |
Spur | +0.173 |
Neg logit contributions | |
)", | -0.327 |
ingo | -0.288 |
uyomi | -0.287 |
glers | -0.285 |
harm | -0.280 |
Token | observ |
Token ID | 3799 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
)", | +0.167 |
ingo | +0.145 |
uyomi | +0.144 |
glers | +0.143 |
emale | +0.140 |
Neg logit contributions | |
smoot | -0.136 |
fres | -0.128 |
ans | -0.126 |
Pac | -0.125 |
chev | -0.122 |
Token | atory |
Token ID | 2870 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
)", | +0.517 |
ingo | +0.427 |
glers | +0.427 |
uyomi | +0.426 |
emale | +0.417 |
Neg logit contributions | |
smoot | -0.651 |
fres | -0.619 |
ans | -0.605 |
Pac | -0.601 |
Spur | -0.592 |
Token | ( |
Token ID | 357 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
)", | +0.435 |
ingo | +0.375 |
uyomi | +0.375 |
glers | +0.372 |
emale | +0.364 |
Neg logit contributions | |
smoot | -0.358 |
fres | -0.337 |
ans | -0.333 |
Pac | -0.328 |
Spur | -0.321 |
Token | alt |
Token ID | 2501 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
)", | +0.111 |
ingo | +0.095 |
uyomi | +0.095 |
glers | +0.095 |
harm | +0.093 |
Neg logit contributions | |
smoot | -0.090 |
fres | -0.085 |
ans | -0.082 |
Pac | -0.081 |
Spur | -0.080 |
Token | itude |
Token ID | 3984 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
)", | +0.941 |
ingo | +0.784 |
uyomi | +0.783 |
glers | +0.781 |
harm | +0.755 |
Neg logit contributions | |
smoot | -1.023 |
fres | -0.967 |
ans | -0.956 |
Pac | -0.941 |
Spur | -0.936 |
Token | 34 |
Token ID | 4974 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
)", | +0.295 |
ingo | +0.251 |
uyomi | +0.249 |
glers | +0.248 |
emale | +0.241 |
Neg logit contributions | |
smoot | -0.244 |
fres | -0.231 |
ans | -0.227 |
Pac | -0.224 |
Spur | -0.221 |
Token | 00 |
Token ID | 405 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
smoot | +0.046 |
fres | +0.043 |
ans | +0.042 |
Pac | +0.041 |
Spur | +0.041 |
Neg logit contributions | |
)", | -0.064 |
uyomi | -0.055 |
ingo | -0.055 |
glers | -0.055 |
emale | -0.054 |
Token | m |
Token ID | 285 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
)", | +0.082 |
uyomi | +0.070 |
ingo | +0.070 |
glers | +0.070 |
emale | +0.068 |
Neg logit contributions | |
smoot | -0.079 |
fres | -0.074 |
ans | -0.073 |
Pac | -0.072 |
Spur | -0.071 |
Token | ; |
Token ID | 26 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
smoot | +0.306 |
fres | +0.290 |
ans | +0.286 |
Pac | +0.280 |
Spur | +0.277 |
Neg logit contributions | |
)", | -0.299 |
uyomi | -0.256 |
ingo | -0.254 |
glers | -0.253 |
emale | -0.246 |
Token | am |
Token ID | 321 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
)", | +0.004 |
ingo | +0.004 |
glers | +0.004 |
harm | +0.004 |
uyomi | +0.004 |
Neg logit contributions | |
smoot | -0.004 |
fres | -0.004 |
Spur | -0.004 |
Pac | -0.004 |
Fedora | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +2.38e-03 |
Pos logit contributions | |
)", | +0.446 |
ingo | +0.392 |
uyomi | +0.390 |
glers | +0.388 |
harm | +0.380 |
Neg logit contributions | |
smoot | -0.321 |
fres | -0.301 |
ans | -0.293 |
Pac | -0.291 |
Spur | -0.290 |
Token | a |
Token ID | 257 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
)", | +0.002 |
ingo | +0.002 |
uyomi | +0.002 |
glers | +0.002 |
harm | +0.002 |
Neg logit contributions | |
smoot | -0.002 |
fres | -0.001 |
ans | -0.001 |
Pac | -0.001 |
chev | -0.001 |
Token | benz |
Token ID | 39601 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
)", | +0.040 |
uyomi | +0.034 |
ingo | +0.034 |
glers | +0.034 |
emale | +0.033 |
Neg logit contributions | |
smoot | -0.035 |
fres | -0.033 |
ans | -0.033 |
Pac | -0.032 |
chev | -0.032 |
Token | od |
Token ID | 375 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
)", | +0.467 |
uyomi | +0.408 |
ingo | +0.406 |
glers | +0.399 |
harm | +0.394 |
Neg logit contributions | |
smoot | -0.400 |
fres | -0.377 |
ans | -0.366 |
Spur | -0.361 |
Pac | -0.361 |
Token | iazep |
Token ID | 48826 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
)", | +0.179 |
uyomi | +0.153 |
ingo | +0.153 |
glers | +0.149 |
harm | +0.147 |
Neg logit contributions | |
smoot | -0.197 |
fres | -0.187 |
ans | -0.182 |
Pac | -0.180 |
Spur | -0.180 |
Token | ine |
Token ID | 500 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
)", | +0.955 |
ingo | +0.822 |
uyomi | +0.817 |
harm | +0.799 |
emale | +0.790 |
Neg logit contributions | |
smoot | -0.979 |
fres | -0.926 |
Pac | -0.909 |
ans | -0.896 |
Spur | -0.890 |
Token | anx |
Token ID | 7296 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
smoot | +0.274 |
fres | +0.257 |
ans | +0.254 |
Pac | +0.252 |
Spur | +0.247 |
Neg logit contributions | |
)", | -0.331 |
uyomi | -0.286 |
ingo | -0.285 |
glers | -0.282 |
harm | -0.277 |
Token | io |
Token ID | 952 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
)", | +0.159 |
ingo | +0.133 |
uyomi | +0.130 |
glers | +0.129 |
harm | +0.128 |
Neg logit contributions | |
smoot | -0.221 |
fres | -0.211 |
Spur | -0.206 |
ans | -0.206 |
Pac | -0.204 |
Token | ly |
Token ID | 306 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
)", | +0.242 |
glers | +0.206 |
ingo | +0.205 |
harm | +0.201 |
uyomi | +0.198 |
Neg logit contributions | |
smoot | -0.224 |
fres | -0.212 |
Pac | -0.205 |
ans | -0.204 |
Spur | -0.204 |
Token | tic |
Token ID | 13370 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
smoot | +0.213 |
fres | +0.201 |
ans | +0.194 |
Pac | +0.191 |
Fedora | +0.190 |
Neg logit contributions | |
)", | -0.240 |
glers | -0.206 |
ingo | -0.206 |
uyomi | -0.203 |
harm | -0.201 |
Token | senior |
Token ID | 4664 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
)", | +0.149 |
uyomi | +0.130 |
glers | +0.130 |
ingo | +0.129 |
emale | +0.126 |
Neg logit contributions | |
smoot | -0.109 |
fres | -0.101 |
ans | -0.100 |
Pac | -0.100 |
chev | -0.098 |
Token | civil |
Token ID | 3026 |
Feature activation | +7.69e-02 |
Pos logit contributions | |
smoot | +0.011 |
fres | +0.010 |
ans | +0.010 |
Pac | +0.010 |
chev | +0.010 |
Neg logit contributions | |
)", | -0.013 |
uyomi | -0.011 |
glers | -0.011 |
ingo | -0.011 |
emale | -0.011 |
Token | servants |
Token ID | 17523 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
)", | +0.049 |
uyomi | +0.041 |
ingo | +0.040 |
glers | +0.040 |
emale | +0.039 |
Neg logit contributions | |
smoot | -0.067 |
fres | -0.063 |
ans | -0.063 |
Pac | -0.062 |
Spur | -0.061 |
Token | , |
Token ID | 11 |
Feature activation | +8.12e-02 |
Pos logit contributions | |
)", | +0.415 |
uyomi | +0.353 |
ingo | +0.353 |
glers | +0.351 |
emale | +0.341 |
Neg logit contributions | |
smoot | -0.391 |
fres | -0.369 |
ans | -0.362 |
Pac | -0.360 |
Spur | -0.353 |
Token | being |
Token ID | 852 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
)", | +0.064 |
uyomi | +0.055 |
ingo | +0.054 |
glers | +0.054 |
emale | +0.053 |
Neg logit contributions | |
smoot | -0.058 |
fres | -0.055 |
ans | -0.054 |
Pac | -0.053 |
Spur | -0.052 |
Token | fully |
Token ID | 3938 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
)", | +0.035 |
uyomi | +0.030 |
ingo | +0.030 |
glers | +0.030 |
emale | +0.029 |
Neg logit contributions | |
smoot | -0.029 |
fres | -0.027 |
ans | -0.026 |
Pac | -0.026 |
chev | -0.025 |
Token | bilingual |
Token ID | 48116 |
Feature activation | -8.51e-02 |
Pos logit contributions | |
)", | +1.045 |
ingo | +0.890 |
glers | +0.889 |
uyomi | +0.888 |
emale | +0.865 |
Neg logit contributions | |
smoot | -0.884 |
fres | -0.830 |
ans | -0.813 |
Pac | -0.807 |
chev | -0.789 |
Token | ." |
Token ID | 526 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
smoot | +0.060 |
fres | +0.057 |
ans | +0.056 |
Pac | +0.055 |
Spur | +0.054 |
Neg logit contributions | |
)", | -0.068 |
uyomi | -0.058 |
ingo | -0.058 |
glers | -0.058 |
emale | -0.056 |
Token |
|
Token ID | 198 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
)", | +0.131 |
uyomi | +0.116 |
ingo | +0.115 |
glers | +0.114 |
emale | +0.112 |
Neg logit contributions | |
smoot | -0.090 |
fres | -0.084 |
ans | -0.083 |
Pac | -0.080 |
Spur | -0.079 |
Token |
|
Token ID | 198 |
Feature activation | +8.94e-02 |
Pos logit contributions | |
)", | +0.136 |
ingo | +0.118 |
glers | +0.117 |
uyomi | +0.117 |
harm | +0.114 |
Neg logit contributions | |
smoot | -0.101 |
fres | -0.095 |
ans | -0.092 |
Pac | -0.090 |
Spur | -0.089 |
Token | In |
Token ID | 818 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
)", | +0.063 |
ingo | +0.053 |
glers | +0.053 |
uyomi | +0.052 |
harm | +0.051 |
Neg logit contributions | |
smoot | -0.072 |
fres | -0.068 |
ans | -0.066 |
Spur | -0.065 |
Fedora | -0.065 |
Token | able |
Token ID | 540 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
)", | +0.105 |
uyomi | +0.092 |
ingo | +0.091 |
glers | +0.091 |
emale | +0.089 |
Neg logit contributions | |
smoot | -0.081 |
fres | -0.076 |
ans | -0.074 |
Pac | -0.073 |
Spur | -0.072 |
Token | version |
Token ID | 2196 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
)", | +0.437 |
uyomi | +0.389 |
ingo | +0.386 |
glers | +0.385 |
emale | +0.377 |
Neg logit contributions | |
smoot | -0.245 |
fres | -0.228 |
ans | -0.222 |
Pac | -0.216 |
Spur | -0.212 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.87e-02 |
Pos logit contributions | |
)", | +0.544 |
ingo | +0.477 |
uyomi | +0.477 |
glers | +0.466 |
emale | +0.455 |
Neg logit contributions | |
smoot | -0.428 |
fres | -0.400 |
ans | -0.389 |
Pac | -0.383 |
bolted | -0.374 |
Token | Rob |
Token ID | 14350 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
smoot | +0.038 |
fres | +0.036 |
ans | +0.035 |
Spur | +0.035 |
Fedora | +0.034 |
Neg logit contributions | |
)", | -0.035 |
ingo | -0.030 |
glers | -0.030 |
uyomi | -0.030 |
harm | -0.029 |
Token | C |
Token ID | 327 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
smoot | +0.225 |
fres | +0.211 |
ans | +0.206 |
Pac | +0.204 |
chev | +0.199 |
Neg logit contributions | |
)", | -0.269 |
uyomi | -0.234 |
ingo | -0.233 |
glers | -0.231 |
emale | -0.226 |
Token | estern |
Token ID | 3330 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
smoot | +0.486 |
fres | +0.461 |
ans | +0.449 |
Pac | +0.445 |
Spur | +0.439 |
Neg logit contributions | |
)", | -0.437 |
ingo | -0.372 |
uyomi | -0.369 |
glers | -0.366 |
emale | -0.355 |
Token | ino |
Token ID | 2879 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
)", | +1.093 |
uyomi | +0.971 |
glers | +0.946 |
ingo | +0.939 |
emale | +0.926 |
Neg logit contributions | |
smoot | -0.838 |
fres | -0.784 |
ans | -0.783 |
Pac | -0.761 |
Spur | -0.743 |
Token | hosts |
Token ID | 11453 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
smoot | +0.263 |
fres | +0.247 |
ans | +0.242 |
Pac | +0.239 |
chev | +0.234 |
Neg logit contributions | |
)", | -0.360 |
ingo | -0.314 |
uyomi | -0.312 |
glers | -0.312 |
emale | -0.304 |
Token | a |
Token ID | 257 |
Feature activation | -5.11e-02 |
Pos logit contributions | |
smoot | +0.011 |
fres | +0.010 |
ans | +0.010 |
Pac | +0.010 |
chev | +0.010 |
Neg logit contributions | |
)", | -0.015 |
ingo | -0.013 |
uyomi | -0.013 |
glers | -0.013 |
emale | -0.013 |
Token | jam |
Token ID | 16853 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
smoot | +0.033 |
fres | +0.031 |
ans | +0.030 |
Pac | +0.030 |
chev | +0.029 |
Neg logit contributions | |
)", | -0.044 |
ingo | -0.038 |
uyomi | -0.038 |
glers | -0.038 |
emale | -0.037 |
Token | packed |
Token ID | 11856 |
Feature activation | -7.46e-02 |
Pos logit contributions | |
smoot | +0.040 |
fres | +0.038 |
ans | +0.037 |
Pac | +0.036 |
Spur | +0.036 |
Neg logit contributions | |
)", | -0.044 |
uyomi | -0.038 |
ingo | -0.037 |
glers | -0.037 |
emale | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
smoot | +0.019 |
fres | +0.018 |
ans | +0.018 |
Pac | +0.017 |
Spur | +0.017 |
Neg logit contributions | |
)", | -0.026 |
ingo | -0.022 |
glers | -0.022 |
uyomi | -0.022 |
harm | -0.022 |
Token | A |
Token ID | 32 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
smoot | +0.010 |
fres | +0.010 |
ans | +0.009 |
Spur | +0.009 |
Pac | +0.009 |
Neg logit contributions | |
)", | -0.009 |
ingo | -0.007 |
glers | -0.007 |
uyomi | -0.007 |
harm | -0.007 |
Token | lot |
Token ID | 1256 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
smoot | +0.024 |
fres | +0.023 |
ans | +0.022 |
Pac | +0.022 |
Spur | +0.021 |
Neg logit contributions | |
)", | -0.032 |
ingo | -0.028 |
uyomi | -0.028 |
glers | -0.028 |
emale | -0.027 |
Token | of |
Token ID | 286 |
Feature activation | +6.07e-02 |
Pos logit contributions | |
smoot | +0.102 |
fres | +0.095 |
ans | +0.093 |
Pac | +0.092 |
Spur | +0.091 |
Neg logit contributions | |
)", | -0.130 |
ingo | -0.113 |
uyomi | -0.113 |
glers | -0.113 |
emale | -0.110 |
Token | public |
Token ID | 1171 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
)", | +0.050 |
ingo | +0.043 |
glers | +0.043 |
uyomi | +0.043 |
harm | +0.042 |
Neg logit contributions | |
smoot | -0.041 |
fres | -0.039 |
ans | -0.038 |
Pac | -0.037 |
Spur | -0.037 |
Token | domain |
Token ID | 7386 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
smoot | +0.024 |
fres | +0.023 |
ans | +0.022 |
Pac | +0.022 |
Spur | +0.022 |
Neg logit contributions | |
)", | -0.024 |
uyomi | -0.021 |
ingo | -0.021 |
glers | -0.021 |
harm | -0.020 |
Token | works |
Token ID | 2499 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
)", | +0.950 |
ingo | +0.808 |
glers | +0.807 |
uyomi | +0.807 |
harm | +0.779 |
Neg logit contributions | |
smoot | -0.944 |
fres | -0.891 |
ans | -0.873 |
Pac | -0.872 |
chev | -0.852 |
Token | are |
Token ID | 389 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
)", | +0.284 |
uyomi | +0.244 |
ingo | +0.244 |
glers | +0.243 |
emale | +0.237 |
Neg logit contributions | |
smoot | -0.255 |
fres | -0.240 |
ans | -0.236 |
Pac | -0.233 |
Spur | -0.229 |
Token | also |
Token ID | 635 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
)", | +0.142 |
uyomi | +0.123 |
ingo | +0.123 |
glers | +0.123 |
harm | +0.120 |
Neg logit contributions | |
smoot | -0.102 |
fres | -0.095 |
ans | -0.094 |
Pac | -0.092 |
Spur | -0.090 |
Token | available |
Token ID | 1695 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
)", | +0.123 |
ingo | +0.107 |
uyomi | +0.107 |
glers | +0.106 |
harm | +0.104 |
Neg logit contributions | |
smoot | -0.090 |
fres | -0.084 |
ans | -0.083 |
Pac | -0.081 |
Spur | -0.080 |
Token | on |
Token ID | 319 |
Feature activation | -8.06e-02 |
Pos logit contributions | |
)", | +0.017 |
uyomi | +0.015 |
ingo | +0.015 |
glers | +0.015 |
emale | +0.014 |
Neg logit contributions | |
smoot | -0.015 |
fres | -0.014 |
ans | -0.014 |
Pac | -0.014 |
Spur | -0.014 |
Token | us |
Token ID | 385 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
)", | +0.185 |
ingo | +0.160 |
glers | +0.158 |
uyomi | +0.157 |
harm | +0.156 |
Neg logit contributions | |
smoot | -0.162 |
fres | -0.151 |
Pac | -0.145 |
Spur | -0.144 |
ans | -0.144 |
Token | / |
Token ID | 14 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
smoot | +0.228 |
fres | +0.215 |
ans | +0.210 |
Pac | +0.207 |
Spur | +0.204 |
Neg logit contributions | |
)", | -0.270 |
uyomi | -0.232 |
ingo | -0.231 |
glers | -0.231 |
emale | -0.225 |
Token | wiki |
Token ID | 15466 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
)", | +0.226 |
ingo | +0.197 |
uyomi | +0.196 |
glers | +0.195 |
harm | +0.193 |
Neg logit contributions | |
smoot | -0.155 |
fres | -0.144 |
ans | -0.138 |
Pac | -0.137 |
Spur | -0.135 |
Token | / |
Token ID | 14 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
smoot | +0.451 |
fres | +0.425 |
ans | +0.412 |
Pac | +0.404 |
Spur | +0.402 |
Neg logit contributions | |
)", | -0.533 |
ingo | -0.456 |
uyomi | -0.455 |
glers | -0.455 |
harm | -0.443 |
Token | trans |
Token ID | 7645 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
)", | +0.127 |
ingo | +0.110 |
glers | +0.109 |
uyomi | +0.109 |
harm | +0.109 |
Neg logit contributions | |
smoot | -0.099 |
fres | -0.094 |
ans | -0.089 |
Spur | -0.088 |
scoop | -0.088 |
Token | cript |
Token ID | 6519 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
)", | +0.106 |
ingo | +0.085 |
glers | +0.084 |
uyomi | +0.084 |
harm | +0.081 |
Neg logit contributions | |
smoot | -0.164 |
fres | -0.156 |
ans | -0.153 |
Pac | -0.152 |
Spur | -0.151 |
Token | s |
Token ID | 82 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
)", | +1.137 |
ingo | +0.988 |
glers | +0.975 |
uyomi | +0.967 |
harm | +0.960 |
Neg logit contributions | |
smoot | -0.773 |
fres | -0.717 |
ans | -0.681 |
Spur | -0.680 |
Pac | -0.677 |
Token | / |
Token ID | 14 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
)", | +0.192 |
uyomi | +0.166 |
ingo | +0.164 |
glers | +0.164 |
emale | +0.159 |
Neg logit contributions | |
smoot | -0.164 |
fres | -0.155 |
ans | -0.151 |
Pac | -0.149 |
Spur | -0.146 |
Token | sc |
Token ID | 1416 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
)", | +0.026 |
ingo | +0.023 |
glers | +0.023 |
uyomi | +0.023 |
harm | +0.022 |
Neg logit contributions | |
smoot | -0.016 |
fres | -0.015 |
ans | -0.014 |
Pac | -0.014 |
Spur | -0.014 |
Token | aling |
Token ID | 4272 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
)", | +0.485 |
ingo | +0.434 |
uyomi | +0.430 |
glers | +0.428 |
harm | +0.422 |
Neg logit contributions | |
smoot | -0.232 |
fres | -0.212 |
Spur | -0.202 |
Pac | -0.201 |
ans | -0.198 |
Token | bitcoin |
Token ID | 35395 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
smoot | +0.089 |
fres | +0.080 |
Spur | +0.072 |
Pac | +0.070 |
ans | +0.070 |
Neg logit contributions | |
)", | -0.280 |
ingo | -0.254 |
glers | -0.251 |
harm | -0.250 |
uyomi | -0.249 |
Token | by |
Token ID | 416 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
)", | +0.166 |
uyomi | +0.144 |
ingo | +0.143 |
glers | +0.142 |
harm | +0.139 |
Neg logit contributions | |
smoot | -0.141 |
fres | -0.133 |
ans | -0.130 |
Pac | -0.128 |
Spur | -0.126 |
Token | the |
Token ID | 262 |
Feature activation | -5.29e-03 |
Pos logit contributions | |
)", | +0.104 |
uyomi | +0.091 |
ingo | +0.090 |
glers | +0.090 |
emale | +0.088 |
Neg logit contributions | |
smoot | -0.079 |
fres | -0.074 |
ans | -0.072 |
Pac | -0.072 |
chev | -0.070 |
Token | territory |
Token ID | 7674 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
smoot | +0.004 |
fres | +0.004 |
ans | +0.004 |
Pac | +0.004 |
chev | +0.004 |
Neg logit contributions | |
)", | -0.004 |
uyomi | -0.003 |
ingo | -0.003 |
glers | -0.003 |
emale | -0.003 |
Token | par |
Token ID | 1582 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
)", | +0.250 |
uyomi | +0.216 |
ingo | +0.214 |
glers | +0.212 |
emale | +0.207 |
Neg logit contributions | |
smoot | -0.239 |
fres | -0.226 |
ans | -0.221 |
Pac | -0.218 |
Spur | -0.215 |
Token | liam |
Token ID | 5058 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
)", | +0.088 |
uyomi | +0.072 |
ingo | +0.072 |
glers | +0.071 |
emale | +0.069 |
Neg logit contributions | |
smoot | -0.128 |
fres | -0.122 |
ans | -0.120 |
Pac | -0.119 |
Spur | -0.117 |
Token | ents |
Token ID | 658 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
)", | +0.347 |
uyomi | +0.286 |
ingo | +0.285 |
glers | +0.283 |
emale | +0.272 |
Neg logit contributions | |
smoot | -0.480 |
fres | -0.458 |
ans | -0.448 |
Pac | -0.444 |
Spur | -0.440 |
Token | .[ |
Token ID | 3693 |
Feature activation | +7.28e-02 |
Pos logit contributions | |
)", | +0.971 |
uyomi | +0.844 |
ingo | +0.838 |
glers | +0.828 |
harm | +0.813 |
Neg logit contributions | |
smoot | -0.871 |
fres | -0.826 |
Pac | -0.808 |
ans | -0.808 |
Spur | -0.789 |
Token | 196 |
Token ID | 25272 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
)", | +0.076 |
ingo | +0.068 |
uyomi | +0.068 |
glers | +0.068 |
emale | +0.067 |
Neg logit contributions | |
smoot | -0.034 |
fres | -0.031 |
ans | -0.029 |
Spur | -0.029 |
Pac | -0.028 |
Token | ] |
Token ID | 60 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
)", | +0.103 |
uyomi | +0.090 |
ingo | +0.088 |
glers | +0.088 |
emale | +0.086 |
Neg logit contributions | |
smoot | -0.100 |
fres | -0.095 |
ans | -0.093 |
Pac | -0.091 |
Spur | -0.090 |
Token |
|
Token ID | 198 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
)", | +0.025 |
ingo | +0.021 |
uyomi | +0.021 |
glers | +0.021 |
emale | +0.021 |
Neg logit contributions | |
smoot | -0.021 |
fres | -0.020 |
ans | -0.019 |
Pac | -0.019 |
chev | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
)", | +0.334 |
ingo | +0.287 |
glers | +0.287 |
uyomi | +0.283 |
harm | +0.280 |
Neg logit contributions | |
smoot | -0.259 |
fres | -0.242 |
ans | -0.235 |
Pac | -0.230 |
bolted | -0.229 |
Token | IT |
Token ID | 2043 |
Feature activation | +8.49e-02 |
Pos logit contributions | |
smoot | +0.041 |
fres | +0.038 |
ans | +0.038 |
Spur | +0.036 |
Pac | +0.036 |
Neg logit contributions | |
)", | -0.050 |
ingo | -0.043 |
uyomi | -0.043 |
glers | -0.042 |
harm | -0.042 |
Token | , |
Token ID | 11 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
)", | +0.070 |
ingo | +0.061 |
uyomi | +0.061 |
glers | +0.060 |
emale | +0.059 |
Neg logit contributions | |
smoot | -0.057 |
fres | -0.053 |
ans | -0.052 |
Pac | -0.052 |
Spur | -0.051 |
Token | has |
Token ID | 468 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
)", | +0.130 |
ingo | +0.114 |
glers | +0.114 |
uyomi | +0.114 |
emale | +0.111 |
Neg logit contributions | |
smoot | -0.088 |
fres | -0.082 |
ans | -0.081 |
Pac | -0.079 |
Spur | -0.077 |
Token | an |
Token ID | 281 |
Feature activation | +9.11e-02 |
Pos logit contributions | |
)", | +0.203 |
ingo | +0.178 |
uyomi | +0.178 |
glers | +0.177 |
emale | +0.172 |
Neg logit contributions | |
smoot | -0.133 |
fres | -0.124 |
ans | -0.121 |
Pac | -0.120 |
Spur | -0.118 |
Token | operating |
Token ID | 5361 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
)", | +0.075 |
uyomi | +0.066 |
ingo | +0.065 |
glers | +0.065 |
emale | +0.063 |
Neg logit contributions | |
smoot | -0.062 |
fres | -0.058 |
ans | -0.057 |
Pac | -0.056 |
Spur | -0.055 |
Token | margin |
Token ID | 10330 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
)", | +0.456 |
uyomi | +0.393 |
ingo | +0.390 |
glers | +0.388 |
emale | +0.379 |
Neg logit contributions | |
smoot | -0.425 |
fres | -0.402 |
ans | -0.396 |
Pac | -0.388 |
Spur | -0.382 |
Token | of |
Token ID | 286 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
)", | +0.992 |
ingo | +0.858 |
uyomi | +0.854 |
glers | +0.848 |
emale | +0.827 |
Neg logit contributions | |
smoot | -0.848 |
fres | -0.805 |
ans | -0.791 |
Pac | -0.788 |
Spur | -0.769 |
Token | 30 |
Token ID | 1542 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
smoot | +0.078 |
fres | +0.074 |
ans | +0.073 |
Pac | +0.071 |
Spur | +0.070 |
Neg logit contributions | |
)", | -0.099 |
ingo | -0.086 |
uyomi | -0.086 |
glers | -0.085 |
emale | -0.083 |
Token | %, |
Token ID | 7441 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
)", | +0.139 |
uyomi | +0.123 |
ingo | +0.122 |
glers | +0.122 |
emale | +0.119 |
Neg logit contributions | |
smoot | -0.084 |
fres | -0.079 |
ans | -0.076 |
Pac | -0.075 |
Spur | -0.073 |
Token | one |
Token ID | 530 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
)", | +0.224 |
ingo | +0.195 |
uyomi | +0.194 |
glers | +0.193 |
emale | +0.188 |
Neg logit contributions | |
smoot | -0.191 |
fres | -0.181 |
ans | -0.177 |
Pac | -0.176 |
Spur | -0.171 |
Token | of |
Token ID | 286 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
)", | +0.105 |
uyomi | +0.092 |
ingo | +0.091 |
glers | +0.090 |
emale | +0.088 |
Neg logit contributions | |
smoot | -0.084 |
fres | -0.079 |
ans | -0.078 |
Pac | -0.077 |
Spur | -0.075 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
)", | +0.153 |
ingo | +0.132 |
glers | +0.132 |
uyomi | +0.131 |
emale | +0.127 |
Neg logit contributions | |
smoot | -0.123 |
fres | -0.116 |
ans | -0.112 |
Pac | -0.110 |
bolted | -0.108 |
Token |
|
Token ID | 198 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
)", | +0.089 |
ingo | +0.077 |
uyomi | +0.077 |
glers | +0.077 |
harm | +0.075 |
Neg logit contributions | |
smoot | -0.066 |
fres | -0.061 |
ans | -0.060 |
Pac | -0.058 |
Spur | -0.058 |
Token | In |
Token ID | 818 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
)", | +0.077 |
ingo | +0.065 |
glers | +0.064 |
uyomi | +0.064 |
harm | +0.062 |
Neg logit contributions | |
smoot | -0.089 |
fres | -0.084 |
ans | -0.082 |
Spur | -0.080 |
Fedora | -0.080 |
Token | a |
Token ID | 257 |
Feature activation | +6.43e-02 |
Pos logit contributions | |
smoot | +0.038 |
fres | +0.035 |
ans | +0.035 |
Pac | +0.034 |
Spur | +0.033 |
Neg logit contributions | |
)", | -0.050 |
uyomi | -0.043 |
ingo | -0.043 |
glers | -0.043 |
emale | -0.042 |
Token | USA |
Token ID | 4916 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
)", | +0.055 |
ingo | +0.048 |
uyomi | +0.048 |
glers | +0.047 |
emale | +0.046 |
Neg logit contributions | |
smoot | -0.041 |
fres | -0.039 |
ans | -0.038 |
Pac | -0.038 |
chev | -0.037 |
Token | Today |
Token ID | 6288 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
)", | +0.028 |
uyomi | +0.025 |
ingo | +0.025 |
glers | +0.025 |
emale | +0.024 |
Neg logit contributions | |
smoot | -0.014 |
fres | -0.013 |
ans | -0.012 |
Pac | -0.012 |
chev | -0.012 |
Token | op |
Token ID | 1034 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
)", | +0.969 |
ingo | +0.835 |
glers | +0.816 |
uyomi | +0.815 |
emale | +0.795 |
Neg logit contributions | |
smoot | -0.868 |
fres | -0.823 |
ans | -0.802 |
Pac | -0.800 |
chev | -0.786 |
Token | - |
Token ID | 12 |
Feature activation | +8.08e-02 |
Pos logit contributions | |
)", | +0.587 |
uyomi | +0.505 |
ingo | +0.504 |
glers | +0.497 |
emale | +0.486 |
Neg logit contributions | |
smoot | -0.544 |
fres | -0.514 |
ans | -0.504 |
Pac | -0.496 |
Spur | -0.490 |
Token | ed |
Token ID | 276 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
)", | +0.066 |
uyomi | +0.057 |
glers | +0.057 |
ingo | +0.057 |
emale | +0.055 |
Neg logit contributions | |
smoot | -0.056 |
fres | -0.052 |
ans | -0.052 |
Pac | -0.050 |
Spur | -0.049 |
Token | on |
Token ID | 319 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
)", | +0.271 |
uyomi | +0.235 |
ingo | +0.234 |
glers | +0.233 |
emale | +0.227 |
Neg logit contributions | |
smoot | -0.220 |
fres | -0.208 |
ans | -0.204 |
Pac | -0.201 |
chev | -0.197 |
Token | August |
Token ID | 2932 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
smoot | +0.111 |
fres | +0.105 |
ans | +0.103 |
Pac | +0.101 |
Spur | +0.099 |
Neg logit contributions | |
)", | -0.121 |
uyomi | -0.104 |
ingo | -0.103 |
glers | -0.103 |
emale | -0.100 |
Token | a |
Token ID | 257 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
smoot | +0.022 |
fres | +0.020 |
ans | +0.020 |
Pac | +0.019 |
chev | +0.019 |
Neg logit contributions | |
)", | -0.029 |
ingo | -0.025 |
uyomi | -0.025 |
glers | -0.025 |
harm | -0.024 |
Token | service |
Token ID | 2139 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
)", | +0.024 |
ingo | +0.021 |
uyomi | +0.021 |
glers | +0.021 |
emale | +0.020 |
Neg logit contributions | |
smoot | -0.021 |
fres | -0.019 |
ans | -0.019 |
Pac | -0.019 |
chev | -0.018 |
Token | pistol |
Token ID | 16790 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
smoot | +0.209 |
fres | +0.196 |
ans | +0.192 |
Pac | +0.187 |
Spur | +0.184 |
Neg logit contributions | |
)", | -0.283 |
uyomi | -0.248 |
ingo | -0.246 |
glers | -0.245 |
emale | -0.240 |
Token | and |
Token ID | 290 |
Feature activation | +9.02e-02 |
Pos logit contributions | |
)", | +0.380 |
uyomi | +0.334 |
ingo | +0.332 |
glers | +0.331 |
emale | +0.324 |
Neg logit contributions | |
smoot | -0.267 |
fres | -0.250 |
ans | -0.245 |
Pac | -0.239 |
Spur | -0.235 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
)", | +0.075 |
uyomi | +0.065 |
ingo | +0.065 |
glers | +0.065 |
emale | +0.063 |
Neg logit contributions | |
smoot | -0.060 |
fres | -0.056 |
ans | -0.055 |
Pac | -0.054 |
Spur | -0.053 |
Token | rounds |
Token ID | 9196 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
smoot | +0.135 |
fres | +0.127 |
ans | +0.125 |
Pac | +0.122 |
Spur | +0.121 |
Neg logit contributions | |
)", | -0.142 |
uyomi | -0.123 |
ingo | -0.122 |
glers | -0.121 |
emale | -0.118 |
Token | of |
Token ID | 286 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
)", | +1.015 |
uyomi | +0.882 |
ingo | +0.876 |
glers | +0.868 |
emale | +0.848 |
Neg logit contributions | |
smoot | -0.832 |
fres | -0.781 |
ans | -0.765 |
Pac | -0.752 |
Spur | -0.742 |
Token | ammunition |
Token ID | 14271 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
)", | +0.011 |
uyomi | +0.010 |
ingo | +0.010 |
glers | +0.009 |
emale | +0.009 |
Neg logit contributions | |
smoot | -0.011 |
fres | -0.010 |
ans | -0.010 |
Pac | -0.010 |
Spur | -0.009 |
Token | that |
Token ID | 326 |
Feature activation | -4.50e-02 |
Pos logit contributions | |
)", | +0.291 |
uyomi | +0.256 |
ingo | +0.255 |
glers | +0.255 |
emale | +0.248 |
Neg logit contributions | |
smoot | -0.193 |
fres | -0.180 |
ans | -0.176 |
Pac | -0.173 |
Spur | -0.169 |
Token | disappeared |
Token ID | 12120 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
smoot | +0.024 |
fres | +0.022 |
ans | +0.021 |
Pac | +0.021 |
Spur | +0.020 |
Neg logit contributions | |
)", | -0.044 |
uyomi | -0.039 |
glers | -0.039 |
ingo | -0.039 |
emale | -0.038 |
Token | last |
Token ID | 938 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
)", | +0.250 |
glers | +0.216 |
ingo | +0.216 |
uyomi | +0.215 |
harm | +0.210 |
Neg logit contributions | |
smoot | -0.198 |
fres | -0.186 |
ans | -0.183 |
Pac | -0.181 |
Spur | -0.177 |
Token | eyed |
Token ID | 18834 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
smoot | +0.000 |
fres | +0.000 |
ans | +0.000 |
Pac | +0.000 |
Spur | +0.000 |
Neg logit contributions | |
)", | -0.000 |
uyomi | -0.000 |
ingo | -0.000 |
glers | -0.000 |
emale | -0.000 |
Token | boy |
Token ID | 2933 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
smoot | +0.202 |
fres | +0.189 |
ans | +0.186 |
Pac | +0.184 |
Spur | +0.180 |
Neg logit contributions | |
)", | -0.243 |
uyomi | -0.209 |
glers | -0.208 |
ingo | -0.208 |
emale | -0.203 |
Token | for |
Token ID | 329 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
smoot | +0.152 |
fres | +0.143 |
ans | +0.140 |
Pac | +0.137 |
Spur | +0.135 |
Neg logit contributions | |
)", | -0.180 |
uyomi | -0.156 |
ingo | -0.155 |
glers | -0.154 |
emale | -0.151 |
Token | a |
Token ID | 257 |
Feature activation | -8.38e-04 |
Pos logit contributions | |
smoot | +0.081 |
fres | +0.076 |
ans | +0.075 |
Pac | +0.073 |
Spur | +0.072 |
Neg logit contributions | |
)", | -0.103 |
uyomi | -0.089 |
ingo | -0.089 |
glers | -0.088 |
emale | -0.086 |
Token | p |
Token ID | 279 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
smoot | +0.001 |
fres | +0.001 |
ans | +0.001 |
Pac | +0.001 |
Spur | +0.001 |
Neg logit contributions | |
)", | -0.001 |
uyomi | -0.001 |
ingo | -0.001 |
glers | -0.001 |
emale | -0.001 |
Token | alt |
Token ID | 2501 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
smoot | +0.051 |
fres | +0.049 |
ans | +0.048 |
Pac | +0.048 |
Spur | +0.047 |
Neg logit contributions | |
)", | -0.032 |
uyomi | -0.026 |
ingo | -0.026 |
glers | -0.026 |
emale | -0.025 |
Token | ry |
Token ID | 563 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
)", | +0.728 |
ingo | +0.596 |
uyomi | +0.592 |
glers | +0.584 |
harm | +0.573 |
Neg logit contributions | |
smoot | -1.105 |
fres | -1.060 |
ans | -1.033 |
Pac | -1.031 |
Spur | -1.014 |
Token | sum |
Token ID | 2160 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
smoot | +0.015 |
fres | +0.014 |
ans | +0.013 |
Pac | +0.013 |
Spur | +0.013 |
Neg logit contributions | |
)", | -0.019 |
uyomi | -0.016 |
ingo | -0.016 |
glers | -0.016 |
emale | -0.016 |
Token | of |
Token ID | 286 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
)", | +0.182 |
uyomi | +0.158 |
ingo | +0.156 |
glers | +0.156 |
emale | +0.152 |
Neg logit contributions | |
smoot | -0.150 |
fres | -0.142 |
ans | -0.138 |
Pac | -0.136 |
Spur | -0.135 |
Token | money |
Token ID | 1637 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
smoot | +0.080 |
fres | +0.075 |
ans | +0.073 |
Pac | +0.072 |
Spur | +0.071 |
Neg logit contributions | |
)", | -0.122 |
uyomi | -0.106 |
ingo | -0.106 |
glers | -0.106 |
harm | -0.103 |
Token | ," |
Token ID | 553 |
Feature activation | +7.83e-02 |
Pos logit contributions | |
smoot | +0.128 |
fres | +0.121 |
ans | +0.118 |
Pac | +0.116 |
Spur | +0.114 |
Neg logit contributions | |
)", | -0.147 |
uyomi | -0.127 |
ingo | -0.126 |
glers | -0.125 |
emale | -0.122 |
Token | anyone |
Token ID | 2687 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
smoot | +0.120 |
fres | +0.113 |
ans | +0.112 |
Pac | +0.111 |
Spur | +0.109 |
Neg logit contributions | |
)", | -0.113 |
ingo | -0.095 |
glers | -0.095 |
uyomi | -0.095 |
harm | -0.092 |
Token | who |
Token ID | 508 |
Feature activation | +8.26e-02 |
Pos logit contributions | |
)", | +0.136 |
uyomi | +0.115 |
ingo | +0.115 |
glers | +0.115 |
harm | +0.111 |
Neg logit contributions | |
smoot | -0.136 |
fres | -0.128 |
ans | -0.126 |
Pac | -0.125 |
Spur | -0.123 |
Token | opposed |
Token ID | 6886 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
)", | +0.080 |
glers | +0.071 |
ingo | +0.071 |
uyomi | +0.070 |
harm | +0.069 |
Neg logit contributions | |
smoot | -0.043 |
fres | -0.040 |
Pac | -0.039 |
ans | -0.039 |
Spur | -0.038 |
Token | being |
Token ID | 852 |
Feature activation | +9.02e-02 |
Pos logit contributions | |
)", | +0.288 |
ingo | +0.253 |
glers | +0.251 |
uyomi | +0.251 |
harm | +0.245 |
Neg logit contributions | |
smoot | -0.190 |
fres | -0.177 |
ans | -0.174 |
Pac | -0.172 |
Spur | -0.167 |
Token | cons |
Token ID | 762 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
)", | +0.080 |
ingo | +0.069 |
glers | +0.069 |
uyomi | +0.069 |
harm | +0.067 |
Neg logit contributions | |
smoot | -0.055 |
fres | -0.051 |
ans | -0.050 |
Pac | -0.050 |
Spur | -0.049 |
Token | cript |
Token ID | 6519 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
smoot | +0.148 |
fres | +0.142 |
ans | +0.139 |
Pac | +0.137 |
Spur | +0.137 |
Neg logit contributions | |
)", | -0.101 |
uyomi | -0.082 |
ingo | -0.082 |
glers | -0.081 |
emale | -0.079 |
Token | ed |
Token ID | 276 |
Feature activation | +9.62e-02 |
Pos logit contributions | |
)", | +0.906 |
ingo | +0.783 |
uyomi | +0.776 |
glers | +0.763 |
emale | +0.748 |
Neg logit contributions | |
smoot | -0.931 |
fres | -0.880 |
Pac | -0.848 |
ans | -0.842 |
Spur | -0.842 |
Token | .[ |
Token ID | 3693 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
)", | +0.077 |
uyomi | +0.067 |
ingo | +0.067 |
glers | +0.066 |
emale | +0.065 |
Neg logit contributions | |
smoot | -0.067 |
fres | -0.063 |
ans | -0.062 |
Pac | -0.061 |
Spur | -0.060 |
Token | 28 |
Token ID | 2078 |
Feature activation | +6.41e-02 |
Pos logit contributions | |
smoot | +0.055 |
fres | +0.050 |
ans | +0.048 |
Pac | +0.047 |
Fedora | +0.046 |
Neg logit contributions | |
)", | -0.112 |
ingo | -0.101 |
uyomi | -0.101 |
glers | -0.100 |
harm | -0.099 |
Token | ] |
Token ID | 60 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
)", | +0.049 |
uyomi | +0.043 |
ingo | +0.042 |
glers | +0.042 |
emale | +0.041 |
Neg logit contributions | |
smoot | -0.047 |
fres | -0.044 |
ans | -0.044 |
Pac | -0.043 |
Spur | -0.042 |
Token | Aut |
Token ID | 5231 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
smoot | +0.157 |
fres | +0.147 |
ans | +0.143 |
Pac | +0.140 |
chev | +0.138 |
Neg logit contributions | |
)", | -0.190 |
glers | -0.164 |
ingo | -0.163 |
uyomi | -0.163 |
emale | -0.159 |
Token | ically |
Token ID | 1146 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
)", | +0.019 |
uyomi | +0.017 |
ingo | +0.017 |
glers | +0.016 |
emale | +0.016 |
Neg logit contributions | |
smoot | -0.018 |
fres | -0.017 |
ans | -0.016 |
Pac | -0.016 |
chev | -0.016 |
Token | Sc |
Token ID | 1446 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
)", | +0.299 |
uyomi | +0.259 |
ingo | +0.257 |
glers | +0.254 |
harm | +0.251 |
Neg logit contributions | |
smoot | -0.251 |
fres | -0.238 |
ans | -0.231 |
Pac | -0.228 |
chev | -0.223 |
Token | anned |
Token ID | 3577 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
)", | +0.253 |
ingo | +0.226 |
uyomi | +0.225 |
glers | +0.222 |
harm | +0.219 |
Neg logit contributions | |
smoot | -0.125 |
fres | -0.117 |
Pac | -0.107 |
Spur | -0.107 |
Fedora | -0.106 |
Token | Array |
Token ID | 15690 |
Feature activation | -5.58e-02 |
Pos logit contributions | |
smoot | +0.091 |
fres | +0.086 |
ans | +0.084 |
Pac | +0.082 |
chev | +0.081 |
Neg logit contributions | |
)", | -0.105 |
ingo | -0.091 |
uyomi | -0.090 |
glers | -0.090 |
emale | -0.088 |
Token | Rad |
Token ID | 5325 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
smoot | +0.036 |
fres | +0.034 |
ans | +0.034 |
Pac | +0.033 |
Spur | +0.032 |
Neg logit contributions | |
)", | -0.047 |
uyomi | -0.041 |
ingo | -0.041 |
glers | -0.041 |
emale | -0.040 |
Token | ars |
Token ID | 945 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
)", | +0.273 |
uyomi | +0.231 |
ingo | +0.230 |
glers | +0.229 |
emale | +0.223 |
Neg logit contributions | |
smoot | -0.301 |
fres | -0.286 |
ans | -0.280 |
Pac | -0.275 |
Spur | -0.273 |
Token | and |
Token ID | 290 |
Feature activation | -8.90e-02 |
Pos logit contributions | |
)", | +0.958 |
ingo | +0.825 |
uyomi | +0.819 |
glers | +0.816 |
emale | +0.792 |
Neg logit contributions | |
smoot | -0.863 |
fres | -0.820 |
ans | -0.799 |
Pac | -0.785 |
chev | -0.774 |
Token | 38 |
Token ID | 4353 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
smoot | +0.061 |
fres | +0.058 |
ans | +0.057 |
Pac | +0.056 |
chev | +0.055 |
Neg logit contributions | |
)", | -0.072 |
ingo | -0.062 |
uyomi | -0.062 |
glers | -0.062 |
emale | -0.060 |
Token | LA |
Token ID | 9131 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
smoot | +0.022 |
fres | +0.021 |
ans | +0.021 |
Pac | +0.020 |
chev | +0.020 |
Neg logit contributions | |
)", | -0.025 |
uyomi | -0.022 |
ingo | -0.022 |
glers | -0.021 |
emale | -0.021 |
Token | U |
Token ID | 52 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
smoot | +0.240 |
fres | +0.226 |
ans | +0.221 |
Pac | +0.216 |
Spur | +0.212 |
Neg logit contributions | |
)", | -0.310 |
uyomi | -0.271 |
ingo | -0.269 |
glers | -0.268 |
emale | -0.262 |
Token | - |
Token ID | 12 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
)", | +0.160 |
ingo | +0.138 |
uyomi | +0.138 |
glers | +0.137 |
emale | +0.134 |
Neg logit contributions | |
smoot | -0.145 |
fres | -0.137 |
ans | -0.134 |
Pac | -0.132 |
Fedora | -0.129 |
Token | er |
Token ID | 263 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
smoot | +0.291 |
fres | +0.275 |
ans | +0.270 |
Pac | +0.264 |
Spur | +0.260 |
Neg logit contributions | |
)", | -0.356 |
uyomi | -0.312 |
ingo | -0.308 |
glers | -0.307 |
emale | -0.301 |
Token | magnet |
Token ID | 19972 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
)", | +0.193 |
ingo | +0.172 |
uyomi | +0.171 |
glers | +0.170 |
harm | +0.167 |
Neg logit contributions | |
smoot | -0.098 |
fres | -0.091 |
ans | -0.089 |
Pac | -0.086 |
Spur | -0.084 |
Token | ? |
Token ID | 30 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
smoot | +0.228 |
fres | +0.209 |
ans | +0.204 |
Pac | +0.198 |
Spur | +0.193 |
Neg logit contributions | |
)", | -0.474 |
uyomi | -0.425 |
ingo | -0.421 |
glers | -0.421 |
emale | -0.414 |
Token |
|
Token ID | 198 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
)", | +0.159 |
uyomi | +0.140 |
ingo | +0.139 |
glers | +0.138 |
emale | +0.136 |
Neg logit contributions | |
smoot | -0.111 |
fres | -0.104 |
ans | -0.102 |
Pac | -0.100 |
Spur | -0.098 |
Token |
|
Token ID | 198 |
Feature activation | +9.21e-02 |
Pos logit contributions | |
)", | +0.119 |
ingo | +0.103 |
glers | +0.102 |
uyomi | +0.102 |
harm | +0.100 |
Neg logit contributions | |
smoot | -0.089 |
fres | -0.084 |
ans | -0.081 |
Pac | -0.080 |
Spur | -0.079 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
)", | +0.087 |
ingo | +0.077 |
uyomi | +0.077 |
glers | +0.077 |
harm | +0.075 |
Neg logit contributions | |
smoot | -0.052 |
fres | -0.048 |
ans | -0.046 |
Pac | -0.045 |
Spur | -0.045 |
Token | : |
Token ID | 25 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
smoot | +0.798 |
fres | +0.737 |
ans | +0.718 |
Pac | +0.698 |
Spur | +0.683 |
Neg logit contributions | |
)", | -1.527 |
uyomi | -1.361 |
ingo | -1.353 |
glers | -1.349 |
emale | -1.322 |
Token | hey |
Token ID | 17207 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
)", | +0.252 |
uyomi | +0.219 |
ingo | +0.218 |
glers | +0.217 |
emale | +0.212 |
Neg logit contributions | |
smoot | -0.213 |
fres | -0.201 |
ans | -0.198 |
Pac | -0.195 |
chev | -0.191 |
Token | _ |
Token ID | 62 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
)", | +0.103 |
ingo | +0.090 |
uyomi | +0.090 |
glers | +0.090 |
emale | +0.088 |
Neg logit contributions | |
smoot | -0.085 |
fres | -0.080 |
ans | -0.078 |
Pac | -0.077 |
Spur | -0.076 |
Token | ler |
Token ID | 1754 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
)", | +0.340 |
ingo | +0.299 |
glers | +0.296 |
uyomi | +0.294 |
harm | +0.291 |
Neg logit contributions | |
smoot | -0.288 |
fres | -0.271 |
ans | -0.259 |
Spur | -0.258 |
Pac | -0.256 |
Token | oy |
Token ID | 726 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
)", | +0.295 |
ingo | +0.262 |
glers | +0.255 |
uyomi | +0.253 |
harm | +0.249 |
Neg logit contributions | |
smoot | -0.242 |
fres | -0.228 |
Pac | -0.220 |
ans | -0.220 |
Spur | -0.217 |
Token | Flyers |
Token ID | 30652 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
smoot | +0.051 |
fres | +0.048 |
ans | +0.047 |
Pac | +0.046 |
chev | +0.045 |
Neg logit contributions | |
)", | -0.064 |
glers | -0.056 |
ingo | -0.055 |
uyomi | -0.055 |
harm | -0.054 |
Token | was |
Token ID | 373 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
smoot | +0.229 |
fres | +0.212 |
ans | +0.211 |
Pac | +0.209 |
chev | +0.204 |
Neg logit contributions | |
)", | -0.425 |
glers | -0.376 |
ingo | -0.372 |
uyomi | -0.371 |
harm | -0.364 |
Token | Chicago |
Token ID | 4842 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
smoot | +0.011 |
fres | +0.011 |
ans | +0.011 |
Pac | +0.010 |
chev | +0.010 |
Neg logit contributions | |
)", | -0.014 |
ingo | -0.012 |
glers | -0.012 |
uyomi | -0.012 |
harm | -0.012 |
Token | 's |
Token ID | 338 |
Feature activation | +5.73e-02 |
Pos logit contributions | |
)", | +0.091 |
ingo | +0.080 |
uyomi | +0.079 |
glers | +0.078 |
emale | +0.077 |
Neg logit contributions | |
smoot | -0.069 |
fres | -0.065 |
ans | -0.063 |
Pac | -0.062 |
chev | -0.062 |
Token | fourth |
Token ID | 5544 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
)", | +0.052 |
ingo | +0.046 |
glers | +0.045 |
uyomi | +0.045 |
adolesc | +0.044 |
Neg logit contributions | |
smoot | -0.033 |
fres | -0.031 |
ans | -0.031 |
Pac | -0.030 |
chev | -0.030 |
Token | straight |
Token ID | 3892 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
smoot | +0.345 |
fres | +0.326 |
ans | +0.320 |
Pac | +0.314 |
chev | +0.308 |
Neg logit contributions | |
)", | -0.421 |
uyomi | -0.365 |
ingo | -0.364 |
glers | -0.363 |
emale | -0.353 |
Token | , |
Token ID | 11 |
Feature activation | -6.62e-02 |
Pos logit contributions | |
smoot | +1.137 |
fres | +1.078 |
ans | +1.060 |
Pac | +1.040 |
Spur | +1.026 |
Neg logit contributions | |
)", | -1.131 |
uyomi | -0.972 |
ingo | -0.961 |
glers | -0.958 |
emale | -0.935 |
Token | the |
Token ID | 262 |
Feature activation | -8.15e-02 |
Pos logit contributions | |
smoot | +0.046 |
fres | +0.043 |
ans | +0.043 |
Pac | +0.042 |
chev | +0.041 |
Neg logit contributions | |
)", | -0.052 |
glers | -0.046 |
ingo | -0.045 |
uyomi | -0.045 |
harm | -0.044 |
Token | Blackhawks |
Token ID | 35663 |
Feature activation | +9.40e-02 |
Pos logit contributions | |
smoot | +0.047 |
fres | +0.044 |
ans | +0.044 |
Pac | +0.043 |
chev | +0.043 |
Neg logit contributions | |
)", | -0.074 |
glers | -0.065 |
ingo | -0.064 |
uyomi | -0.064 |
harm | -0.063 |
Token | ' |
Token ID | 6 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
)", | +0.084 |
ingo | +0.073 |
glers | +0.073 |
uyomi | +0.073 |
emale | +0.071 |
Neg logit contributions | |
smoot | -0.056 |
fres | -0.053 |
ans | -0.052 |
Pac | -0.051 |
chev | -0.050 |
Token | longest |
Token ID | 14069 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
)", | +0.247 |
ingo | +0.218 |
glers | +0.217 |
uyomi | +0.216 |
emale | +0.210 |
Neg logit contributions | |
smoot | -0.159 |
fres | -0.149 |
ans | -0.147 |
Pac | -0.145 |
chev | -0.143 |
Token | was |
Token ID | 373 |
Feature activation | +5.12e-02 |
Pos logit contributions | |
)", | +0.066 |
ingo | +0.058 |
uyomi | +0.058 |
glers | +0.058 |
harm | +0.057 |
Neg logit contributions | |
smoot | -0.040 |
fres | -0.037 |
ans | -0.036 |
Pac | -0.036 |
Fedora | -0.035 |
Token | about |
Token ID | 546 |
Feature activation | +5.40e-02 |
Pos logit contributions | |
)", | +0.045 |
ingo | +0.039 |
uyomi | +0.039 |
glers | +0.038 |
harm | +0.038 |
Neg logit contributions | |
smoot | -0.032 |
fres | -0.030 |
ans | -0.029 |
Pac | -0.029 |
chev | -0.028 |
Token | homosexuality |
Token ID | 19822 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
)", | +0.045 |
ingo | +0.039 |
uyomi | +0.039 |
glers | +0.038 |
emale | +0.038 |
Neg logit contributions | |
smoot | -0.036 |
fres | -0.034 |
ans | -0.034 |
Pac | -0.033 |
chev | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | +8.81e-02 |
Pos logit contributions | |
smoot | +0.282 |
fres | +0.266 |
ans | +0.260 |
Pac | +0.256 |
Spur | +0.252 |
Neg logit contributions | |
)", | -0.330 |
ingo | -0.285 |
uyomi | -0.285 |
glers | -0.283 |
harm | -0.275 |
Token |
|
Token ID | 198 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
)", | +0.074 |
ingo | +0.065 |
uyomi | +0.064 |
glers | +0.064 |
harm | +0.063 |
Neg logit contributions | |
smoot | -0.059 |
fres | -0.055 |
ans | -0.053 |
bolted | -0.051 |
Pac | -0.051 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
)", | +0.096 |
ingo | +0.082 |
uyomi | +0.082 |
glers | +0.081 |
harm | +0.080 |
Neg logit contributions | |
smoot | -0.093 |
fres | -0.087 |
ans | -0.084 |
Spur | -0.083 |
Pac | -0.083 |
Token | : |
Token ID | 25 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
smoot | +0.776 |
fres | +0.717 |
ans | +0.698 |
Pac | +0.681 |
Spur | +0.665 |
Neg logit contributions | |
)", | -1.454 |
uyomi | -1.290 |
ingo | -1.288 |
glers | -1.283 |
emale | -1.253 |
Token | k |
Token ID | 479 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
)", | +0.312 |
uyomi | +0.271 |
ingo | +0.270 |
glers | +0.268 |
emale | +0.262 |
Neg logit contributions | |
smoot | -0.258 |
fres | -0.243 |
ans | -0.239 |
Pac | -0.236 |
chev | -0.230 |
Token | imp |
Token ID | 11011 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
)", | +0.009 |
uyomi | +0.007 |
ingo | +0.007 |
glers | +0.007 |
emale | +0.007 |
Neg logit contributions | |
smoot | -0.008 |
fres | -0.007 |
ans | -0.007 |
Pac | -0.007 |
Spur | -0.007 |
Token | unk |
Token ID | 2954 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
smoot | +0.070 |
fres | +0.066 |
ans | +0.063 |
Pac | +0.063 |
Spur | +0.063 |
Neg logit contributions | |
)", | -0.083 |
ingo | -0.073 |
uyomi | -0.072 |
glers | -0.072 |
emale | -0.070 |
Token | rock |
Token ID | 10823 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
smoot | +0.308 |
fres | +0.291 |
ans | +0.283 |
Pac | +0.279 |
Spur | +0.276 |
Neg logit contributions | |
)", | -0.345 |
ingo | -0.299 |
uyomi | -0.299 |
glers | -0.297 |
emale | -0.289 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
smoot | +0.014 |
fres | +0.013 |
ans | +0.013 |
chev | +0.013 |
Pac | +0.013 |
Neg logit contributions | |
)", | -0.018 |
glers | -0.016 |
ingo | -0.016 |
uyomi | -0.016 |
harm | -0.015 |
Token | boys |
Token ID | 13202 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
)", | +0.121 |
ingo | +0.101 |
glers | +0.101 |
uyomi | +0.101 |
harm | +0.098 |
Neg logit contributions | |
smoot | -0.144 |
fres | -0.137 |
ans | -0.133 |
Pac | -0.132 |
Spur | -0.132 |
Token | beware |
Token ID | 40600 |
Feature activation | +9.76e-02 |
Pos logit contributions | |
smoot | +0.114 |
fres | +0.107 |
ans | +0.104 |
Pac | +0.104 |
chev | +0.102 |
Neg logit contributions | |
)", | -0.140 |
uyomi | -0.122 |
ingo | -0.122 |
glers | -0.119 |
harm | -0.117 |
Token |
|
Token ID | 198 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
)", | +0.084 |
ingo | +0.074 |
uyomi | +0.074 |
glers | +0.073 |
emale | +0.071 |
Neg logit contributions | |
smoot | -0.063 |
fres | -0.059 |
ans | -0.057 |
Pac | -0.056 |
Spur | -0.055 |
Token |
|
Token ID | 198 |
Feature activation | -4.45e-02 |
Pos logit contributions | |
smoot | +0.027 |
fres | +0.025 |
ans | +0.024 |
Pac | +0.024 |
Spur | +0.023 |
Neg logit contributions | |
)", | -0.036 |
ingo | -0.031 |
glers | -0.031 |
uyomi | -0.031 |
harm | -0.030 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
smoot | +0.025 |
fres | +0.023 |
ans | +0.022 |
Pac | +0.022 |
Spur | +0.022 |
Neg logit contributions | |
)", | -0.042 |
ingo | -0.037 |
glers | -0.037 |
uyomi | -0.037 |
harm | -0.036 |
Token | : |
Token ID | 25 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
smoot | +0.743 |
fres | +0.686 |
ans | +0.667 |
Pac | +0.649 |
Spur | +0.637 |
Neg logit contributions | |
)", | -1.395 |
uyomi | -1.238 |
ingo | -1.234 |
glers | -1.231 |
harm | -1.201 |
Token | j |
Token ID | 474 |
Feature activation | -8.43e-02 |
Pos logit contributions | |
)", | +0.292 |
uyomi | +0.254 |
ingo | +0.253 |
glers | +0.251 |
emale | +0.245 |
Neg logit contributions | |
smoot | -0.244 |
fres | -0.229 |
ans | -0.226 |
Pac | -0.222 |
chev | -0.217 |
Token | wt |
Token ID | 46569 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
smoot | +0.061 |
fres | +0.057 |
ans | +0.055 |
Pac | +0.055 |
Spur | +0.054 |
Neg logit contributions | |
)", | -0.066 |
ingo | -0.057 |
uyomi | -0.057 |
glers | -0.057 |
emale | -0.055 |
Token | 0001 |
Token ID | 18005 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
)", | +0.178 |
ingo | +0.157 |
uyomi | +0.156 |
glers | +0.155 |
harm | +0.152 |
Neg logit contributions | |
smoot | -0.147 |
fres | -0.138 |
ans | -0.133 |
Pac | -0.133 |
Spur | -0.131 |
Token | - |
Token ID | 532 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
smoot | +0.248 |
fres | +0.236 |
ans | +0.231 |
Pac | +0.227 |
Spur | +0.224 |
Neg logit contributions | |
)", | -0.254 |
uyomi | -0.219 |
ingo | -0.218 |
glers | -0.217 |
emale | -0.211 |
Token | bad |
Token ID | 2089 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
)", | +0.006 |
ingo | +0.005 |
glers | +0.005 |
harm | +0.005 |
uyomi | +0.005 |
Neg logit contributions | |
smoot | -0.005 |
fres | -0.005 |
ans | -0.005 |
Pac | -0.005 |
chev | -0.005 |
Token | idea |
Token ID | 2126 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
)", | +0.158 |
ingo | +0.137 |
glers | +0.134 |
uyomi | +0.134 |
harm | +0.131 |
Neg logit contributions | |
smoot | -0.138 |
fres | -0.131 |
ans | -0.128 |
Pac | -0.126 |
chev | -0.124 |
Token | . |
Token ID | 13 |
Feature activation | -5.58e-03 |
Pos logit contributions | |
)", | +0.117 |
ingo | +0.101 |
uyomi | +0.100 |
glers | +0.100 |
harm | +0.097 |
Neg logit contributions | |
smoot | -0.096 |
fres | -0.090 |
ans | -0.088 |
Pac | -0.086 |
Spur | -0.085 |
Token |
|
Token ID | 198 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
smoot | +0.004 |
fres | +0.003 |
ans | +0.003 |
Pac | +0.003 |
Spur | +0.003 |
Neg logit contributions | |
)", | -0.005 |
uyomi | -0.004 |
ingo | -0.004 |
glers | -0.004 |
emale | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
smoot | +0.091 |
fres | +0.085 |
ans | +0.083 |
Pac | +0.081 |
Spur | +0.080 |
Neg logit contributions | |
)", | -0.122 |
ingo | -0.106 |
glers | -0.106 |
uyomi | -0.106 |
harm | -0.103 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
smoot | +0.077 |
fres | +0.071 |
ans | +0.069 |
Pac | +0.067 |
Spur | +0.066 |
Neg logit contributions | |
)", | -0.136 |
uyomi | -0.120 |
ingo | -0.120 |
glers | -0.120 |
emale | -0.117 |
Token | : |
Token ID | 25 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
smoot | +0.729 |
fres | +0.673 |
ans | +0.655 |
Pac | +0.637 |
Spur | +0.624 |
Neg logit contributions | |
)", | -1.381 |
uyomi | -1.227 |
ingo | -1.222 |
glers | -1.219 |
emale | -1.191 |
Token | Mike |
Token ID | 4995 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
)", | +0.224 |
uyomi | +0.194 |
ingo | +0.193 |
glers | +0.192 |
emale | +0.187 |
Neg logit contributions | |
smoot | -0.189 |
fres | -0.178 |
ans | -0.175 |
Pac | -0.173 |
chev | -0.169 |
Token | M |
Token ID | 44 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
)", | +0.032 |
ingo | +0.027 |
uyomi | +0.027 |
glers | +0.027 |
emale | +0.026 |
Neg logit contributions | |
smoot | -0.031 |
fres | -0.029 |
ans | -0.028 |
Pac | -0.028 |
chev | -0.027 |
Token | anners |
Token ID | 15672 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
)", | +0.010 |
ingo | +0.008 |
uyomi | +0.008 |
glers | +0.008 |
emale | +0.008 |
Neg logit contributions | |
smoot | -0.009 |
fres | -0.008 |
ans | -0.008 |
Pac | -0.008 |
Spur | -0.008 |
Token | - |
Token ID | 532 |
Feature activation | -4.03e-02 |
Pos logit contributions | |
)", | +0.173 |
ingo | +0.150 |
uyomi | +0.149 |
glers | +0.148 |
harm | +0.145 |
Neg logit contributions | |
smoot | -0.165 |
fres | -0.156 |
ans | -0.152 |
Pac | -0.148 |
Spur | -0.147 |
Token | , |
Token ID | 11 |
Feature activation | -6.29e-02 |
Pos logit contributions | |
smoot | +0.047 |
fres | +0.044 |
ans | +0.043 |
Pac | +0.042 |
Spur | +0.042 |
Neg logit contributions | |
)", | -0.051 |
uyomi | -0.044 |
ingo | -0.044 |
glers | -0.043 |
emale | -0.042 |
Token | I |
Token ID | 314 |
Feature activation | -8.86e-02 |
Pos logit contributions | |
smoot | +0.041 |
fres | +0.038 |
ans | +0.037 |
Pac | +0.037 |
Spur | +0.036 |
Neg logit contributions | |
)", | -0.054 |
uyomi | -0.047 |
ingo | -0.047 |
glers | -0.047 |
emale | -0.046 |
Token | think |
Token ID | 892 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
smoot | +0.062 |
fres | +0.058 |
ans | +0.058 |
Pac | +0.057 |
Spur | +0.056 |
Neg logit contributions | |
)", | -0.070 |
ingo | -0.060 |
uyomi | -0.060 |
glers | -0.060 |
harm | -0.058 |
Token |
|
Token ID | 198 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
)", | +0.026 |
uyomi | +0.022 |
ingo | +0.022 |
glers | +0.022 |
emale | +0.022 |
Neg logit contributions | |
smoot | -0.019 |
fres | -0.018 |
ans | -0.017 |
Pac | -0.017 |
Spur | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
)", | +0.165 |
ingo | +0.143 |
glers | +0.143 |
uyomi | +0.142 |
harm | +0.139 |
Neg logit contributions | |
smoot | -0.126 |
fres | -0.118 |
ans | -0.114 |
Pac | -0.112 |
Spur | -0.110 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
)", | +0.259 |
ingo | +0.228 |
uyomi | +0.228 |
glers | +0.228 |
harm | +0.223 |
Neg logit contributions | |
smoot | -0.154 |
fres | -0.143 |
ans | -0.137 |
Pac | -0.133 |
Spur | -0.133 |
Token | : |
Token ID | 25 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
smoot | +0.724 |
fres | +0.669 |
ans | +0.650 |
Pac | +0.632 |
Spur | +0.620 |
Neg logit contributions | |
)", | -1.353 |
uyomi | -1.198 |
ingo | -1.196 |
glers | -1.193 |
harm | -1.164 |
Token | B |
Token ID | 347 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
)", | +0.379 |
uyomi | +0.329 |
ingo | +0.328 |
glers | +0.326 |
emale | +0.318 |
Neg logit contributions | |
smoot | -0.320 |
fres | -0.301 |
ans | -0.297 |
Pac | -0.292 |
chev | -0.286 |
Token | iz |
Token ID | 528 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
)", | +0.025 |
ingo | +0.021 |
uyomi | +0.021 |
glers | +0.021 |
harm | +0.021 |
Neg logit contributions | |
smoot | -0.022 |
fres | -0.021 |
ans | -0.020 |
Pac | -0.020 |
Fedora | -0.019 |
Token | r |
Token ID | 81 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
)", | +0.011 |
uyomi | +0.010 |
ingo | +0.010 |
glers | +0.010 |
emale | +0.009 |
Neg logit contributions | |
smoot | -0.011 |
fres | -0.010 |
ans | -0.010 |
Pac | -0.010 |
Spur | -0.010 |
Token | Pix |
Token ID | 21642 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
)", | +0.168 |
ingo | +0.149 |
uyomi | +0.147 |
glers | +0.146 |
harm | +0.143 |
Neg logit contributions | |
smoot | -0.144 |
fres | -0.136 |
ans | -0.130 |
Pac | -0.128 |
Spur | -0.127 |
Token | and |
Token ID | 290 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
)", | +0.388 |
ingo | +0.341 |
glers | +0.339 |
uyomi | +0.339 |
harm | +0.328 |
Neg logit contributions | |
smoot | -0.257 |
fres | -0.239 |
ans | -0.235 |
Pac | -0.233 |
chev | -0.226 |
Token | retiring |
Token ID | 29040 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
smoot | +0.017 |
fres | +0.016 |
ans | +0.016 |
Pac | +0.016 |
Spur | +0.015 |
Neg logit contributions | |
)", | -0.022 |
ingo | -0.019 |
uyomi | -0.019 |
glers | -0.018 |
harm | -0.018 |
Token | old |
Token ID | 1468 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
)", | +0.038 |
ingo | +0.034 |
uyomi | +0.033 |
glers | +0.033 |
harm | +0.032 |
Neg logit contributions | |
smoot | -0.028 |
fres | -0.026 |
ans | -0.026 |
Pac | -0.025 |
chev | -0.025 |
Token | fuel |
Token ID | 5252 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
smoot | +0.280 |
fres | +0.262 |
ans | +0.257 |
Pac | +0.252 |
Spur | +0.247 |
Neg logit contributions | |
)", | -0.386 |
uyomi | -0.338 |
ingo | -0.336 |
glers | -0.334 |
emale | -0.326 |
Token | oil |
Token ID | 3056 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
smoot | +0.023 |
fres | +0.022 |
ans | +0.021 |
Pac | +0.021 |
Spur | +0.021 |
Neg logit contributions | |
)", | -0.035 |
uyomi | -0.031 |
ingo | -0.031 |
glers | -0.031 |
emale | -0.030 |
Token | plants |
Token ID | 6134 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
smoot | +0.441 |
fres | +0.415 |
ans | +0.407 |
Pac | +0.399 |
Spur | +0.392 |
Neg logit contributions | |
)", | -0.562 |
uyomi | -0.492 |
ingo | -0.488 |
glers | -0.486 |
emale | -0.475 |
Token | , |
Token ID | 11 |
Feature activation | +7.48e-02 |
Pos logit contributions | |
smoot | +0.914 |
fres | +0.860 |
ans | +0.844 |
Pac | +0.825 |
Spur | +0.813 |
Neg logit contributions | |
)", | -1.143 |
uyomi | -0.999 |
ingo | -0.988 |
glers | -0.986 |
emale | -0.965 |
Token | the |
Token ID | 262 |
Feature activation | +7.92e-02 |
Pos logit contributions | |
)", | +0.063 |
ingo | +0.055 |
glers | +0.054 |
uyomi | +0.054 |
harm | +0.053 |
Neg logit contributions | |
smoot | -0.049 |
fres | -0.046 |
ans | -0.045 |
Pac | -0.045 |
chev | -0.043 |
Token | H |
Token ID | 367 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
)", | +0.065 |
ingo | +0.056 |
uyomi | +0.056 |
glers | +0.056 |
harm | +0.054 |
Neg logit contributions | |
smoot | -0.053 |
fres | -0.050 |
ans | -0.049 |
Pac | -0.049 |
Spur | -0.048 |
Token | EC |
Token ID | 2943 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
)", | +0.016 |
ingo | +0.014 |
uyomi | +0.014 |
glers | +0.013 |
harm | +0.013 |
Neg logit contributions | |
smoot | -0.017 |
fres | -0.016 |
ans | -0.015 |
Pac | -0.015 |
Spur | -0.015 |
Token | O |
Token ID | 46 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
smoot | +0.266 |
fres | +0.252 |
ans | +0.247 |
Spur | +0.241 |
Pac | +0.241 |
Neg logit contributions | |
)", | -0.251 |
ingo | -0.213 |
uyomi | -0.210 |
glers | -0.210 |
harm | -0.203 |
Token | to |
Token ID | 284 |
Feature activation | -8.71e-02 |
Pos logit contributions | |
)", | +0.062 |
ingo | +0.053 |
glers | +0.052 |
uyomi | +0.052 |
emale | +0.051 |
Neg logit contributions | |
smoot | -0.053 |
fres | -0.050 |
ans | -0.049 |
Pac | -0.048 |
chev | -0.047 |
Token | Go |
Token ID | 1514 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
smoot | +0.066 |
fres | +0.062 |
ans | +0.061 |
Pac | +0.060 |
Spur | +0.059 |
Neg logit contributions | |
)", | -0.066 |
uyomi | -0.055 |
ingo | -0.055 |
glers | -0.055 |
emale | -0.054 |
Token | Back |
Token ID | 5157 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
smoot | +0.102 |
fres | +0.096 |
ans | +0.093 |
Pac | +0.092 |
chev | +0.090 |
Neg logit contributions | |
)", | -0.112 |
ingo | -0.095 |
glers | -0.095 |
uyomi | -0.094 |
emale | -0.092 |
Token | There |
Token ID | 1318 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
smoot | +0.026 |
fres | +0.025 |
ans | +0.024 |
Pac | +0.024 |
Spur | +0.023 |
Neg logit contributions | |
)", | -0.028 |
ingo | -0.024 |
uyomi | -0.023 |
glers | -0.023 |
emale | -0.023 |
Token | Som |
Token ID | 9995 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
smoot | +0.228 |
fres | +0.215 |
ans | +0.211 |
Pac | +0.207 |
Spur | +0.204 |
Neg logit contributions | |
)", | -0.240 |
uyomi | -0.205 |
ingo | -0.205 |
glers | -0.203 |
emale | -0.199 |
Token | eday |
Token ID | 23712 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
smoot | +0.328 |
fres | +0.314 |
ans | +0.309 |
Pac | +0.305 |
Spur | +0.303 |
Neg logit contributions | |
)", | -0.180 |
uyomi | -0.142 |
ingo | -0.142 |
glers | -0.141 |
emale | -0.135 |
Token | ." |
Token ID | 526 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
smoot | +0.991 |
fres | +0.938 |
ans | +0.923 |
Pac | +0.904 |
Spur | +0.891 |
Neg logit contributions | |
)", | -1.062 |
uyomi | -0.921 |
ingo | -0.910 |
glers | -0.908 |
emale | -0.887 |
Token |
|
Token ID | 198 |
Feature activation | -6.87e-02 |
Pos logit contributions | |
smoot | +0.069 |
fres | +0.065 |
ans | +0.063 |
Pac | +0.061 |
chev | +0.061 |
Neg logit contributions | |
)", | -0.086 |
ingo | -0.074 |
glers | -0.074 |
uyomi | -0.074 |
harm | -0.072 |
Token |
|
Token ID | 198 |
Feature activation | -8.25e-02 |
Pos logit contributions | |
smoot | +0.044 |
fres | +0.041 |
ans | +0.040 |
Pac | +0.039 |
Spur | +0.039 |
Neg logit contributions | |
)", | -0.059 |
ingo | -0.051 |
uyomi | -0.051 |
glers | -0.051 |
harm | -0.050 |
Token | In |
Token ID | 818 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
smoot | +0.069 |
fres | +0.065 |
ans | +0.064 |
Spur | +0.062 |
Fedora | +0.062 |
Neg logit contributions | |
)", | -0.056 |
ingo | -0.046 |
uyomi | -0.046 |
glers | -0.046 |
harm | -0.045 |
Token | 1984 |
Token ID | 12844 |
Feature activation | +8.59e-02 |
Pos logit contributions | |
smoot | +0.127 |
fres | +0.119 |
ans | +0.116 |
Pac | +0.114 |
chev | +0.111 |
Neg logit contributions | |
)", | -0.172 |
ingo | -0.150 |
uyomi | -0.149 |
glers | -0.149 |
emale | -0.145 |
Token | as |
Token ID | 355 |
Feature activation | +5.35e-03 |
Pos logit contributions | |
)", | +0.124 |
uyomi | +0.107 |
ingo | +0.106 |
glers | +0.105 |
emale | +0.103 |
Neg logit contributions | |
smoot | -0.109 |
fres | -0.103 |
ans | -0.101 |
Pac | -0.100 |
Spur | -0.098 |
Token | it |
Token ID | 340 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
)", | +0.005 |
uyomi | +0.004 |
ingo | +0.004 |
glers | +0.004 |
harm | +0.004 |
Neg logit contributions | |
smoot | -0.003 |
fres | -0.003 |
ans | -0.003 |
Pac | -0.003 |
chev | -0.003 |
Token | is |
Token ID | 318 |
Feature activation | -7.83e-02 |
Pos logit contributions | |
)", | +0.033 |
ingo | +0.029 |
uyomi | +0.029 |
glers | +0.029 |
harm | +0.028 |
Neg logit contributions | |
smoot | -0.023 |
fres | -0.022 |
ans | -0.021 |
Pac | -0.021 |
chev | -0.021 |
Token | dem |
Token ID | 1357 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
smoot | +0.050 |
fres | +0.047 |
ans | +0.046 |
Pac | +0.046 |
chev | +0.045 |
Neg logit contributions | |
)", | -0.067 |
ingo | -0.058 |
uyomi | -0.058 |
glers | -0.057 |
harm | -0.057 |
Token | e |
Token ID | 68 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
smoot | +0.574 |
fres | +0.545 |
ans | +0.538 |
Pac | +0.526 |
Spur | +0.517 |
Neg logit contributions | |
)", | -0.613 |
uyomi | -0.532 |
glers | -0.526 |
ingo | -0.522 |
emale | -0.509 |
Token | aning |
Token ID | 7574 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
)", | +0.147 |
ingo | +0.133 |
uyomi | +0.133 |
glers | +0.132 |
emale | +0.130 |
Neg logit contributions | |
smoot | -0.053 |
fres | -0.047 |
Pac | -0.044 |
ans | -0.043 |
Spur | -0.043 |
Token | for |
Token ID | 329 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
smoot | +0.919 |
fres | +0.866 |
ans | +0.849 |
Pac | +0.832 |
Spur | +0.819 |
Neg logit contributions | |
)", | -1.109 |
uyomi | -0.965 |
ingo | -0.958 |
glers | -0.955 |
emale | -0.933 |
Token | women |
Token ID | 1466 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
smoot | +0.102 |
fres | +0.096 |
ans | +0.095 |
Pac | +0.093 |
chev | +0.091 |
Neg logit contributions | |
)", | -0.121 |
uyomi | -0.104 |
ingo | -0.104 |
glers | -0.103 |
emale | -0.102 |
Token | , |
Token ID | 11 |
Feature activation | -4.13e-02 |
Pos logit contributions | |
)", | +0.011 |
ingo | +0.009 |
uyomi | +0.009 |
glers | +0.009 |
harm | +0.009 |
Neg logit contributions | |
smoot | -0.009 |
fres | -0.008 |
ans | -0.008 |
Pac | -0.008 |
Spur | -0.008 |
Token | but |
Token ID | 475 |
Feature activation | +7.92e-02 |
Pos logit contributions | |
smoot | +0.029 |
fres | +0.027 |
ans | +0.027 |
Pac | +0.026 |
Spur | +0.026 |
Neg logit contributions | |
)", | -0.033 |
uyomi | -0.029 |
ingo | -0.029 |
glers | -0.028 |
emale | -0.028 |
Token | according |
Token ID | 1864 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
)", | +0.068 |
ingo | +0.059 |
glers | +0.058 |
uyomi | +0.058 |
emale | +0.057 |
Neg logit contributions | |
smoot | -0.051 |
fres | -0.048 |
ans | -0.047 |
Pac | -0.046 |
chev | -0.045 |
Token | from |
Token ID | 422 |
Feature activation | -1.36e-03 |
Pos logit contributions | |
)", | +0.051 |
ingo | +0.043 |
uyomi | +0.043 |
glers | +0.042 |
harm | +0.041 |
Neg logit contributions | |
smoot | -0.053 |
fres | -0.050 |
ans | -0.049 |
Pac | -0.049 |
Spur | -0.048 |
Token | natural |
Token ID | 3288 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
smoot | +0.001 |
fres | +0.001 |
ans | +0.001 |
Pac | +0.001 |
chev | +0.001 |
Neg logit contributions | |
)", | -0.001 |
ingo | -0.001 |
uyomi | -0.001 |
glers | -0.001 |
emale | -0.001 |
Token | gas |
Token ID | 3623 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
)", | +0.153 |
ingo | +0.136 |
uyomi | +0.136 |
glers | +0.135 |
harm | +0.132 |
Neg logit contributions | |
smoot | -0.073 |
fres | -0.067 |
ans | -0.065 |
Pac | -0.065 |
Spur | -0.062 |
Token | supplied |
Token ID | 14275 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
smoot | +0.121 |
fres | +0.114 |
ans | +0.112 |
Pac | +0.110 |
Spur | +0.108 |
Neg logit contributions | |
)", | -0.149 |
uyomi | -0.130 |
ingo | -0.129 |
glers | -0.129 |
emale | -0.125 |
Token | power |
Token ID | 1176 |
Feature activation | -6.21e-04 |
Pos logit contributions | |
)", | +0.025 |
uyomi | +0.022 |
ingo | +0.022 |
glers | +0.021 |
emale | +0.021 |
Neg logit contributions | |
smoot | -0.021 |
fres | -0.020 |
ans | -0.019 |
Pac | -0.019 |
Spur | -0.019 |
Token | plants |
Token ID | 6134 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
smoot | +0.000 |
fres | +0.000 |
ans | +0.000 |
Pac | +0.000 |
Spur | +0.000 |
Neg logit contributions | |
)", | -0.001 |
ingo | -0.000 |
uyomi | -0.000 |
glers | -0.000 |
harm | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
smoot | +0.896 |
fres | +0.844 |
ans | +0.828 |
Pac | +0.813 |
Spur | +0.798 |
Neg logit contributions | |
)", | -1.124 |
uyomi | -0.980 |
ingo | -0.974 |
glers | -0.970 |
emale | -0.947 |
Token | as |
Token ID | 355 |
Feature activation | -9.17e-03 |
Pos logit contributions | |
)", | +0.013 |
ingo | +0.011 |
uyomi | +0.011 |
glers | +0.011 |
emale | +0.011 |
Neg logit contributions | |
smoot | -0.011 |
fres | -0.011 |
ans | -0.010 |
Pac | -0.010 |
Spur | -0.010 |
Token | estimated |
Token ID | 6108 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
smoot | +0.006 |
fres | +0.005 |
ans | +0.005 |
Pac | +0.005 |
chev | +0.005 |
Neg logit contributions | |
)", | -0.008 |
uyomi | -0.007 |
ingo | -0.007 |
glers | -0.007 |
harm | -0.007 |
Token | by |
Token ID | 416 |
Feature activation | +6.66e-02 |
Pos logit contributions | |
)", | +0.195 |
uyomi | +0.168 |
ingo | +0.168 |
glers | +0.167 |
harm | +0.163 |
Neg logit contributions | |
smoot | -0.166 |
fres | -0.156 |
ans | -0.154 |
Pac | -0.153 |
Spur | -0.149 |
Token | I |
Token ID | 314 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
)", | +0.058 |
uyomi | +0.051 |
ingo | +0.051 |
glers | +0.050 |
harm | +0.049 |
Neg logit contributions | |
smoot | -0.041 |
fres | -0.039 |
ans | -0.038 |
Pac | -0.038 |
Spur | -0.037 |
Token | are |
Token ID | 389 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
)", | +0.120 |
uyomi | +0.103 |
ingo | +0.103 |
glers | +0.102 |
emale | +0.099 |
Neg logit contributions | |
smoot | -0.118 |
fres | -0.112 |
ans | -0.110 |
Pac | -0.108 |
Spur | -0.107 |
Token | Here |
Token ID | 3423 |
Feature activation | +9.78e-02 |
Pos logit contributions | |
)", | +0.010 |
ingo | +0.009 |
uyomi | +0.009 |
glers | +0.009 |
harm | +0.008 |
Neg logit contributions | |
smoot | -0.006 |
fres | -0.006 |
ans | -0.006 |
Pac | -0.005 |
Spur | -0.005 |
Token | .... |
Token ID | 1106 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
)", | +0.072 |
uyomi | +0.062 |
ingo | +0.061 |
glers | +0.061 |
emale | +0.059 |
Neg logit contributions | |
smoot | -0.075 |
fres | -0.071 |
ans | -0.070 |
Pac | -0.068 |
Spur | -0.068 |
Token |
|
Token ID | 198 |
Feature activation | +6.20e-03 |
Pos logit contributions | |
smoot | +0.070 |
fres | +0.066 |
ans | +0.065 |
Pac | +0.063 |
Spur | +0.062 |
Neg logit contributions | |
)", | -0.100 |
uyomi | -0.088 |
ingo | -0.087 |
glers | -0.087 |
emale | -0.085 |
Token |
|
Token ID | 198 |
Feature activation | +4.39e-02 |
Pos logit contributions | |
)", | +0.005 |
ingo | +0.005 |
glers | +0.005 |
uyomi | +0.005 |
harm | +0.004 |
Neg logit contributions | |
smoot | -0.004 |
fres | -0.004 |
ans | -0.004 |
Pac | -0.004 |
Spur | -0.004 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
)", | +0.041 |
ingo | +0.037 |
uyomi | +0.037 |
glers | +0.036 |
harm | +0.036 |
Neg logit contributions | |
smoot | -0.025 |
fres | -0.023 |
ans | -0.022 |
Pac | -0.022 |
Spur | -0.021 |
Token | : |
Token ID | 25 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
smoot | +0.698 |
fres | +0.645 |
ans | +0.627 |
Pac | +0.610 |
Spur | +0.598 |
Neg logit contributions | |
)", | -1.313 |
uyomi | -1.165 |
ingo | -1.161 |
glers | -1.158 |
harm | -1.130 |
Token | SAS |
Token ID | 35516 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
)", | +0.143 |
uyomi | +0.124 |
ingo | +0.123 |
glers | +0.122 |
emale | +0.120 |
Neg logit contributions | |
smoot | -0.122 |
fres | -0.115 |
ans | -0.113 |
Pac | -0.111 |
chev | -0.109 |
Token | K |
Token ID | 42 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
smoot | +0.010 |
fres | +0.009 |
ans | +0.009 |
Pac | +0.009 |
Fedora | +0.009 |
Neg logit contributions | |
)", | -0.011 |
ingo | -0.009 |
uyomi | -0.009 |
glers | -0.009 |
emale | -0.009 |
Token | ATCH |
Token ID | 11417 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
smoot | +0.173 |
fres | +0.163 |
ans | +0.158 |
Pac | +0.157 |
Spur | +0.155 |
Neg logit contributions | |
)", | -0.185 |
ingo | -0.160 |
uyomi | -0.160 |
glers | -0.158 |
emale | -0.155 |
Token | EW |
Token ID | 6217 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
)", | +0.056 |
ingo | +0.048 |
uyomi | +0.047 |
glers | +0.047 |
emale | +0.046 |
Neg logit contributions | |
smoot | -0.058 |
fres | -0.055 |
ans | -0.053 |
Pac | -0.052 |
Spur | -0.052 |
Token | team |
Token ID | 1074 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
)", | +0.027 |
glers | +0.024 |
ingo | +0.024 |
uyomi | +0.024 |
emale | +0.023 |
Neg logit contributions | |
smoot | -0.019 |
fres | -0.017 |
ans | -0.017 |
Pac | -0.017 |
chev | -0.017 |
Token | ๏ฟฝ |
Token ID | 447 |
Feature activation | -5.34e-02 |
Pos logit contributions | |
smoot | +0.013 |
fres | +0.012 |
ans | +0.012 |
Pac | +0.012 |
chev | +0.012 |
Neg logit contributions | |
)", | -0.017 |
ingo | -0.015 |
uyomi | -0.015 |
glers | -0.015 |
emale | -0.015 |
Token | ๏ฟฝ |
Token ID | 247 |
Feature activation | +9.31e-02 |
Pos logit contributions | |
smoot | +0.039 |
fres | +0.037 |
ans | +0.036 |
Pac | +0.036 |
Spur | +0.035 |
Neg logit contributions | |
)", | -0.041 |
uyomi | -0.035 |
ingo | -0.035 |
glers | -0.035 |
emale | -0.034 |
Token | s |
Token ID | 82 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
)", | +0.081 |
ingo | +0.071 |
glers | +0.070 |
uyomi | +0.070 |
emale | +0.069 |
Neg logit contributions | |
smoot | -0.058 |
fres | -0.054 |
ans | -0.053 |
Pac | -0.052 |
Fedora | -0.052 |
Token | third |
Token ID | 2368 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
smoot | +0.076 |
fres | +0.071 |
ans | +0.070 |
Pac | +0.069 |
chev | +0.068 |
Neg logit contributions | |
)", | -0.117 |
ingo | -0.103 |
uyomi | -0.102 |
glers | -0.102 |
emale | -0.100 |
Token | straight |
Token ID | 3892 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
smoot | +0.163 |
fres | +0.154 |
ans | +0.152 |
Pac | +0.149 |
chev | +0.146 |
Neg logit contributions | |
)", | -0.196 |
ingo | -0.169 |
uyomi | -0.169 |
glers | -0.168 |
emale | -0.164 |
Token | in |
Token ID | 287 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
smoot | +0.976 |
fres | +0.924 |
ans | +0.909 |
Pac | +0.891 |
Spur | +0.877 |
Neg logit contributions | |
)", | -1.019 |
uyomi | -0.876 |
ingo | -0.870 |
glers | -0.867 |
emale | -0.845 |
Token | pads |
Token ID | 21226 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
smoot | +0.076 |
fres | +0.072 |
ans | +0.070 |
Pac | +0.069 |
Spur | +0.067 |
Neg logit contributions | |
)", | -0.098 |
uyomi | -0.085 |
ingo | -0.085 |
glers | -0.085 |
emale | -0.083 |
Token | , |
Token ID | 11 |
Feature activation | -9.42e-02 |
Pos logit contributions | |
smoot | +0.275 |
fres | +0.260 |
ans | +0.255 |
Pac | +0.250 |
Spur | +0.246 |
Neg logit contributions | |
)", | -0.344 |
uyomi | -0.300 |
ingo | -0.298 |
glers | -0.298 |
emale | -0.290 |
Token | that |
Token ID | 326 |
Feature activation | -6.29e-02 |
Pos logit contributions | |
smoot | +0.062 |
fres | +0.059 |
ans | +0.058 |
Pac | +0.057 |
chev | +0.056 |
Neg logit contributions | |
)", | -0.078 |
glers | -0.067 |
uyomi | -0.067 |
ingo | -0.067 |
emale | -0.065 |
Token | focused |
Token ID | 5670 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
smoot | +0.039 |
fres | +0.037 |
ans | +0.037 |
Pac | +0.036 |
chev | +0.036 |
Neg logit contributions | |
)", | -0.054 |
glers | -0.047 |
ingo | -0.047 |
uyomi | -0.047 |
adolesc | -0.045 |
Token | a |
Token ID | 64 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
smoot | +0.069 |
fres | +0.064 |
ans | +0.061 |
Fedora | +0.061 |
Pac | +0.061 |
Neg logit contributions | |
)", | -0.097 |
ingo | -0.086 |
glers | -0.085 |
uyomi | -0.084 |
harm | -0.084 |
Token | hee |
Token ID | 21067 |
Feature activation | -6.98e-02 |
Pos logit contributions | |
)", | +0.074 |
ingo | +0.061 |
uyomi | +0.061 |
glers | +0.060 |
emale | +0.058 |
Neg logit contributions | |
smoot | -0.102 |
fres | -0.097 |
ans | -0.096 |
Pac | -0.094 |
Spur | -0.094 |
Token | III |
Token ID | 6711 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
smoot | +0.050 |
fres | +0.047 |
ans | +0.046 |
Pac | +0.045 |
Spur | +0.045 |
Neg logit contributions | |
)", | -0.055 |
uyomi | -0.047 |
ingo | -0.047 |
glers | -0.047 |
emale | -0.046 |
Token | / |
Token ID | 14 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
smoot | +0.073 |
fres | +0.069 |
ans | +0.068 |
Pac | +0.067 |
Spur | +0.066 |
Neg logit contributions | |
)", | -0.078 |
uyomi | -0.067 |
ingo | -0.067 |
glers | -0.066 |
emale | -0.065 |
Token | Dem |
Token ID | 11522 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
)", | +0.025 |
uyomi | +0.022 |
ingo | +0.021 |
glers | +0.021 |
harm | +0.021 |
Neg logit contributions | |
smoot | -0.026 |
fres | -0.025 |
ans | -0.024 |
Pac | -0.023 |
Fedora | -0.023 |
Token | ocrat |
Token ID | 35128 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
)", | +0.093 |
ingo | +0.081 |
uyomi | +0.080 |
glers | +0.079 |
emale | +0.078 |
Neg logit contributions | |
smoot | -0.087 |
fres | -0.082 |
ans | -0.080 |
Pac | -0.079 |
Spur | -0.078 |
Token | ) |
Token ID | 8 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
smoot | +1.094 |
fres | +1.042 |
ans | +1.030 |
Pac | +1.010 |
Spur | +0.996 |
Neg logit contributions | |
)", | -0.896 |
uyomi | -0.761 |
glers | -0.753 |
ingo | -0.746 |
emale | -0.729 |
Token | Buy |
Token ID | 14518 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
smoot | +0.009 |
fres | +0.008 |
ans | +0.008 |
Pac | +0.008 |
Spur | +0.008 |
Neg logit contributions | |
)", | -0.010 |
uyomi | -0.009 |
ingo | -0.009 |
glers | -0.009 |
emale | -0.009 |
Token | Photo |
Token ID | 5555 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
smoot | +0.234 |
fres | +0.220 |
ans | +0.215 |
Pac | +0.209 |
chev | +0.206 |
Neg logit contributions | |
)", | -0.302 |
uyomi | -0.262 |
ingo | -0.260 |
glers | -0.260 |
harm | -0.252 |
Token |
|
Token ID | 198 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
)", | +0.128 |
uyomi | +0.112 |
ingo | +0.111 |
glers | +0.110 |
emale | +0.108 |
Neg logit contributions | |
smoot | -0.098 |
fres | -0.092 |
ans | -0.090 |
Pac | -0.088 |
chev | -0.086 |
Token |
|
Token ID | 198 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
)", | +0.014 |
uyomi | +0.012 |
ingo | +0.012 |
glers | +0.012 |
harm | +0.012 |
Neg logit contributions | |
smoot | -0.010 |
fres | -0.010 |
ans | -0.009 |
Pac | -0.009 |
Spur | -0.009 |
Token | wan |
Token ID | 8149 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
smoot | +0.168 |
fres | +0.156 |
ans | +0.151 |
Pac | +0.149 |
Spur | +0.146 |
Neg logit contributions | |
)", | -0.278 |
uyomi | -0.246 |
ingo | -0.245 |
glers | -0.244 |
emale | -0.240 |
Token | and |
Token ID | 290 |
Feature activation | -8.42e-02 |
Pos logit contributions | |
)", | +0.510 |
uyomi | +0.439 |
ingo | +0.437 |
harm | +0.429 |
glers | +0.428 |
Neg logit contributions | |
smoot | -0.443 |
fres | -0.417 |
ans | -0.402 |
Pac | -0.402 |
Fedora | -0.391 |
Token | BJP |
Token ID | 18317 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
smoot | +0.057 |
fres | +0.053 |
ans | +0.053 |
Pac | +0.052 |
chev | +0.051 |
Neg logit contributions | |
)", | -0.070 |
ingo | -0.060 |
uyomi | -0.060 |
glers | -0.059 |
harm | -0.058 |
Token | Raj |
Token ID | 13308 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
smoot | +0.084 |
fres | +0.079 |
ans | +0.077 |
Pac | +0.076 |
chev | +0.075 |
Neg logit contributions | |
)", | -0.105 |
uyomi | -0.090 |
ingo | -0.090 |
glers | -0.089 |
emale | -0.087 |
Token | ya |
Token ID | 3972 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
smoot | +0.206 |
fres | +0.195 |
ans | +0.190 |
Pac | +0.187 |
Spur | +0.186 |
Neg logit contributions | |
)", | -0.216 |
ingo | -0.185 |
uyomi | -0.185 |
glers | -0.182 |
emale | -0.180 |
Token | Sabha |
Token ID | 41941 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
smoot | +0.084 |
fres | +0.077 |
ans | +0.073 |
Pac | +0.073 |
scoop | +0.071 |
Neg logit contributions | |
)", | -0.156 |
ingo | -0.137 |
uyomi | -0.136 |
glers | -0.135 |
emale | -0.135 |
Token | member |
Token ID | 2888 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
smoot | +0.867 |
fres | +0.814 |
ans | +0.798 |
Pac | +0.784 |
Spur | +0.768 |
Neg logit contributions | |
)", | -1.120 |
uyomi | -0.974 |
ingo | -0.968 |
glers | -0.964 |
emale | -0.945 |
Token | from |
Token ID | 422 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
smoot | +0.331 |
fres | +0.312 |
ans | +0.305 |
Pac | +0.300 |
chev | +0.294 |
Neg logit contributions | |
)", | -0.406 |
uyomi | -0.351 |
ingo | -0.347 |
glers | -0.346 |
harm | -0.340 |
Token | Gujarat |
Token ID | 30311 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
smoot | +0.138 |
fres | +0.129 |
ans | +0.127 |
Pac | +0.124 |
Spur | +0.121 |
Neg logit contributions | |
)", | -0.196 |
uyomi | -0.171 |
ingo | -0.170 |
glers | -0.169 |
emale | -0.166 |
Token | Shank |
Token ID | 41595 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
smoot | +0.019 |
fres | +0.018 |
ans | +0.017 |
Pac | +0.017 |
chev | +0.017 |
Neg logit contributions | |
)", | -0.022 |
uyomi | -0.019 |
ingo | -0.019 |
glers | -0.019 |
harm | -0.019 |
Token | ar |
Token ID | 283 |
Feature activation | -7.16e-02 |
Pos logit contributions | |
)", | +0.166 |
uyomi | +0.141 |
ingo | +0.139 |
glers | +0.138 |
emale | +0.134 |
Neg logit contributions | |
smoot | -0.194 |
fres | -0.185 |
ans | -0.179 |
Pac | -0.177 |
Spur | -0.175 |
Token | next |
Token ID | 1306 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
smoot | +0.060 |
fres | +0.056 |
ans | +0.056 |
Pac | +0.055 |
Spur | +0.054 |
Neg logit contributions | |
)", | -0.074 |
glers | -0.064 |
ingo | -0.064 |
uyomi | -0.064 |
harm | -0.062 |
Token | year |
Token ID | 614 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
smoot | +0.148 |
fres | +0.138 |
ans | +0.137 |
Pac | +0.133 |
Spur | +0.130 |
Neg logit contributions | |
)", | -0.240 |
glers | -0.211 |
ingo | -0.211 |
uyomi | -0.211 |
harm | -0.204 |
Token | . |
Token ID | 13 |
Feature activation | +6.14e-02 |
Pos logit contributions | |
smoot | +0.087 |
fres | +0.082 |
ans | +0.081 |
Pac | +0.079 |
Spur | +0.078 |
Neg logit contributions | |
)", | -0.096 |
uyomi | -0.084 |
ingo | -0.083 |
glers | -0.083 |
emale | -0.080 |
Token | La |
Token ID | 4689 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
)", | +0.050 |
glers | +0.043 |
ingo | +0.043 |
uyomi | +0.042 |
Militia | +0.041 |
Neg logit contributions | |
smoot | -0.043 |
fres | -0.040 |
ans | -0.039 |
Pac | -0.038 |
bolted | -0.038 |
Token | R |
Token ID | 49 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
)", | +0.185 |
ingo | +0.159 |
uyomi | +0.157 |
glers | +0.156 |
emale | +0.152 |
Neg logit contributions | |
smoot | -0.178 |
fres | -0.168 |
ans | -0.166 |
Pac | -0.162 |
Spur | -0.161 |
Token | oche |
Token ID | 30848 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
smoot | +0.096 |
fres | +0.089 |
ans | +0.086 |
Pac | +0.085 |
Spur | +0.084 |
Neg logit contributions | |
)", | -0.131 |
ingo | -0.116 |
uyomi | -0.114 |
glers | -0.114 |
emale | -0.111 |
Token | is |
Token ID | 318 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
smoot | +0.759 |
fres | +0.709 |
ans | +0.690 |
Pac | +0.677 |
Spur | +0.668 |
Neg logit contributions | |
)", | -1.194 |
ingo | -1.056 |
uyomi | -1.052 |
glers | -1.052 |
emale | -1.021 |
Token | a |
Token ID | 257 |
Feature activation | -9.46e-02 |
Pos logit contributions | |
smoot | +0.108 |
fres | +0.101 |
ans | +0.100 |
Pac | +0.098 |
chev | +0.097 |
Neg logit contributions | |
)", | -0.137 |
ingo | -0.118 |
glers | -0.118 |
uyomi | -0.117 |
harm | -0.114 |
Token | free |
Token ID | 1479 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
smoot | +0.059 |
fres | +0.055 |
ans | +0.055 |
Pac | +0.053 |
chev | +0.052 |
Neg logit contributions | |
)", | -0.083 |
ingo | -0.072 |
glers | -0.072 |
uyomi | -0.072 |
emale | -0.070 |
Token | agent |
Token ID | 5797 |
Feature activation | -6.04e-02 |
Pos logit contributions | |
)", | +0.106 |
ingo | +0.091 |
glers | +0.090 |
uyomi | +0.089 |
harm | +0.088 |
Neg logit contributions | |
smoot | -0.109 |
fres | -0.103 |
ans | -0.101 |
Pac | -0.101 |
Spur | -0.099 |
Token | , |
Token ID | 11 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
smoot | +0.042 |
fres | +0.040 |
ans | +0.039 |
Pac | +0.039 |
Spur | +0.038 |
Neg logit contributions | |
)", | -0.048 |
glers | -0.041 |
ingo | -0.041 |
uyomi | -0.041 |
emale | -0.040 |
Token | venture |
Token ID | 5388 |
Feature activation | -7.20e-03 |
Pos logit contributions | |
)", | +0.258 |
ingo | +0.221 |
uyomi | +0.220 |
glers | +0.219 |
harm | +0.213 |
Neg logit contributions | |
smoot | -0.257 |
fres | -0.243 |
ans | -0.233 |
Pac | -0.233 |
Spur | -0.232 |
Token | backers |
Token ID | 18917 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
smoot | +0.003 |
fres | +0.003 |
ans | +0.003 |
Pac | +0.003 |
Spur | +0.003 |
Neg logit contributions | |
)", | -0.008 |
uyomi | -0.007 |
ingo | -0.007 |
glers | -0.007 |
emale | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -4.13e-02 |
Pos logit contributions | |
smoot | +0.133 |
fres | +0.124 |
ans | +0.123 |
Pac | +0.121 |
chev | +0.118 |
Neg logit contributions | |
)", | -0.181 |
ingo | -0.157 |
uyomi | -0.157 |
glers | -0.156 |
emale | -0.152 |
Token | Steam |
Token ID | 9094 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
smoot | +0.027 |
ans | +0.025 |
fres | +0.025 |
Pac | +0.025 |
chev | +0.024 |
Neg logit contributions | |
)", | -0.035 |
ingo | -0.030 |
uyomi | -0.030 |
glers | -0.030 |
emale | -0.029 |
Token | Early |
Token ID | 12556 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
smoot | +0.089 |
fres | +0.081 |
ans | +0.079 |
Pac | +0.077 |
chev | +0.074 |
Neg logit contributions | |
)", | -0.203 |
uyomi | -0.181 |
ingo | -0.180 |
glers | -0.179 |
harm | -0.176 |
Token | Access |
Token ID | 8798 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
smoot | +0.202 |
fres | +0.184 |
ans | +0.177 |
Pac | +0.171 |
Spur | +0.167 |
Neg logit contributions | |
)", | -0.497 |
uyomi | -0.445 |
ingo | -0.444 |
glers | -0.441 |
emale | -0.435 |
Token | key |
Token ID | 1994 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
smoot | +0.674 |
fres | +0.622 |
ans | +0.608 |
Pac | +0.594 |
Spur | +0.578 |
Neg logit contributions | |
)", | -1.279 |
uyomi | -1.134 |
ingo | -1.134 |
glers | -1.123 |
emale | -1.108 |
Token | for |
Token ID | 329 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
)", | +0.107 |
uyomi | +0.092 |
ingo | +0.092 |
glers | +0.091 |
emale | +0.089 |
Neg logit contributions | |
smoot | -0.091 |
fres | -0.086 |
ans | -0.085 |
Pac | -0.084 |
Spur | -0.082 |
Token | T |
Token ID | 309 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
)", | +0.036 |
ingo | +0.031 |
uyomi | +0.031 |
glers | +0.031 |
harm | +0.030 |
Neg logit contributions | |
smoot | -0.022 |
fres | -0.021 |
ans | -0.020 |
Pac | -0.020 |
chev | -0.020 |
Token | UG |
Token ID | 7340 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
)", | +0.026 |
ingo | +0.023 |
uyomi | +0.023 |
glers | +0.022 |
emale | +0.022 |
Neg logit contributions | |
smoot | -0.025 |
fres | -0.024 |
ans | -0.023 |
Pac | -0.023 |
Spur | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | -7.22e-02 |
Pos logit contributions | |
smoot | +0.204 |
fres | +0.193 |
ans | +0.189 |
Pac | +0.186 |
Spur | +0.183 |
Neg logit contributions | |
)", | -0.235 |
uyomi | -0.204 |
ingo | -0.204 |
glers | -0.202 |
emale | -0.197 |
Token | machine |
Token ID | 4572 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
smoot | +0.145 |
fres | +0.136 |
ans | +0.133 |
Pac | +0.131 |
chev | +0.129 |
Neg logit contributions | |
)", | -0.210 |
uyomi | -0.185 |
ingo | -0.184 |
glers | -0.183 |
emale | -0.178 |
Token | is |
Token ID | 318 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
smoot | +0.280 |
fres | +0.260 |
ans | +0.253 |
Pac | +0.249 |
Spur | +0.243 |
Neg logit contributions | |
)", | -0.514 |
uyomi | -0.457 |
ingo | -0.456 |
glers | -0.454 |
harm | -0.441 |
Token | to |
Token ID | 284 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
smoot | +0.123 |
fres | +0.118 |
ans | +0.115 |
Pac | +0.114 |
Spur | +0.112 |
Neg logit contributions | |
)", | -0.149 |
ingo | -0.129 |
uyomi | -0.129 |
glers | -0.129 |
harm | -0.125 |
Token | sew |
Token ID | 34249 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
smoot | +0.081 |
fres | +0.077 |
ans | +0.076 |
Pac | +0.075 |
Spur | +0.073 |
Neg logit contributions | |
)", | -0.106 |
ingo | -0.092 |
uyomi | -0.092 |
glers | -0.091 |
harm | -0.089 |
Token | a |
Token ID | 257 |
Feature activation | -7.90e-02 |
Pos logit contributions | |
smoot | +0.142 |
fres | +0.137 |
ans | +0.133 |
Pac | +0.132 |
chev | +0.129 |
Neg logit contributions | |
)", | -0.183 |
ingo | -0.159 |
glers | -0.158 |
uyomi | -0.158 |
harm | -0.154 |
Token | straight |
Token ID | 3892 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
smoot | +0.051 |
fres | +0.049 |
ans | +0.048 |
Pac | +0.047 |
chev | +0.046 |
Neg logit contributions | |
)", | -0.067 |
ingo | -0.058 |
uyomi | -0.058 |
glers | -0.057 |
harm | -0.056 |
Token | seam |
Token ID | 15787 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
smoot | +0.779 |
fres | +0.732 |
ans | +0.714 |
Pac | +0.701 |
Spur | +0.686 |
Neg logit contributions | |
)", | -1.159 |
uyomi | -1.017 |
ingo | -1.013 |
glers | -1.008 |
emale | -0.985 |
Token | . |
Token ID | 13 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
smoot | +0.076 |
fres | +0.073 |
ans | +0.071 |
Pac | +0.070 |
Spur | +0.069 |
Neg logit contributions | |
)", | -0.088 |
ingo | -0.077 |
uyomi | -0.076 |
glers | -0.076 |
harm | -0.074 |
Token | To |
Token ID | 1675 |
Feature activation | -6.20e-02 |
Pos logit contributions | |
)", | +0.020 |
ingo | +0.018 |
uyomi | +0.018 |
glers | +0.017 |
harm | +0.017 |
Neg logit contributions | |
smoot | -0.018 |
fres | -0.017 |
ans | -0.017 |
Pac | -0.016 |
chev | -0.016 |
Token | practice |
Token ID | 3357 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
smoot | +0.043 |
fres | +0.041 |
ans | +0.040 |
Pac | +0.040 |
Spur | +0.039 |
Neg logit contributions | |
)", | -0.049 |
ingo | -0.043 |
uyomi | -0.043 |
glers | -0.042 |
harm | -0.041 |
Token | sewing |
Token ID | 35356 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
smoot | +0.104 |
fres | +0.099 |
ans | +0.097 |
Pac | +0.095 |
Spur | +0.093 |
Neg logit contributions | |
)", | -0.136 |
ingo | -0.119 |
uyomi | -0.118 |
glers | -0.118 |
emale | -0.114 |
Token | , |
Token ID | 11 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
)", | +0.126 |
uyomi | +0.109 |
ingo | +0.108 |
glers | +0.108 |
emale | +0.105 |
Neg logit contributions | |
smoot | -0.106 |
fres | -0.100 |
ans | -0.098 |
Pac | -0.097 |
Spur | -0.095 |
Token | electricity |
Token ID | 8744 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
)", | +0.138 |
ingo | +0.119 |
uyomi | +0.119 |
glers | +0.118 |
harm | +0.115 |
Neg logit contributions | |
smoot | -0.109 |
fres | -0.102 |
ans | -0.101 |
Pac | -0.100 |
Spur | -0.097 |
Token | from |
Token ID | 422 |
Feature activation | +5.36e-02 |
Pos logit contributions | |
smoot | +0.063 |
fres | +0.059 |
ans | +0.058 |
Pac | +0.057 |
Spur | +0.056 |
Neg logit contributions | |
)", | -0.089 |
ingo | -0.078 |
uyomi | -0.078 |
glers | -0.077 |
harm | -0.076 |
Token | these |
Token ID | 777 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
)", | +0.041 |
ingo | +0.035 |
uyomi | +0.035 |
glers | +0.035 |
harm | +0.034 |
Neg logit contributions | |
smoot | -0.039 |
fres | -0.037 |
ans | -0.036 |
Pac | -0.036 |
chev | -0.035 |
Token | power |
Token ID | 1176 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
smoot | +0.098 |
fres | +0.092 |
ans | +0.090 |
Pac | +0.089 |
Spur | +0.087 |
Neg logit contributions | |
)", | -0.137 |
ingo | -0.119 |
uyomi | -0.119 |
glers | -0.118 |
emale | -0.115 |
Token | plants |
Token ID | 6134 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
)", | +0.106 |
ingo | +0.092 |
uyomi | +0.091 |
glers | +0.091 |
harm | +0.089 |
Neg logit contributions | |
smoot | -0.079 |
fres | -0.074 |
ans | -0.072 |
Pac | -0.071 |
Spur | -0.070 |
Token | will |
Token ID | 481 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
smoot | +0.818 |
fres | +0.768 |
ans | +0.753 |
Pac | +0.740 |
Spur | +0.728 |
Neg logit contributions | |
)", | -1.110 |
uyomi | -0.969 |
ingo | -0.969 |
glers | -0.963 |
emale | -0.942 |
Token | cost |
Token ID | 1575 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
smoot | +0.022 |
fres | +0.021 |
ans | +0.021 |
Pac | +0.020 |
Spur | +0.020 |
Neg logit contributions | |
)", | -0.026 |
uyomi | -0.023 |
ingo | -0.023 |
glers | -0.023 |
harm | -0.022 |
Token | 18 |
Token ID | 1248 |
Feature activation | -6.94e-02 |
Pos logit contributions | |
)", | +0.141 |
ingo | +0.124 |
glers | +0.123 |
uyomi | +0.122 |
harm | +0.120 |
Neg logit contributions | |
smoot | -0.097 |
fres | -0.090 |
ans | -0.088 |
Pac | -0.088 |
Spur | -0.086 |
Token | to |
Token ID | 284 |
Feature activation | -8.10e-02 |
Pos logit contributions | |
smoot | +0.033 |
fres | +0.030 |
ans | +0.029 |
Pac | +0.028 |
Spur | +0.028 |
Neg logit contributions | |
)", | -0.071 |
ingo | -0.063 |
uyomi | -0.063 |
glers | -0.063 |
harm | -0.062 |
Token | 50 |
Token ID | 2026 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
smoot | +0.056 |
fres | +0.053 |
ans | +0.052 |
Pac | +0.051 |
chev | +0.050 |
Neg logit contributions | |
)", | -0.065 |
ingo | -0.056 |
glers | -0.056 |
uyomi | -0.055 |
harm | -0.054 |
Token | the |
Token ID | 262 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
smoot | +0.073 |
fres | +0.068 |
ans | +0.068 |
Pac | +0.066 |
chev | +0.065 |
Neg logit contributions | |
)", | -0.098 |
uyomi | -0.085 |
ingo | -0.085 |
glers | -0.084 |
emale | -0.082 |
Token | Greek |
Token ID | 8312 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
smoot | +0.181 |
fres | +0.169 |
ans | +0.167 |
Pac | +0.164 |
chev | +0.161 |
Neg logit contributions | |
)", | -0.230 |
uyomi | -0.200 |
ingo | -0.199 |
glers | -0.198 |
emale | -0.193 |
Token | historian |
Token ID | 18026 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
smoot | +0.253 |
fres | +0.238 |
ans | +0.234 |
Pac | +0.230 |
Spur | +0.226 |
Neg logit contributions | |
)", | -0.297 |
uyomi | -0.258 |
ingo | -0.255 |
glers | -0.254 |
emale | -0.248 |
Token | Herod |
Token ID | 48084 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
smoot | +0.524 |
fres | +0.494 |
ans | +0.486 |
Pac | +0.477 |
Spur | +0.469 |
Neg logit contributions | |
)", | -0.603 |
uyomi | -0.522 |
ingo | -0.518 |
glers | -0.517 |
emale | -0.504 |
Token | ot |
Token ID | 313 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
smoot | +0.206 |
fres | +0.189 |
ans | +0.183 |
Pac | +0.179 |
Spur | +0.175 |
Neg logit contributions | |
)", | -0.426 |
uyomi | -0.381 |
ingo | -0.379 |
glers | -0.376 |
harm | -0.370 |
Token | us |
Token ID | 385 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
smoot | +0.248 |
fres | +0.233 |
ans | +0.227 |
Pac | +0.224 |
Spur | +0.221 |
Neg logit contributions | |
)", | -0.309 |
uyomi | -0.269 |
ingo | -0.267 |
glers | -0.266 |
emale | -0.261 |
Token | begins |
Token ID | 6140 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
smoot | +0.856 |
fres | +0.803 |
ans | +0.792 |
Pac | +0.784 |
Spur | +0.765 |
Neg logit contributions | |
)", | -1.060 |
ingo | -0.917 |
uyomi | -0.915 |
glers | -0.907 |
emale | -0.886 |
Token | the |
Token ID | 262 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
)", | +0.019 |
uyomi | +0.017 |
ingo | +0.017 |
glers | +0.017 |
emale | +0.016 |
Neg logit contributions | |
smoot | -0.014 |
fres | -0.013 |
ans | -0.013 |
Pac | -0.013 |
chev | -0.012 |
Token | Australian |
Token ID | 6638 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
smoot | +0.273 |
fres | +0.258 |
ans | +0.256 |
Pac | +0.253 |
chev | +0.247 |
Neg logit contributions | |
)", | -0.288 |
uyomi | -0.247 |
ingo | -0.246 |
glers | -0.245 |
emale | -0.237 |
Token | Alan |
Token ID | 12246 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
)", | +0.082 |
uyomi | +0.070 |
ingo | +0.069 |
glers | +0.069 |
emale | +0.067 |
Neg logit contributions | |
smoot | -0.083 |
fres | -0.079 |
ans | -0.077 |
Pac | -0.076 |
Spur | -0.075 |
Token | Moore |
Token ID | 8877 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
smoot | +0.209 |
fres | +0.197 |
ans | +0.193 |
Pac | +0.189 |
Fedora | +0.185 |
Neg logit contributions | |
)", | -0.248 |
ingo | -0.215 |
uyomi | -0.215 |
glers | -0.213 |
emale | -0.208 |
Token | approve |
Token ID | 14762 |
Feature activation | -6.66e-02 |
Pos logit contributions | |
smoot | +0.026 |
fres | +0.025 |
ans | +0.024 |
Pac | +0.024 |
Spur | +0.024 |
Neg logit contributions | |
)", | -0.028 |
uyomi | -0.024 |
ingo | -0.024 |
glers | -0.024 |
harm | -0.023 |
Token | its |
Token ID | 663 |
Feature activation | +7.41e-02 |
Pos logit contributions | |
smoot | +0.046 |
fres | +0.044 |
ans | +0.043 |
Pac | +0.043 |
Spur | +0.042 |
Neg logit contributions | |
)", | -0.053 |
uyomi | -0.046 |
ingo | -0.046 |
glers | -0.046 |
emale | -0.045 |
Token | connection |
Token ID | 4637 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
)", | +0.065 |
ingo | +0.057 |
uyomi | +0.057 |
glers | +0.056 |
emale | +0.055 |
Neg logit contributions | |
smoot | -0.046 |
fres | -0.043 |
ans | -0.042 |
Pac | -0.042 |
Spur | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
)", | +0.189 |
uyomi | +0.165 |
ingo | +0.164 |
glers | +0.163 |
emale | +0.159 |
Neg logit contributions | |
smoot | -0.164 |
fres | -0.156 |
ans | -0.153 |
Pac | -0.150 |
Spur | -0.147 |
Token | 3 |
Token ID | 513 |
Feature activation | -6.83e-02 |
Pos logit contributions | |
)", | +0.009 |
ingo | +0.007 |
glers | +0.007 |
uyomi | +0.007 |
harm | +0.007 |
Neg logit contributions | |
smoot | -0.008 |
fres | -0.008 |
ans | -0.007 |
Pac | -0.007 |
Spur | -0.007 |
Token | D |
Token ID | 35 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
smoot | +0.057 |
fres | +0.055 |
ans | +0.054 |
Pac | +0.053 |
Spur | +0.052 |
Neg logit contributions | |
)", | -0.045 |
ingo | -0.038 |
uyomi | -0.038 |
glers | -0.037 |
emale | -0.036 |
Token | Gallery |
Token ID | 12917 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
smoot | +1.087 |
fres | +1.034 |
ans | +1.022 |
Pac | +1.011 |
Spur | +0.997 |
Neg logit contributions | |
)", | -0.815 |
ingo | -0.681 |
uyomi | -0.681 |
glers | -0.674 |
emale | -0.652 |
Token | also |
Token ID | 635 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
smoot | +0.135 |
fres | +0.128 |
ans | +0.126 |
Pac | +0.125 |
Spur | +0.123 |
Neg logit contributions | |
)", | -0.170 |
ingo | -0.149 |
glers | -0.147 |
uyomi | -0.147 |
emale | -0.143 |
Token | makes |
Token ID | 1838 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
smoot | +0.065 |
fres | +0.061 |
ans | +0.061 |
Pac | +0.060 |
Spur | +0.059 |
Neg logit contributions | |
)", | -0.091 |
ingo | -0.080 |
glers | -0.080 |
uyomi | -0.079 |
emale | -0.077 |
Token | short |
Token ID | 1790 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
smoot | +0.165 |
fres | +0.156 |
ans | +0.153 |
Pac | +0.151 |
Spur | +0.148 |
Neg logit contributions | |
)", | -0.201 |
uyomi | -0.175 |
ingo | -0.174 |
glers | -0.173 |
emale | -0.169 |
Token | work |
Token ID | 670 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
smoot | +0.280 |
fres | +0.263 |
ans | +0.258 |
Pac | +0.252 |
Spur | +0.248 |
Neg logit contributions | |
)", | -0.369 |
uyomi | -0.323 |
ingo | -0.320 |
glers | -0.319 |
emale | -0.312 |
Token | 4 |
Token ID | 19 |
Feature activation | +4.76e-04 |
Pos logit contributions | |
)", | +0.030 |
ingo | +0.026 |
uyomi | +0.026 |
glers | +0.026 |
emale | +0.025 |
Neg logit contributions | |
smoot | -0.022 |
fres | -0.020 |
ans | -0.020 |
Pac | -0.020 |
Spur | -0.019 |
Token | fe |
Token ID | 5036 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
)", | +0.000 |
ingo | +0.000 |
uyomi | +0.000 |
glers | +0.000 |
emale | +0.000 |
Neg logit contributions | |
smoot | -0.000 |
fres | -0.000 |
ans | -0.000 |
Pac | -0.000 |
Spur | -0.000 |
Token | 353 |
Token ID | 33319 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
)", | +0.130 |
ingo | +0.113 |
uyomi | +0.111 |
glers | +0.110 |
emale | +0.109 |
Neg logit contributions | |
smoot | -0.094 |
fres | -0.087 |
ans | -0.084 |
Pac | -0.084 |
Spur | -0.083 |
Token | ef |
Token ID | 891 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
)", | +0.486 |
ingo | +0.415 |
uyomi | +0.407 |
glers | +0.406 |
emale | +0.400 |
Neg logit contributions | |
smoot | -0.403 |
fres | -0.377 |
ans | -0.365 |
Pac | -0.365 |
Spur | -0.362 |
Token | 015 |
Token ID | 25150 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
)", | +0.276 |
ingo | +0.239 |
uyomi | +0.233 |
glers | +0.233 |
emale | +0.230 |
Neg logit contributions | |
smoot | -0.207 |
fres | -0.193 |
Pac | -0.186 |
ans | -0.186 |
Spur | -0.183 |
Token | 390 |
Token ID | 25964 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
)", | +0.451 |
ingo | +0.388 |
uyomi | +0.381 |
glers | +0.379 |
emale | +0.375 |
Neg logit contributions | |
smoot | -0.358 |
fres | -0.334 |
ans | -0.323 |
Pac | -0.323 |
Spur | -0.320 |
Token | b |
Token ID | 65 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
)", | +0.877 |
ingo | +0.755 |
uyomi | +0.737 |
glers | +0.733 |
emale | +0.722 |
Neg logit contributions | |
smoot | -0.721 |
fres | -0.674 |
Pac | -0.651 |
ans | -0.650 |
Spur | -0.647 |
Token | 0 |
Token ID | 15 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
)", | +0.146 |
ingo | +0.126 |
uyomi | +0.125 |
glers | +0.124 |
emale | +0.122 |
Neg logit contributions | |
smoot | -0.107 |
fres | -0.100 |
Pac | -0.096 |
ans | -0.096 |
Spur | -0.094 |
Token | bb |
Token ID | 11848 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
)", | +0.135 |
ingo | +0.115 |
uyomi | +0.115 |
glers | +0.113 |
emale | +0.112 |
Neg logit contributions | |
smoot | -0.115 |
fres | -0.108 |
ans | -0.105 |
Pac | -0.104 |
Spur | -0.103 |
Token | 9 |
Token ID | 24 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
)", | +0.254 |
ingo | +0.219 |
uyomi | +0.215 |
glers | +0.215 |
harm | +0.212 |
Neg logit contributions | |
smoot | -0.192 |
fres | -0.179 |
Pac | -0.173 |
ans | -0.172 |
Spur | -0.171 |
Token | d |
Token ID | 67 |
Feature activation | -7.37e-03 |
Pos logit contributions | |
)", | +0.301 |
ingo | +0.258 |
uyomi | +0.253 |
glers | +0.251 |
emale | +0.249 |
Neg logit contributions | |
smoot | -0.237 |
fres | -0.222 |
ans | -0.214 |
Pac | -0.213 |
Spur | -0.211 |
Token | to |
Token ID | 284 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
smoot | +0.213 |
fres | +0.201 |
ans | +0.197 |
Pac | +0.194 |
Spur | +0.191 |
Neg logit contributions | |
)", | -0.250 |
uyomi | -0.218 |
ingo | -0.217 |
glers | -0.214 |
emale | -0.210 |
Token | zero |
Token ID | 6632 |
Feature activation | +1.76e-03 |
Pos logit contributions | |
)", | +0.024 |
ingo | +0.020 |
uyomi | +0.020 |
glers | +0.020 |
harm | +0.020 |
Neg logit contributions | |
smoot | -0.020 |
fres | -0.019 |
ans | -0.019 |
Pac | -0.019 |
chev | -0.018 |
Token | - |
Token ID | 12 |
Feature activation | -9.68e-02 |
Pos logit contributions | |
)", | +0.001 |
ingo | +0.001 |
uyomi | +0.001 |
glers | +0.001 |
harm | +0.001 |
Neg logit contributions | |
smoot | -0.001 |
fres | -0.001 |
ans | -0.001 |
Pac | -0.001 |
chev | -0.001 |
Token | out |
Token ID | 448 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
smoot | +0.058 |
fres | +0.054 |
ans | +0.052 |
Pac | +0.051 |
Spur | +0.050 |
Neg logit contributions | |
)", | -0.088 |
ingo | -0.077 |
uyomi | -0.077 |
glers | -0.076 |
harm | -0.076 |
Token | Planned |
Token ID | 18451 |
Feature activation | +7.46e-02 |
Pos logit contributions | |
smoot | +0.196 |
fres | +0.184 |
ans | +0.181 |
Pac | +0.177 |
chev | +0.173 |
Neg logit contributions | |
)", | -0.255 |
uyomi | -0.222 |
ingo | -0.222 |
glers | -0.220 |
emale | -0.216 |
Token | Parenthood |
Token ID | 18461 |
Feature activation | +9.11e-01 |
Pos logit contributions | |
)", | +0.029 |
uyomi | +0.022 |
ingo | +0.021 |
glers | +0.021 |
emale | +0.020 |
Neg logit contributions | |
smoot | -0.083 |
fres | -0.080 |
ans | -0.079 |
Pac | -0.078 |
Spur | -0.077 |
Token | ๏ฟฝ |
Token ID | 447 |
Feature activation | -8.92e-02 |
Pos logit contributions | |
)", | +0.922 |
ingo | +0.832 |
uyomi | +0.826 |
glers | +0.820 |
harm | +0.805 |
Neg logit contributions | |
smoot | -0.433 |
fres | -0.394 |
ans | -0.381 |
Pac | -0.377 |
Fedora | -0.368 |
Token | ๏ฟฝ |
Token ID | 247 |
Feature activation | +5.63e-02 |
Pos logit contributions | |
smoot | +0.081 |
fres | +0.077 |
ans | +0.076 |
Pac | +0.075 |
Spur | +0.074 |
Neg logit contributions | |
)", | -0.053 |
uyomi | -0.044 |
ingo | -0.043 |
glers | -0.043 |
emale | -0.042 |
Token | s |
Token ID | 82 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
)", | +0.051 |
ingo | +0.045 |
uyomi | +0.045 |
glers | +0.045 |
harm | +0.044 |
Neg logit contributions | |
smoot | -0.033 |
fres | -0.031 |
ans | -0.030 |
Pac | -0.030 |
Fedora | -0.029 |
Token | federal |
Token ID | 2717 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
smoot | +0.015 |
fres | +0.014 |
ans | +0.014 |
Pac | +0.014 |
chev | +0.013 |
Neg logit contributions | |
)", | -0.018 |
uyomi | -0.015 |
ingo | -0.015 |
glers | -0.015 |
emale | -0.015 |
Token | funding |
Token ID | 4918 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
)", | +0.113 |
uyomi | +0.101 |
ingo | +0.100 |
glers | +0.100 |
emale | +0.098 |
Neg logit contributions | |
smoot | -0.067 |
fres | -0.063 |
ans | -0.061 |
Pac | -0.059 |
Spur | -0.058 |
Token | can |
Token ID | 460 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
)", | +0.543 |
glers | +0.478 |
ingo | +0.476 |
uyomi | +0.474 |
harm | +0.469 |
Neg logit contributions | |
smoot | -0.367 |
fres | -0.344 |
ans | -0.341 |
Pac | -0.340 |
Spur | -0.333 |
Token | damage |
Token ID | 2465 |
Feature activation | +8.73e-02 |
Pos logit contributions | |
)", | +0.086 |
uyomi | +0.074 |
ingo | +0.073 |
glers | +0.073 |
harm | +0.072 |
Neg logit contributions | |
smoot | -0.082 |
fres | -0.078 |
ans | -0.077 |
Pac | -0.077 |
Spur | -0.075 |
Token | the |
Token ID | 262 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
)", | +0.075 |
ingo | +0.065 |
glers | +0.064 |
uyomi | +0.064 |
adolesc | +0.063 |
Neg logit contributions | |
smoot | -0.055 |
fres | -0.051 |
Pac | -0.051 |
ans | -0.051 |
chev | -0.050 |
Token | liver |
Token ID | 14383 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
)", | +0.114 |
ingo | +0.100 |
uyomi | +0.099 |
glers | +0.099 |
harm | +0.096 |
Neg logit contributions | |
smoot | -0.087 |
fres | -0.081 |
Pac | -0.081 |
ans | -0.081 |
chev | -0.079 |
Token | and |
Token ID | 290 |
Feature activation | +8.06e-02 |
Pos logit contributions | |
)", | +0.216 |
ingo | +0.187 |
uyomi | +0.186 |
glers | +0.184 |
harm | +0.180 |
Neg logit contributions | |
smoot | -0.185 |
fres | -0.174 |
ans | -0.171 |
Pac | -0.169 |
Spur | -0.166 |
Token | lead |
Token ID | 1085 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
)", | +0.073 |
ingo | +0.064 |
uyomi | +0.064 |
glers | +0.063 |
harm | +0.062 |
Neg logit contributions | |
smoot | -0.047 |
fres | -0.044 |
ans | -0.043 |
Pac | -0.043 |
chev | -0.042 |
Token | to |
Token ID | 284 |
Feature activation | +8.90e-02 |
Pos logit contributions | |
)", | +0.873 |
ingo | +0.759 |
uyomi | +0.756 |
glers | +0.743 |
harm | +0.734 |
Neg logit contributions | |
smoot | -0.733 |
fres | -0.692 |
ans | -0.681 |
Pac | -0.680 |
Spur | -0.663 |
Token | cancer |
Token ID | 4890 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
)", | +0.072 |
uyomi | +0.063 |
ingo | +0.063 |
glers | +0.062 |
harm | +0.061 |
Neg logit contributions | |
smoot | -0.061 |
fres | -0.058 |
ans | -0.057 |
Pac | -0.056 |
chev | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | +9.27e-04 |
Pos logit contributions | |
)", | +0.199 |
ingo | +0.173 |
uyomi | +0.173 |
glers | +0.170 |
harm | +0.167 |
Neg logit contributions | |
smoot | -0.166 |
fres | -0.157 |
ans | -0.153 |
Pac | -0.151 |
Spur | -0.149 |
Token |
|
Token ID | 198 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
)", | +0.001 |
glers | +0.001 |
ingo | +0.001 |
uyomi | +0.001 |
harm | +0.001 |
Neg logit contributions | |
smoot | -0.001 |
fres | -0.001 |
ans | -0.001 |
Pac | -0.001 |
bolted | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -6.52e-02 |
Pos logit contributions | |
smoot | +0.041 |
fres | +0.039 |
ans | +0.037 |
Pac | +0.037 |
bolted | +0.036 |
Neg logit contributions | |
)", | -0.054 |
ingo | -0.047 |
glers | -0.047 |
uyomi | -0.046 |
harm | -0.045 |
Token | pipeline |
Token ID | 11523 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
)", | +0.162 |
ingo | +0.142 |
uyomi | +0.141 |
glers | +0.140 |
emale | +0.138 |
Neg logit contributions | |
smoot | -0.111 |
fres | -0.104 |
ans | -0.102 |
Pac | -0.099 |
Fedora | -0.098 |
Token | was |
Token ID | 373 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
smoot | +0.311 |
fres | +0.292 |
ans | +0.287 |
Pac | +0.281 |
Fedora | +0.274 |
Neg logit contributions | |
)", | -0.486 |
uyomi | -0.427 |
ingo | -0.426 |
glers | -0.424 |
emale | -0.414 |
Token | ๏ฟฝ |
Token ID | 564 |
Feature activation | +7.37e-02 |
Pos logit contributions | |
)", | +0.033 |
ingo | +0.028 |
uyomi | +0.028 |
glers | +0.028 |
harm | +0.028 |
Neg logit contributions | |
smoot | -0.026 |
fres | -0.025 |
ans | -0.024 |
Pac | -0.024 |
chev | -0.024 |
Token | ๏ฟฝ |
Token ID | 250 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
)", | +0.060 |
uyomi | +0.052 |
ingo | +0.052 |
glers | +0.052 |
emale | +0.050 |
Neg logit contributions | |
smoot | -0.051 |
fres | -0.048 |
ans | -0.047 |
Pac | -0.046 |
Spur | -0.045 |
Token | man |
Token ID | 805 |
Feature activation | +5.64e-02 |
Pos logit contributions | |
)", | +0.172 |
ingo | +0.150 |
harm | +0.149 |
glers | +0.149 |
uyomi | +0.148 |
Neg logit contributions | |
smoot | -0.132 |
fres | -0.124 |
Pac | -0.119 |
Spur | -0.118 |
ans | -0.118 |
Token | ifest |
Token ID | 8409 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
)", | +0.038 |
uyomi | +0.033 |
ingo | +0.032 |
glers | +0.032 |
harm | +0.031 |
Neg logit contributions | |
smoot | -0.047 |
fres | -0.044 |
ans | -0.043 |
Pac | -0.043 |
Spur | -0.042 |
Token | ly |
Token ID | 306 |
Feature activation | -6.76e-02 |
Pos logit contributions | |
)", | +0.879 |
ingo | +0.760 |
uyomi | +0.755 |
glers | +0.753 |
harm | +0.736 |
Neg logit contributions | |
smoot | -0.761 |
fres | -0.717 |
ans | -0.696 |
Pac | -0.691 |
Spur | -0.679 |
Token | adequate |
Token ID | 12872 |
Feature activation | -7.44e-02 |
Pos logit contributions | |
smoot | +0.047 |
fres | +0.044 |
ans | +0.043 |
Pac | +0.043 |
Spur | +0.042 |
Neg logit contributions | |
)", | -0.055 |
ingo | -0.047 |
uyomi | -0.047 |
glers | -0.046 |
harm | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
smoot | +0.053 |
fres | +0.050 |
ans | +0.049 |
Pac | +0.048 |
Spur | +0.047 |
Neg logit contributions | |
)", | -0.059 |
uyomi | -0.051 |
ingo | -0.051 |
glers | -0.050 |
emale | -0.049 |
Token | ๏ฟฝ |
Token ID | 447 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
)", | +0.011 |
ingo | +0.009 |
glers | +0.009 |
uyomi | +0.009 |
harm | +0.009 |
Neg logit contributions | |
smoot | -0.009 |
fres | -0.008 |
ans | -0.008 |
Pac | -0.008 |
bolted | -0.008 |
Token | ๏ฟฝ |
Token ID | 251 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
smoot | +0.014 |
fres | +0.013 |
ans | +0.013 |
Pac | +0.013 |
Spur | +0.012 |
Neg logit contributions | |
)", | -0.023 |
uyomi | -0.020 |
ingo | -0.020 |
glers | -0.020 |
emale | -0.020 |
Token | D |
Token ID | 35 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
)", | +0.162 |
ingo | +0.137 |
glers | +0.135 |
uyomi | +0.135 |
harm | +0.133 |
Neg logit contributions | |
smoot | -0.175 |
fres | -0.165 |
ans | -0.159 |
Spur | -0.157 |
Fedora | -0.156 |
Token | ani |
Token ID | 3216 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
smoot | +0.016 |
fres | +0.015 |
ans | +0.014 |
Pac | +0.014 |
Spur | +0.014 |
Neg logit contributions | |
)", | -0.016 |
ingo | -0.014 |
uyomi | -0.013 |
glers | -0.013 |
harm | -0.013 |
Token | els |
Token ID | 1424 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
smoot | +0.165 |
fres | +0.160 |
ans | +0.158 |
Pac | +0.157 |
Spur | +0.156 |
Neg logit contributions | |
)", | -0.033 |
ingo | -0.018 |
uyomi | -0.018 |
glers | -0.017 |
emale | -0.015 |
Token | ๏ฟฝ |
Token ID | 447 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
)", | +0.538 |
ingo | +0.474 |
uyomi | +0.470 |
glers | +0.470 |
harm | +0.459 |
Neg logit contributions | |
smoot | -0.315 |
fres | -0.291 |
ans | -0.286 |
Pac | -0.280 |
Spur | -0.273 |
Token | ๏ฟฝ |
Token ID | 247 |
Feature activation | +9.24e-02 |
Pos logit contributions | |
)", | +0.115 |
uyomi | +0.097 |
ingo | +0.096 |
glers | +0.095 |
emale | +0.093 |
Neg logit contributions | |
smoot | -0.144 |
fres | -0.136 |
ans | -0.134 |
Pac | -0.132 |
Spur | -0.130 |
Token | mug |
Token ID | 25152 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
)", | +0.084 |
uyomi | +0.073 |
ingo | +0.073 |
glers | +0.073 |
emale | +0.072 |
Neg logit contributions | |
smoot | -0.055 |
fres | -0.051 |
ans | -0.049 |
Pac | -0.049 |
Fedora | -0.048 |
Token | shot |
Token ID | 9442 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
)", | +0.726 |
glers | +0.628 |
ingo | +0.625 |
uyomi | +0.619 |
harm | +0.598 |
Neg logit contributions | |
smoot | -0.674 |
fres | -0.633 |
ans | -0.620 |
Pac | -0.617 |
Spur | -0.609 |
Token | was |
Token ID | 373 |
Feature activation | +9.90e-02 |
Pos logit contributions | |
smoot | +0.169 |
fres | +0.158 |
ans | +0.155 |
Pac | +0.153 |
Spur | +0.150 |
Neg logit contributions | |
)", | -0.221 |
ingo | -0.192 |
uyomi | -0.192 |
glers | -0.190 |
emale | -0.187 |
Token | also |
Token ID | 635 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
)", | +0.089 |
ingo | +0.078 |
uyomi | +0.078 |
glers | +0.078 |
emale | +0.076 |
Neg logit contributions | |
smoot | -0.059 |
fres | -0.055 |
ans | -0.054 |
Pac | -0.053 |
Spur | -0.052 |
Token | taken |
Token ID | 2077 |
Feature activation | -6.22e-03 |
Pos logit contributions | |
)", | +0.111 |
ingo | +0.097 |
uyomi | +0.097 |
glers | +0.096 |
emale | +0.094 |
Neg logit contributions | |
smoot | -0.069 |
fres | -0.064 |
ans | -0.063 |
Pac | -0.062 |
Spur | -0.061 |
Token | in |
Token ID | 287 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
smoot | +0.004 |
fres | +0.004 |
ans | +0.004 |
Pac | +0.004 |
Spur | +0.004 |
Neg logit contributions | |
)", | -0.005 |
uyomi | -0.004 |
ingo | -0.004 |
glers | -0.004 |
emale | -0.004 |
Token | in |
Token ID | 287 |
Feature activation | -8.97e-02 |
Pos logit contributions | |
smoot | +0.007 |
fres | +0.007 |
ans | +0.007 |
Pac | +0.007 |
Spur | +0.007 |
Neg logit contributions | |
)", | -0.009 |
uyomi | -0.008 |
ingo | -0.008 |
glers | -0.008 |
emale | -0.007 |
Token | Asian |
Token ID | 7740 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
smoot | +0.054 |
fres | +0.051 |
ans | +0.050 |
Pac | +0.050 |
chev | +0.049 |
Neg logit contributions | |
)", | -0.080 |
ingo | -0.069 |
glers | -0.069 |
uyomi | -0.069 |
harm | -0.067 |
Token | cooking |
Token ID | 10801 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
smoot | +0.171 |
fres | +0.159 |
ans | +0.156 |
Pac | +0.154 |
chev | +0.150 |
Neg logit contributions | |
)", | -0.262 |
uyomi | -0.231 |
ingo | -0.229 |
glers | -0.228 |
emale | -0.223 |
Token | ). |
Token ID | 737 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
smoot | +0.186 |
fres | +0.175 |
ans | +0.173 |
Pac | +0.171 |
Spur | +0.168 |
Neg logit contributions | |
)", | -0.197 |
uyomi | -0.167 |
ingo | -0.167 |
glers | -0.166 |
emale | -0.161 |
Token | Apparently |
Token ID | 18626 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
smoot | +0.016 |
fres | +0.015 |
ans | +0.015 |
Pac | +0.015 |
chev | +0.015 |
Neg logit contributions | |
)", | -0.018 |
ingo | -0.015 |
glers | -0.015 |
uyomi | -0.015 |
harm | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
)", | +0.009 |
uyomi | +0.008 |
ingo | +0.008 |
glers | +0.008 |
emale | +0.008 |
Neg logit contributions | |
smoot | -0.008 |
fres | -0.008 |
ans | -0.007 |
Pac | -0.007 |
chev | -0.007 |
Token | it |
Token ID | 340 |
Feature activation | +6.13e-02 |
Pos logit contributions | |
)", | +0.188 |
glers | +0.161 |
ingo | +0.161 |
uyomi | +0.160 |
harm | +0.155 |
Neg logit contributions | |
smoot | -0.162 |
fres | -0.153 |
ans | -0.152 |
Pac | -0.151 |
chev | -0.147 |
Token | is |
Token ID | 318 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
)", | +0.053 |
ingo | +0.046 |
glers | +0.046 |
uyomi | +0.046 |
harm | +0.045 |
Neg logit contributions | |
smoot | -0.038 |
fres | -0.036 |
Pac | -0.035 |
ans | -0.035 |
Spur | -0.035 |
Token | even |
Token ID | 772 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
smoot | +0.068 |
fres | +0.064 |
ans | +0.064 |
Pac | +0.063 |
chev | +0.062 |
Neg logit contributions | |
)", | -0.100 |
ingo | -0.087 |
uyomi | -0.086 |
glers | -0.085 |
harm | -0.084 |
Token | better |
Token ID | 1365 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
smoot | +0.057 |
fres | +0.052 |
ans | +0.052 |
Pac | +0.051 |
chev | +0.050 |
Neg logit contributions | |
)", | -0.094 |
ingo | -0.083 |
uyomi | -0.082 |
glers | -0.082 |
harm | -0.080 |
Token | than |
Token ID | 621 |
Feature activation | -5.19e-02 |
Pos logit contributions | |
smoot | +0.151 |
fres | +0.144 |
ans | +0.142 |
Pac | +0.142 |
chev | +0.138 |
Neg logit contributions | |
)", | -0.184 |
ingo | -0.159 |
glers | -0.158 |
uyomi | -0.158 |
harm | -0.154 |
Token | Wisconsin |
Token ID | 9279 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
smoot | +0.126 |
fres | +0.118 |
ans | +0.117 |
Pac | +0.114 |
chev | +0.112 |
Neg logit contributions | |
)", | -0.149 |
uyomi | -0.129 |
ingo | -0.129 |
glers | -0.128 |
harm | -0.124 |
Token | . |
Token ID | 13 |
Feature activation | -5.73e-02 |
Pos logit contributions | |
)", | +0.011 |
uyomi | +0.009 |
ingo | +0.009 |
glers | +0.009 |
harm | +0.009 |
Neg logit contributions | |
smoot | -0.010 |
fres | -0.009 |
ans | -0.009 |
Pac | -0.009 |
Spur | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
smoot | +0.041 |
fres | +0.039 |
ans | +0.037 |
Pac | +0.036 |
chev | +0.036 |
Neg logit contributions | |
)", | -0.046 |
glers | -0.039 |
ingo | -0.039 |
uyomi | -0.039 |
harm | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | +8.50e-02 |
Pos logit contributions | |
)", | +0.035 |
ingo | +0.030 |
glers | +0.030 |
uyomi | +0.030 |
harm | +0.029 |
Neg logit contributions | |
smoot | -0.026 |
fres | -0.025 |
ans | -0.024 |
Pac | -0.024 |
Spur | -0.023 |
Token | Lyn |
Token ID | 37207 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
)", | +0.060 |
ingo | +0.050 |
glers | +0.050 |
uyomi | +0.049 |
harm | +0.048 |
Neg logit contributions | |
smoot | -0.069 |
fres | -0.066 |
ans | -0.063 |
Spur | -0.062 |
scoop | -0.062 |
Token | ch |
Token ID | 354 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
smoot | +0.199 |
fres | +0.184 |
ans | +0.176 |
Spur | +0.174 |
Pac | +0.173 |
Neg logit contributions | |
)", | -0.332 |
ingo | -0.292 |
glers | -0.290 |
uyomi | -0.289 |
harm | -0.287 |
Token | also |
Token ID | 635 |
Feature activation | -7.78e-02 |
Pos logit contributions | |
)", | +0.125 |
glers | +0.111 |
ingo | +0.111 |
uyomi | +0.110 |
harm | +0.107 |
Neg logit contributions | |
smoot | -0.072 |
fres | -0.068 |
ans | -0.067 |
Pac | -0.067 |
Spur | -0.065 |
Token | was |
Token ID | 373 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
smoot | +0.040 |
ans | +0.038 |
Pac | +0.037 |
fres | +0.037 |
Spur | +0.036 |
Neg logit contributions | |
)", | -0.075 |
glers | -0.066 |
ingo | -0.066 |
uyomi | -0.066 |
harm | -0.064 |
Token | intercepted |
Token ID | 29842 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
smoot | +0.062 |
ans | +0.058 |
fres | +0.058 |
Pac | +0.057 |
chev | +0.056 |
Neg logit contributions | |
)", | -0.093 |
ingo | -0.082 |
uyomi | -0.081 |
glers | -0.081 |
harm | -0.079 |
Token | late |
Token ID | 2739 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
)", | +0.264 |
uyomi | +0.228 |
glers | +0.226 |
ingo | +0.226 |
harm | +0.220 |
Neg logit contributions | |
smoot | -0.225 |
fres | -0.211 |
ans | -0.211 |
Pac | -0.207 |
chev | -0.203 |
Token | in |
Token ID | 287 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
smoot | +0.166 |
fres | +0.156 |
ans | +0.154 |
Pac | +0.150 |
Spur | +0.147 |
Neg logit contributions | |
)", | -0.200 |
uyomi | -0.175 |
glers | -0.174 |
ingo | -0.173 |
emale | -0.168 |
Token | atic |
Token ID | 1512 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
)", | +0.071 |
uyomi | +0.061 |
ingo | +0.061 |
glers | +0.060 |
emale | +0.059 |
Neg logit contributions | |
smoot | -0.067 |
fres | -0.063 |
ans | -0.061 |
Pac | -0.061 |
Spur | -0.060 |
Token | a |
Token ID | 64 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
)", | +0.322 |
ingo | +0.280 |
uyomi | +0.280 |
glers | +0.275 |
harm | +0.273 |
Neg logit contributions | |
smoot | -0.268 |
fres | -0.252 |
ans | -0.241 |
Pac | -0.239 |
Fedora | -0.235 |
Token | Jane |
Token ID | 12091 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
)", | +0.199 |
ingo | +0.172 |
uyomi | +0.172 |
glers | +0.169 |
emale | +0.167 |
Neg logit contributions | |
smoot | -0.165 |
fres | -0.154 |
ans | -0.150 |
Pac | -0.148 |
chev | -0.145 |
Token | va |
Token ID | 6862 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
smoot | +0.072 |
fres | +0.068 |
ans | +0.066 |
Pac | +0.065 |
Spur | +0.064 |
Neg logit contributions | |
)", | -0.087 |
uyomi | -0.076 |
ingo | -0.075 |
glers | -0.075 |
harm | -0.073 |
Token | in |
Token ID | 287 |
Feature activation | -6.76e-02 |
Pos logit contributions | |
smoot | +0.294 |
fres | +0.276 |
ans | +0.268 |
Pac | +0.265 |
Spur | +0.259 |
Neg logit contributions | |
)", | -0.366 |
uyomi | -0.318 |
ingo | -0.318 |
glers | -0.314 |
emale | -0.309 |
Token | front |
Token ID | 2166 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
smoot | +0.045 |
fres | +0.042 |
ans | +0.041 |
Pac | +0.041 |
Spur | +0.040 |
Neg logit contributions | |
)", | -0.057 |
uyomi | -0.049 |
ingo | -0.049 |
glers | -0.049 |
emale | -0.048 |
Token | ot |
Token ID | 30972 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
)", | +0.186 |
uyomi | +0.162 |
ingo | +0.161 |
glers | +0.160 |
emale | +0.157 |
Neg logit contributions | |
smoot | -0.147 |
fres | -0.138 |
ans | -0.136 |
Pac | -0.133 |
Spur | -0.131 |
Token | the |
Token ID | 262 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
smoot | +0.186 |
fres | +0.174 |
ans | +0.170 |
Pac | +0.169 |
Spur | +0.166 |
Neg logit contributions | |
)", | -0.232 |
uyomi | -0.202 |
ingo | -0.201 |
glers | -0.201 |
emale | -0.195 |
Token | Secret |
Token ID | 3943 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
)", | +0.031 |
uyomi | +0.027 |
ingo | +0.027 |
glers | +0.027 |
emale | +0.026 |
Neg logit contributions | |
smoot | -0.023 |
fres | -0.022 |
ans | -0.022 |
Pac | -0.021 |
Spur | -0.021 |
Token | Police |
Token ID | 4287 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
smoot | +0.229 |
fres | +0.218 |
ans | +0.214 |
Pac | +0.212 |
Spur | +0.209 |
Neg logit contributions | |
)", | -0.148 |
uyomi | -0.121 |
ingo | -0.120 |
glers | -0.119 |
emale | -0.115 |
Token | HQ |
Token ID | 25112 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
)", | +0.167 |
uyomi | +0.144 |
ingo | +0.143 |
glers | +0.143 |
emale | +0.139 |
Neg logit contributions | |
smoot | -0.139 |
fres | -0.131 |
ans | -0.129 |
Pac | -0.127 |
chev | -0.124 |
Token | ๏ฟฝ |
Token ID | 250 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
)", | +0.286 |
ingo | +0.253 |
uyomi | +0.252 |
glers | +0.250 |
harm | +0.245 |
Neg logit contributions | |
smoot | -0.174 |
fres | -0.162 |
ans | -0.157 |
Spur | -0.152 |
Pac | -0.152 |
Token | death |
Token ID | 22595 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
)", | +0.242 |
ingo | +0.203 |
uyomi | +0.202 |
glers | +0.201 |
harm | +0.198 |
Neg logit contributions | |
smoot | -0.283 |
fres | -0.269 |
ans | -0.259 |
Spur | -0.257 |
Pac | -0.255 |
Token | to |
Token ID | 284 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
)", | +0.180 |
ingo | +0.156 |
uyomi | +0.155 |
glers | +0.153 |
emale | +0.151 |
Neg logit contributions | |
smoot | -0.157 |
fres | -0.147 |
ans | -0.144 |
Pac | -0.143 |
Spur | -0.140 |
Token | the |
Token ID | 262 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
)", | +0.170 |
ingo | +0.148 |
uyomi | +0.147 |
glers | +0.147 |
emale | +0.143 |
Neg logit contributions | |
smoot | -0.134 |
fres | -0.126 |
ans | -0.123 |
Pac | -0.121 |
Spur | -0.119 |
Token | dictator |
Token ID | 26671 |
Feature activation | -4.44e-03 |
Pos logit contributions | |
)", | +0.171 |
ingo | +0.150 |
uyomi | +0.149 |
glers | +0.149 |
harm | +0.145 |
Neg logit contributions | |
smoot | -0.111 |
fres | -0.104 |
ans | -0.101 |
Pac | -0.100 |
Spur | -0.098 |
Token | ๏ฟฝ |
Token ID | 447 |
Feature activation | +9.03e-02 |
Pos logit contributions | |
smoot | +0.003 |
fres | +0.003 |
ans | +0.003 |
Pac | +0.003 |
Spur | +0.003 |
Neg logit contributions | |
)", | -0.004 |
uyomi | -0.003 |
ingo | -0.003 |
glers | -0.003 |
emale | -0.003 |
Token | ๏ฟฝ |
Token ID | 251 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
)", | +0.074 |
uyomi | +0.064 |
ingo | +0.064 |
glers | +0.063 |
emale | +0.062 |
Neg logit contributions | |
smoot | -0.062 |
fres | -0.058 |
ans | -0.057 |
Pac | -0.056 |
Spur | -0.056 |
Token | as |
Token ID | 355 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
)", | +0.180 |
ingo | +0.158 |
uyomi | +0.158 |
glers | +0.157 |
harm | +0.154 |
Neg logit contributions | |
smoot | -0.110 |
fres | -0.103 |
ans | -0.099 |
Pac | -0.098 |
Spur | -0.097 |
Token | they |
Token ID | 484 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
)", | +0.083 |
uyomi | +0.071 |
glers | +0.071 |
ingo | +0.070 |
emale | +0.069 |
Neg logit contributions | |
smoot | -0.074 |
fres | -0.070 |
ans | -0.069 |
Pac | -0.069 |
Spur | -0.067 |
Token | walked |
Token ID | 6807 |
Feature activation | -7.93e-02 |
Pos logit contributions | |
)", | +0.032 |
uyomi | +0.028 |
ingo | +0.028 |
glers | +0.027 |
harm | +0.027 |
Neg logit contributions | |
smoot | -0.020 |
fres | -0.019 |
Pac | -0.018 |
ans | -0.018 |
Fedora | -0.018 |
Token | down |
Token ID | 866 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
smoot | +0.056 |
fres | +0.054 |
ans | +0.053 |
Pac | +0.053 |
chev | +0.052 |
Neg logit contributions | |
)", | -0.061 |
uyomi | -0.052 |
glers | -0.052 |
ingo | -0.052 |
harm | -0.051 |
Token | disappearing |
Token ID | 28867 |
Feature activation | +7.34e-01 |
Pos logit contributions | |
smoot | +0.184 |
fres | +0.173 |
ans | +0.171 |
Pac | +0.169 |
Spur | +0.164 |
Neg logit contributions | |
)", | -0.239 |
ingo | -0.208 |
uyomi | -0.207 |
glers | -0.206 |
harm | -0.202 |
Token | employment |
Token ID | 7184 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
)", | +0.587 |
ingo | +0.503 |
glers | +0.499 |
uyomi | +0.496 |
harm | +0.487 |
Neg logit contributions | |
smoot | -0.510 |
fres | -0.477 |
Pac | -0.472 |
ans | -0.470 |
chev | -0.459 |
Token | opportunities |
Token ID | 6443 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
)", | +0.233 |
ingo | +0.201 |
uyomi | +0.201 |
glers | +0.200 |
harm | +0.194 |
Neg logit contributions | |
smoot | -0.205 |
fres | -0.194 |
ans | -0.190 |
Pac | -0.189 |
Fedora | -0.185 |
Token | in |
Token ID | 287 |
Feature activation | +7.50e-02 |
Pos logit contributions | |
)", | +0.494 |
ingo | +0.427 |
uyomi | +0.423 |
glers | +0.421 |
harm | +0.410 |
Neg logit contributions | |
smoot | -0.435 |
fres | -0.412 |
Pac | -0.403 |
ans | -0.403 |
Fedora | -0.392 |
Token | traditional |
Token ID | 4569 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
)", | +0.061 |
ingo | +0.053 |
glers | +0.052 |
uyomi | +0.052 |
harm | +0.051 |
Neg logit contributions | |
smoot | -0.051 |
fres | -0.048 |
ans | -0.047 |
Pac | -0.047 |
chev | -0.046 |
Token | industries |
Token ID | 11798 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
)", | +0.313 |
ingo | +0.267 |
uyomi | +0.266 |
glers | +0.265 |
emale | +0.257 |
Neg logit contributions | |
smoot | -0.297 |
fres | -0.281 |
ans | -0.277 |
Pac | -0.275 |
Spur | -0.268 |
Token | . |
Token ID | 13 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
)", | +0.276 |
ingo | +0.237 |
uyomi | +0.237 |
glers | +0.235 |
harm | +0.229 |
Neg logit contributions | |
smoot | -0.237 |
fres | -0.224 |
ans | -0.220 |
Pac | -0.218 |
Spur | -0.213 |
Token | Furthermore |
Token ID | 11399 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
)", | +0.123 |
ingo | +0.106 |
uyomi | +0.106 |
glers | +0.105 |
harm | +0.103 |
Neg logit contributions | |
smoot | -0.101 |
fres | -0.095 |
ans | -0.093 |
Pac | -0.091 |
bolted | -0.089 |
Token | , |
Token ID | 11 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
)", | +0.093 |
uyomi | +0.080 |
ingo | +0.080 |
glers | +0.080 |
harm | +0.077 |
Neg logit contributions | |
smoot | -0.092 |
fres | -0.087 |
ans | -0.086 |
Pac | -0.085 |
Spur | -0.083 |
Token | the |
Token ID | 262 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
smoot | +0.037 |
fres | +0.035 |
ans | +0.035 |
Pac | +0.034 |
Spur | +0.033 |
Neg logit contributions | |
)", | -0.044 |
ingo | -0.038 |
uyomi | -0.038 |
glers | -0.038 |
emale | -0.037 |
Token | vision |
Token ID | 5761 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
)", | +0.100 |
ingo | +0.087 |
uyomi | +0.086 |
glers | +0.086 |
harm | +0.084 |
Neg logit contributions | |
smoot | -0.081 |
fres | -0.076 |
ans | -0.075 |
Pac | -0.074 |
chev | -0.072 |
Token | ide |
Token ID | 485 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
)", | +0.251 |
uyomi | +0.223 |
ingo | +0.222 |
glers | +0.221 |
emale | +0.217 |
Neg logit contributions | |
smoot | -0.138 |
fres | -0.127 |
ans | -0.124 |
Pac | -0.121 |
Spur | -0.119 |
Token | hi |
Token ID | 23105 |
Feature activation | +5.03e-02 |
Pos logit contributions | |
)", | +0.190 |
ingo | +0.167 |
uyomi | +0.165 |
glers | +0.164 |
harm | +0.161 |
Neg logit contributions | |
smoot | -0.143 |
fres | -0.134 |
ans | -0.132 |
Pac | -0.131 |
Spur | -0.127 |
Token | - |
Token ID | 12 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
)", | +0.039 |
ingo | +0.033 |
uyomi | +0.033 |
glers | +0.033 |
harm | +0.032 |
Neg logit contributions | |
smoot | -0.037 |
fres | -0.035 |
ans | -0.034 |
Pac | -0.033 |
Spur | -0.033 |
Token | fi |
Token ID | 12463 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
smoot | +0.211 |
fres | +0.201 |
ans | +0.196 |
Pac | +0.193 |
Spur | +0.192 |
Neg logit contributions | |
)", | -0.201 |
ingo | -0.171 |
uyomi | -0.170 |
glers | -0.169 |
harm | -0.166 |
Token | sound |
Token ID | 2128 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
smoot | +0.349 |
fres | +0.328 |
ans | +0.322 |
Pac | +0.318 |
Spur | +0.311 |
Neg logit contributions | |
)", | -0.488 |
ingo | -0.429 |
uyomi | -0.427 |
glers | -0.424 |
harm | -0.416 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
smoot | +0.087 |
fres | +0.082 |
ans | +0.080 |
Pac | +0.080 |
Spur | +0.079 |
Neg logit contributions | |
)", | -0.111 |
uyomi | -0.097 |
ingo | -0.097 |
glers | -0.097 |
harm | -0.095 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e-05 |
Pos logit contributions | |
)", | +0.009 |
ingo | +0.007 |
glers | +0.007 |
uyomi | +0.007 |
harm | +0.007 |
Neg logit contributions | |
smoot | -0.008 |
fres | -0.007 |
ans | -0.007 |
Pac | -0.007 |
bolted | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
smoot | +0.000 |
fres | +0.000 |
ans | +0.000 |
Pac | +0.000 |
Spur | +0.000 |
Neg logit contributions | |
)", | -0.000 |
ingo | -0.000 |
glers | -0.000 |
uyomi | -0.000 |
harm | -0.000 |
Token | Will |
Token ID | 8743 |
Feature activation | +9.00e-02 |
Pos logit contributions | |
)", | +0.008 |
ingo | +0.006 |
glers | +0.006 |
uyomi | +0.006 |
harm | +0.006 |
Neg logit contributions | |
smoot | -0.009 |
fres | -0.008 |
ans | -0.008 |
Spur | -0.008 |
Fedora | -0.008 |
Token | Dev |
Token ID | 6245 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
)", | +0.075 |
ingo | +0.065 |
uyomi | +0.065 |
glers | +0.065 |
harm | +0.063 |
Neg logit contributions | |
smoot | -0.060 |
fres | -0.056 |
ans | -0.055 |
Pac | -0.055 |
Spur | -0.053 |
Token | ial |
Token ID | 498 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
smoot | +0.107 |
fres | +0.102 |
ans | +0.100 |
Pac | +0.098 |
Spur | +0.097 |
Neg logit contributions | |
)", | -0.088 |
uyomi | -0.075 |
ingo | -0.074 |
glers | -0.074 |
emale | -0.071 |
Token | " |
Token ID | 1 |
Feature activation | +9.14e-02 |
Pos logit contributions | |
)", | +0.352 |
ingo | +0.299 |
uyomi | +0.298 |
glers | +0.297 |
harm | +0.288 |
Neg logit contributions | |
smoot | -0.324 |
fres | -0.307 |
ans | -0.302 |
Pac | -0.299 |
Spur | -0.293 |
Token | in |
Token ID | 287 |
Feature activation | +9.22e-02 |
Pos logit contributions | |
)", | +0.081 |
ingo | +0.071 |
glers | +0.070 |
uyomi | +0.070 |
harm | +0.069 |
Neg logit contributions | |
smoot | -0.055 |
fres | -0.051 |
ans | -0.051 |
Pac | -0.050 |
chev | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
)", | +0.082 |
ingo | +0.072 |
glers | +0.072 |
uyomi | +0.071 |
harm | +0.070 |
Neg logit contributions | |
smoot | -0.055 |
fres | -0.052 |
ans | -0.051 |
Pac | -0.051 |
chev | -0.049 |
Token | flight |
Token ID | 5474 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
)", | +0.034 |
ingo | +0.029 |
glers | +0.029 |
uyomi | +0.029 |
emale | +0.028 |
Neg logit contributions | |
smoot | -0.026 |
fres | -0.025 |
ans | -0.024 |
Pac | -0.024 |
chev | -0.024 |
Token | control |
Token ID | 1630 |
Feature activation | +7.57e-02 |
Pos logit contributions | |
)", | +0.105 |
ingo | +0.091 |
uyomi | +0.090 |
glers | +0.090 |
harm | +0.088 |
Neg logit contributions | |
smoot | -0.075 |
fres | -0.070 |
ans | -0.069 |
Pac | -0.069 |
Spur | -0.067 |
Token | primary |
Token ID | 4165 |
Feature activation | +5.93e-02 |
Pos logit contributions | |
)", | +0.062 |
ingo | +0.053 |
uyomi | +0.053 |
glers | +0.052 |
harm | +0.051 |
Neg logit contributions | |
smoot | -0.051 |
fres | -0.049 |
ans | -0.047 |
Pac | -0.047 |
chev | -0.046 |
Token | computer |
Token ID | 3644 |
Feature activation | -9.54e-02 |
Pos logit contributions | |
)", | +0.044 |
ingo | +0.037 |
uyomi | +0.037 |
glers | +0.037 |
harm | +0.036 |
Neg logit contributions | |
smoot | -0.044 |
fres | -0.042 |
ans | -0.041 |
Pac | -0.041 |
Spur | -0.040 |
Token | 's |
Token ID | 338 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
smoot | +0.056 |
fres | +0.053 |
ans | +0.052 |
Pac | +0.051 |
chev | +0.050 |
Neg logit contributions | |
)", | -0.086 |
ingo | -0.075 |
uyomi | -0.075 |
glers | -0.075 |
harm | -0.073 |
Token | algorithm |
Token ID | 11862 |
Feature activation | +8.31e-02 |
Pos logit contributions | |
)", | +0.211 |
ingo | +0.183 |
uyomi | +0.183 |
glers | +0.180 |
emale | +0.177 |
Neg logit contributions | |
smoot | -0.166 |
fres | -0.157 |
ans | -0.155 |
Pac | -0.153 |
chev | -0.150 |
Token | failed |
Token ID | 4054 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
)", | +0.077 |
ingo | +0.067 |
uyomi | +0.067 |
glers | +0.067 |
harm | +0.065 |
Neg logit contributions | |
smoot | -0.047 |
fres | -0.044 |
ans | -0.043 |
Pac | -0.043 |
chev | -0.042 |
Token | to |
Token ID | 284 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
)", | +0.268 |
uyomi | +0.232 |
ingo | +0.231 |
glers | +0.230 |
emale | +0.224 |
Neg logit contributions | |
smoot | -0.228 |
fres | -0.215 |
ans | -0.212 |
Pac | -0.209 |
chev | -0.204 |
Token | an |
Token ID | 281 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
)", | +0.008 |
uyomi | +0.007 |
ingo | +0.007 |
glers | +0.007 |
emale | +0.007 |
Neg logit contributions | |
smoot | -0.007 |
fres | -0.007 |
ans | -0.007 |
Pac | -0.007 |
chev | -0.007 |
Token | earlier |
Token ID | 2961 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
smoot | +0.104 |
fres | +0.098 |
ans | +0.097 |
Pac | +0.095 |
Spur | +0.093 |
Neg logit contributions | |
)", | -0.117 |
uyomi | -0.101 |
ingo | -0.100 |
glers | -0.100 |
emale | -0.098 |
Token | start |
Token ID | 923 |
Feature activation | -9.44e-02 |
Pos logit contributions | |
smoot | +0.186 |
fres | +0.175 |
ans | +0.172 |
Pac | +0.168 |
Spur | +0.165 |
Neg logit contributions | |
)", | -0.236 |
uyomi | -0.206 |
ingo | -0.205 |
glers | -0.204 |
emale | -0.199 |
Token | for |
Token ID | 329 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
smoot | +0.064 |
fres | +0.061 |
ans | +0.060 |
Pac | +0.059 |
Spur | +0.058 |
Neg logit contributions | |
)", | -0.077 |
uyomi | -0.067 |
ingo | -0.067 |
glers | -0.066 |
emale | -0.065 |
Token | elementary |
Token ID | 19823 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
smoot | +0.022 |
fres | +0.021 |
ans | +0.021 |
Pac | +0.021 |
chev | +0.020 |
Neg logit contributions | |
)", | -0.027 |
glers | -0.023 |
ingo | -0.023 |
uyomi | -0.023 |
adolesc | -0.023 |
Token | schools |
Token ID | 4266 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
smoot | +0.462 |
fres | +0.435 |
ans | +0.429 |
Pac | +0.423 |
Spur | +0.415 |
Neg logit contributions | |
)", | -0.529 |
uyomi | -0.457 |
ingo | -0.456 |
glers | -0.455 |
emale | -0.441 |
Token | , |
Token ID | 11 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
smoot | +0.331 |
fres | +0.312 |
ans | +0.307 |
Pac | +0.302 |
Spur | +0.296 |
Neg logit contributions | |
)", | -0.376 |
uyomi | -0.325 |
ingo | -0.325 |
glers | -0.322 |
emale | -0.314 |
Token | and |
Token ID | 290 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
smoot | +0.014 |
fres | +0.013 |
ans | +0.013 |
Pac | +0.013 |
Spur | +0.012 |
Neg logit contributions | |
)", | -0.016 |
uyomi | -0.014 |
ingo | -0.014 |
glers | -0.014 |
emale | -0.014 |
Token | sets |
Token ID | 5621 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
)", | +0.018 |
uyomi | +0.016 |
ingo | +0.016 |
glers | +0.016 |
emale | +0.015 |
Neg logit contributions | |
smoot | -0.014 |
fres | -0.013 |
ans | -0.013 |
Pac | -0.013 |
Spur | -0.013 |
Token | off |
Token ID | 572 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
smoot | +0.037 |
fres | +0.035 |
ans | +0.034 |
Pac | +0.034 |
chev | +0.033 |
Neg logit contributions | |
)", | -0.047 |
uyomi | -0.041 |
glers | -0.041 |
ingo | -0.041 |
harm | -0.040 |
Token | a |
Token ID | 257 |
Feature activation | -8.16e-02 |
Pos logit contributions | |
smoot | +0.315 |
fres | +0.297 |
ans | +0.294 |
Pac | +0.290 |
chev | +0.284 |
Neg logit contributions | |
)", | -0.328 |
uyomi | -0.283 |
glers | -0.281 |
ingo | -0.281 |
emale | -0.272 |
Token | icas |
Token ID | 44645 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
)", | +0.151 |
ingo | +0.125 |
uyomi | +0.124 |
glers | +0.124 |
emale | +0.120 |
Neg logit contributions | |
smoot | -0.201 |
fres | -0.190 |
ans | -0.185 |
Pac | -0.184 |
Spur | -0.184 |
Token | of |
Token ID | 286 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
smoot | +0.164 |
fres | +0.154 |
ans | +0.152 |
Pac | +0.150 |
Spur | +0.148 |
Neg logit contributions | |
)", | -0.197 |
uyomi | -0.171 |
ingo | -0.170 |
glers | -0.169 |
harm | -0.164 |
Token | the |
Token ID | 262 |
Feature activation | +9.03e-03 |
Pos logit contributions | |
smoot | +0.018 |
fres | +0.017 |
ans | +0.017 |
Pac | +0.017 |
Spur | +0.017 |
Neg logit contributions | |
)", | -0.022 |
glers | -0.019 |
uyomi | -0.019 |
ingo | -0.019 |
harm | -0.019 |
Token | pots |
Token ID | 32195 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
)", | +0.007 |
uyomi | +0.006 |
ingo | +0.006 |
glers | +0.006 |
harm | +0.006 |
Neg logit contributions | |
smoot | -0.006 |
fres | -0.006 |
ans | -0.006 |
Pac | -0.006 |
Spur | -0.005 |
Token | that |
Token ID | 326 |
Feature activation | -7.46e-02 |
Pos logit contributions | |
smoot | +0.071 |
fres | +0.066 |
ans | +0.065 |
Pac | +0.064 |
Spur | +0.063 |
Neg logit contributions | |
)", | -0.083 |
uyomi | -0.072 |
ingo | -0.072 |
glers | -0.072 |
emale | -0.069 |
Token | are |
Token ID | 389 |
Feature activation | +5.27e-02 |
Pos logit contributions | |
smoot | +0.049 |
fres | +0.046 |
ans | +0.045 |
Pac | +0.044 |
Spur | +0.043 |
Neg logit contributions | |
)", | -0.063 |
uyomi | -0.055 |
glers | -0.054 |
ingo | -0.054 |
harm | -0.053 |
Token | in |
Token ID | 287 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
)", | +0.046 |
ingo | +0.041 |
uyomi | +0.040 |
glers | +0.040 |
harm | +0.039 |
Neg logit contributions | |
smoot | -0.032 |
ans | -0.030 |
fres | -0.029 |
Pac | -0.029 |
Spur | -0.029 |
Token | fact |
Token ID | 1109 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
)", | +0.039 |
ingo | +0.033 |
uyomi | +0.033 |
glers | +0.033 |
harm | +0.033 |
Neg logit contributions | |
smoot | -0.033 |
fres | -0.031 |
ans | -0.031 |
Pac | -0.030 |
Spur | -0.029 |
Token | capable |
Token ID | 6007 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
)", | +0.200 |
ingo | +0.173 |
glers | +0.171 |
uyomi | +0.171 |
harm | +0.168 |
Neg logit contributions | |
smoot | -0.152 |
ans | -0.141 |
Pac | -0.141 |
fres | -0.140 |
Spur | -0.137 |
Token | of |
Token ID | 286 |
Feature activation | +7.40e-02 |
Pos logit contributions | |
smoot | +0.177 |
fres | +0.166 |
ans | +0.164 |
Pac | +0.161 |
Spur | +0.159 |
Neg logit contributions | |
)", | -0.216 |
uyomi | -0.187 |
ingo | -0.187 |
glers | -0.186 |
harm | -0.180 |
Token | producing |
Token ID | 9194 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
)", | +0.057 |
uyomi | +0.049 |
ingo | +0.049 |
glers | +0.048 |
harm | +0.047 |
Neg logit contributions | |
smoot | -0.054 |
fres | -0.051 |
ans | -0.050 |
Pac | -0.050 |
Spur | -0.049 |
Token | he |
Token ID | 339 |
Feature activation | -9.41e-02 |
Pos logit contributions | |
smoot | +0.088 |
fres | +0.084 |
ans | +0.082 |
Pac | +0.081 |
Spur | +0.079 |
Neg logit contributions | |
)", | -0.084 |
uyomi | -0.071 |
ingo | -0.071 |
glers | -0.071 |
emale | -0.069 |
Token | says |
Token ID | 1139 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
smoot | +0.066 |
fres | +0.062 |
ans | +0.061 |
Pac | +0.060 |
Spur | +0.059 |
Neg logit contributions | |
)", | -0.075 |
uyomi | -0.065 |
ingo | -0.065 |
glers | -0.064 |
harm | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
smoot | +0.096 |
fres | +0.090 |
ans | +0.089 |
Pac | +0.087 |
Spur | +0.085 |
Neg logit contributions | |
)", | -0.121 |
uyomi | -0.106 |
ingo | -0.105 |
glers | -0.105 |
emale | -0.102 |
Token |
|
Token ID | 198 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
smoot | +0.139 |
fres | +0.131 |
ans | +0.127 |
Pac | +0.125 |
chev | +0.123 |
Neg logit contributions | |
)", | -0.173 |
ingo | -0.148 |
uyomi | -0.148 |
glers | -0.148 |
harm | -0.144 |
Token |
|
Token ID | 198 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
smoot | +0.123 |
fres | +0.116 |
ans | +0.113 |
Pac | +0.110 |
Spur | +0.109 |
Neg logit contributions | |
)", | -0.168 |
ingo | -0.146 |
uyomi | -0.145 |
glers | -0.145 |
harm | -0.142 |
Token | Fake |
Token ID | 49233 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
smoot | +0.173 |
fres | +0.164 |
ans | +0.160 |
Pac | +0.156 |
Spur | +0.156 |
Neg logit contributions | |
)", | -0.149 |
ingo | -0.125 |
uyomi | -0.124 |
glers | -0.124 |
harm | -0.121 |
Token | - |
Token ID | 12 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
smoot | +0.160 |
fres | +0.150 |
ans | +0.147 |
Pac | +0.145 |
Spur | +0.142 |
Neg logit contributions | |
)", | -0.216 |
uyomi | -0.189 |
ingo | -0.188 |
glers | -0.188 |
emale | -0.182 |
Token | data |
Token ID | 7890 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
)", | +0.128 |
ingo | +0.112 |
uyomi | +0.111 |
glers | +0.111 |
harm | +0.109 |
Neg logit contributions | |
smoot | -0.103 |
fres | -0.097 |
ans | -0.093 |
Pac | -0.092 |
Spur | -0.091 |
Token | challenges |
Token ID | 6459 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
smoot | +0.148 |
fres | +0.140 |
ans | +0.137 |
Pac | +0.137 |
Spur | +0.133 |
Neg logit contributions | |
)", | -0.180 |
glers | -0.156 |
ingo | -0.156 |
uyomi | -0.155 |
harm | -0.151 |
Token | have |
Token ID | 423 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
)", | +0.123 |
ingo | +0.107 |
glers | +0.106 |
uyomi | +0.106 |
harm | +0.103 |
Neg logit contributions | |
smoot | -0.099 |
fres | -0.093 |
ans | -0.091 |
Pac | -0.090 |
chev | -0.088 |
Token | been |
Token ID | 587 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
)", | +0.046 |
ingo | +0.040 |
glers | +0.040 |
uyomi | +0.040 |
harm | +0.039 |
Neg logit contributions | |
smoot | -0.031 |
fres | -0.029 |
Pac | -0.029 |
ans | -0.029 |
chev | -0.028 |
Token | version |
Token ID | 2196 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
smoot | +0.158 |
fres | +0.151 |
ans | +0.147 |
Pac | +0.146 |
chev | +0.145 |
Neg logit contributions | |
)", | -0.151 |
ingo | -0.129 |
uyomi | -0.129 |
glers | -0.127 |
emale | -0.124 |
Token | will |
Token ID | 481 |
Feature activation | -7.22e-02 |
Pos logit contributions | |
)", | +0.523 |
ingo | +0.457 |
uyomi | +0.449 |
glers | +0.447 |
emale | +0.439 |
Neg logit contributions | |
smoot | -0.457 |
fres | -0.433 |
ans | -0.424 |
Pac | -0.421 |
Spur | -0.418 |
Token | be |
Token ID | 307 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
smoot | +0.049 |
fres | +0.046 |
ans | +0.046 |
Pac | +0.045 |
Spur | +0.044 |
Neg logit contributions | |
)", | -0.059 |
uyomi | -0.051 |
ingo | -0.051 |
glers | -0.050 |
emale | -0.049 |
Token | with |
Token ID | 351 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
smoot | +0.030 |
fres | +0.029 |
ans | +0.028 |
Pac | +0.028 |
Spur | +0.028 |
Neg logit contributions | |
)", | -0.033 |
ingo | -0.029 |
uyomi | -0.029 |
glers | -0.028 |
emale | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
smoot | +0.020 |
fres | +0.019 |
ans | +0.018 |
Pac | +0.018 |
chev | +0.018 |
Neg logit contributions | |
)", | -0.028 |
ingo | -0.025 |
uyomi | -0.024 |
glers | -0.024 |
emale | -0.024 |
Token | PC |
Token ID | 4217 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
smoot | +0.138 |
fres | +0.131 |
ans | +0.129 |
Pac | +0.127 |
chev | +0.127 |
Neg logit contributions | |
)", | -0.151 |
ingo | -0.131 |
uyomi | -0.129 |
glers | -0.128 |
emale | -0.125 |
Token | version |
Token ID | 2196 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
smoot | +0.553 |
fres | +0.517 |
ans | +0.503 |
Pac | +0.493 |
Spur | +0.485 |
Neg logit contributions | |
)", | -0.883 |
ingo | -0.779 |
uyomi | -0.779 |
glers | -0.769 |
emale | -0.757 |
Token | upon |
Token ID | 2402 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
)", | +0.390 |
ingo | +0.339 |
uyomi | +0.336 |
glers | +0.334 |
emale | +0.324 |
Neg logit contributions | |
smoot | -0.349 |
fres | -0.330 |
ans | -0.323 |
Pac | -0.320 |
Spur | -0.317 |
Token | its |
Token ID | 663 |
Feature activation | -5.07e-02 |
Pos logit contributions | |
)", | +0.268 |
ingo | +0.234 |
uyomi | +0.228 |
glers | +0.228 |
emale | +0.224 |
Neg logit contributions | |
smoot | -0.209 |
fres | -0.197 |
ans | -0.195 |
Pac | -0.193 |
chev | -0.191 |
Token | release |
Token ID | 2650 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
smoot | +0.034 |
fres | +0.032 |
ans | +0.032 |
Pac | +0.031 |
chev | +0.031 |
Neg logit contributions | |
)", | -0.041 |
ingo | -0.036 |
uyomi | -0.035 |
glers | -0.035 |
emale | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
)", | +0.292 |
ingo | +0.253 |
uyomi | +0.249 |
glers | +0.248 |
emale | +0.242 |
Neg logit contributions | |
smoot | -0.255 |
fres | -0.240 |
ans | -0.236 |
Pac | -0.232 |
Spur | -0.230 |
Token | drives |
Token ID | 10182 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
smoot | +0.056 |
fres | +0.053 |
ans | +0.052 |
Pac | +0.051 |
chev | +0.050 |
Neg logit contributions | |
)", | -0.078 |
glers | -0.068 |
ingo | -0.068 |
uyomi | -0.068 |
emale | -0.066 |
Token | them |
Token ID | 606 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
)", | +0.303 |
ingo | +0.263 |
glers | +0.262 |
uyomi | +0.260 |
emale | +0.253 |
Neg logit contributions | |
smoot | -0.260 |
fres | -0.245 |
ans | -0.241 |
Pac | -0.237 |
chev | -0.235 |
Token | toward |
Token ID | 3812 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
)", | +0.081 |
ingo | +0.071 |
glers | +0.070 |
uyomi | +0.069 |
harm | +0.068 |
Neg logit contributions | |
smoot | -0.069 |
fres | -0.065 |
ans | -0.064 |
Pac | -0.064 |
chev | -0.063 |
Token | developing |
Token ID | 5922 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
smoot | +0.397 |
fres | +0.373 |
ans | +0.369 |
Pac | +0.361 |
Spur | +0.354 |
Neg logit contributions | |
)", | -0.504 |
ingo | -0.438 |
uyomi | -0.437 |
glers | -0.435 |
emale | -0.423 |
Token | new |
Token ID | 649 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
)", | +0.229 |
ingo | +0.199 |
uyomi | +0.199 |
glers | +0.198 |
harm | +0.193 |
Neg logit contributions | |
smoot | -0.176 |
fres | -0.164 |
ans | -0.162 |
Pac | -0.159 |
chev | -0.157 |
Token | Metroid |
Token ID | 45430 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
smoot | +0.021 |
fres | +0.019 |
ans | +0.019 |
Pac | +0.019 |
Spur | +0.018 |
Neg logit contributions | |
)", | -0.024 |
uyomi | -0.021 |
ingo | -0.020 |
glers | -0.020 |
emale | -0.020 |
Token | v |
Token ID | 85 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
smoot | +0.662 |
fres | +0.625 |
ans | +0.614 |
Pac | +0.600 |
Spur | +0.590 |
Neg logit contributions | |
)", | -0.772 |
uyomi | -0.671 |
ingo | -0.664 |
glers | -0.662 |
emale | -0.648 |
Token | ania |
Token ID | 5411 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
smoot | +0.176 |
fres | +0.165 |
Spur | +0.160 |
Fedora | +0.158 |
Pac | +0.157 |
Neg logit contributions | |
)", | -0.170 |
ingo | -0.146 |
uyomi | -0.144 |
glers | -0.143 |
harm | -0.140 |
Token | games |
Token ID | 1830 |
Feature activation | +6.35e-02 |
Pos logit contributions | |
smoot | +0.289 |
fres | +0.272 |
ans | +0.267 |
Pac | +0.261 |
Spur | +0.258 |
Neg logit contributions | |
)", | -0.356 |
uyomi | -0.310 |
ingo | -0.308 |
glers | -0.306 |
emale | -0.299 |
Token | . |
Token ID | 13 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
)", | +0.051 |
ingo | +0.044 |
uyomi | +0.044 |
glers | +0.044 |
harm | +0.043 |
Neg logit contributions | |
smoot | -0.044 |
fres | -0.041 |
ans | -0.040 |
Pac | -0.040 |
Spur | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
smoot | +0.170 |
fres | +0.159 |
ans | +0.155 |
Pac | +0.151 |
chev | +0.150 |
Neg logit contributions | |
)", | -0.199 |
ingo | -0.172 |
glers | -0.171 |
uyomi | -0.169 |
harm | -0.165 |
Token | ' |
Token ID | 6 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
smoot | +0.325 |
fres | +0.308 |
ans | +0.301 |
Pac | +0.294 |
Spur | +0.293 |
Neg logit contributions | |
)", | -0.308 |
ingo | -0.263 |
uyomi | -0.260 |
glers | -0.259 |
emale | -0.253 |
Token | sc |
Token ID | 629 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
)", | +0.129 |
ingo | +0.114 |
glers | +0.112 |
uyomi | +0.111 |
harm | +0.109 |
Neg logit contributions | |
smoot | -0.090 |
fres | -0.084 |
ans | -0.083 |
Pac | -0.082 |
chev | -0.080 |
Token | rawled |
Token ID | 49263 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
)", | +0.209 |
ingo | +0.183 |
harm | +0.178 |
glers | +0.178 |
uyomi | +0.177 |
Neg logit contributions | |
smoot | -0.159 |
fres | -0.151 |
Pac | -0.145 |
chev | -0.143 |
Spur | -0.142 |
Token | in |
Token ID | 287 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
)", | +0.153 |
ingo | +0.130 |
uyomi | +0.128 |
glers | +0.127 |
harm | +0.125 |
Neg logit contributions | |
smoot | -0.138 |
fres | -0.131 |
ans | -0.130 |
Pac | -0.130 |
chev | -0.127 |
Token | large |
Token ID | 1588 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
smoot | +0.028 |
fres | +0.026 |
ans | +0.025 |
Pac | +0.025 |
chev | +0.024 |
Neg logit contributions | |
)", | -0.041 |
ingo | -0.035 |
uyomi | -0.035 |
glers | -0.035 |
harm | -0.034 |
Token | letters |
Token ID | 7475 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
smoot | +0.167 |
fres | +0.157 |
ans | +0.155 |
Pac | +0.153 |
chev | +0.148 |
Neg logit contributions | |
)", | -0.225 |
ingo | -0.195 |
uyomi | -0.194 |
glers | -0.192 |
emale | -0.188 |
Token | across |
Token ID | 1973 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
smoot | +0.596 |
fres | +0.564 |
ans | +0.559 |
Pac | +0.550 |
chev | +0.538 |
Neg logit contributions | |
)", | -0.683 |
ingo | -0.584 |
glers | -0.578 |
uyomi | -0.578 |
harm | -0.562 |
Token | the |
Token ID | 262 |
Feature activation | -8.00e-02 |
Pos logit contributions | |
smoot | +0.067 |
fres | +0.062 |
ans | +0.062 |
Pac | +0.060 |
chev | +0.058 |
Neg logit contributions | |
)", | -0.105 |
uyomi | -0.091 |
ingo | -0.091 |
glers | -0.090 |
harm | -0.088 |
Token | bottom |
Token ID | 4220 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
smoot | +0.042 |
fres | +0.039 |
ans | +0.039 |
Pac | +0.039 |
chev | +0.037 |
Neg logit contributions | |
)", | -0.077 |
ingo | -0.067 |
uyomi | -0.067 |
glers | -0.066 |
Militia | -0.065 |
Token | half |
Token ID | 2063 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
smoot | +0.414 |
fres | +0.389 |
ans | +0.386 |
Pac | +0.382 |
chev | +0.370 |
Neg logit contributions | |
)", | -0.515 |
ingo | -0.440 |
uyomi | -0.440 |
glers | -0.434 |
harm | -0.425 |
Token | of |
Token ID | 286 |
Feature activation | -8.50e-02 |
Pos logit contributions | |
)", | +0.331 |
uyomi | +0.287 |
ingo | +0.284 |
glers | +0.280 |
emale | +0.276 |
Neg logit contributions | |
smoot | -0.280 |
fres | -0.264 |
ans | -0.260 |
Pac | -0.255 |
Spur | -0.251 |
Token | . |
Token ID | 13 |
Feature activation | +5.72e-02 |
Pos logit contributions | |
)", | +0.064 |
ingo | +0.055 |
uyomi | +0.055 |
glers | +0.055 |
harm | +0.054 |
Neg logit contributions | |
smoot | -0.057 |
fres | -0.053 |
ans | -0.053 |
Pac | -0.051 |
chev | -0.051 |
Token | He |
Token ID | 679 |
Feature activation | +7.21e-03 |
Pos logit contributions | |
)", | +0.046 |
ingo | +0.040 |
glers | +0.040 |
uyomi | +0.040 |
harm | +0.039 |
Neg logit contributions | |
smoot | -0.040 |
fres | -0.037 |
ans | -0.036 |
Pac | -0.035 |
chev | -0.035 |
Token | said |
Token ID | 531 |
Feature activation | +8.23e-02 |
Pos logit contributions | |
)", | +0.007 |
ingo | +0.006 |
glers | +0.006 |
uyomi | +0.006 |
harm | +0.006 |
Neg logit contributions | |
smoot | -0.004 |
fres | -0.004 |
ans | -0.004 |
Pac | -0.004 |
Spur | -0.004 |
Token | [ |
Token ID | 685 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
)", | +0.066 |
glers | +0.056 |
ingo | +0.056 |
uyomi | +0.056 |
harm | +0.054 |
Neg logit contributions | |
smoot | -0.058 |
fres | -0.054 |
ans | -0.054 |
Pac | -0.053 |
chev | -0.052 |
Token | ass |
Token ID | 562 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
)", | +0.219 |
ingo | +0.192 |
glers | +0.191 |
harm | +0.189 |
uyomi | +0.189 |
Neg logit contributions | |
smoot | -0.165 |
fres | -0.153 |
ans | -0.146 |
Spur | -0.143 |
Fedora | -0.143 |
Token | istant |
Token ID | 10167 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
)", | +0.205 |
ingo | +0.175 |
uyomi | +0.174 |
glers | +0.174 |
emale | +0.169 |
Neg logit contributions | |
smoot | -0.200 |
fres | -0.191 |
ans | -0.182 |
Pac | -0.182 |
Spur | -0.180 |
Token | coach |
Token ID | 3985 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
smoot | +0.493 |
fres | +0.459 |
ans | +0.446 |
Pac | +0.436 |
chev | +0.427 |
Neg logit contributions | |
)", | -0.808 |
uyomi | -0.713 |
ingo | -0.713 |
glers | -0.707 |
emale | -0.692 |
Token | ] |
Token ID | 60 |
Feature activation | -9.01e-02 |
Pos logit contributions | |
smoot | +0.348 |
fres | +0.327 |
ans | +0.320 |
Pac | +0.313 |
chev | +0.309 |
Neg logit contributions | |
)", | -0.413 |
uyomi | -0.357 |
ingo | -0.357 |
glers | -0.354 |
emale | -0.346 |
Token | Ju |
Token ID | 12585 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
smoot | +0.062 |
fres | +0.059 |
ans | +0.058 |
Pac | +0.056 |
chev | +0.056 |
Neg logit contributions | |
)", | -0.073 |
ingo | -0.063 |
uyomi | -0.062 |
glers | -0.062 |
harm | -0.061 |
Token | wan |
Token ID | 8149 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
smoot | +0.200 |
fres | +0.184 |
ans | +0.178 |
Pac | +0.175 |
Spur | +0.170 |
Neg logit contributions | |
)", | -0.367 |
uyomi | -0.325 |
ingo | -0.324 |
glers | -0.323 |
emale | -0.318 |
Token | Howard |
Token ID | 8442 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
)", | +0.488 |
ingo | +0.424 |
uyomi | +0.414 |
emale | +0.407 |
glers | +0.405 |
Neg logit contributions | |
smoot | -0.412 |
fres | -0.385 |
ans | -0.374 |
Pac | -0.367 |
chev | -0.362 |
Token | of |
Token ID | 286 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
)", | +0.134 |
uyomi | +0.115 |
glers | +0.115 |
ingo | +0.114 |
harm | +0.110 |
Neg logit contributions | |
smoot | -0.113 |
fres | -0.107 |
ans | -0.105 |
Pac | -0.104 |
Spur | -0.102 |
Token | the |
Token ID | 262 |
Feature activation | +5.12e-02 |
Pos logit contributions | |
)", | +0.093 |
ingo | +0.081 |
uyomi | +0.081 |
glers | +0.080 |
harm | +0.078 |
Neg logit contributions | |
smoot | -0.071 |
fres | -0.067 |
ans | -0.065 |
Pac | -0.064 |
Spur | -0.063 |
Token | game |
Token ID | 983 |
Feature activation | +9.30e-02 |
Pos logit contributions | |
)", | +0.042 |
uyomi | +0.036 |
ingo | +0.036 |
glers | +0.036 |
emale | +0.035 |
Neg logit contributions | |
smoot | -0.035 |
fres | -0.033 |
ans | -0.033 |
Pac | -0.032 |
Spur | -0.031 |
Token | ," |
Token ID | 553 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
)", | +0.073 |
glers | +0.063 |
uyomi | +0.063 |
ingo | +0.063 |
harm | +0.060 |
Neg logit contributions | |
smoot | -0.066 |
fres | -0.062 |
ans | -0.062 |
Pac | -0.061 |
Spur | -0.060 |
Token | longtime |
Token ID | 15076 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
)", | +0.207 |
ingo | +0.178 |
uyomi | +0.178 |
glers | +0.177 |
emale | +0.173 |
Neg logit contributions | |
smoot | -0.175 |
fres | -0.164 |
ans | -0.161 |
Pac | -0.159 |
chev | -0.156 |
Token | Metroid |
Token ID | 45430 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
smoot | +0.235 |
fres | +0.219 |
ans | +0.216 |
Pac | +0.212 |
chev | +0.208 |
Neg logit contributions | |
)", | -0.306 |
ingo | -0.267 |
uyomi | -0.266 |
glers | -0.265 |
emale | -0.259 |
Token | series |
Token ID | 2168 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
smoot | +0.468 |
fres | +0.435 |
ans | +0.423 |
Pac | +0.412 |
Spur | +0.405 |
Neg logit contributions | |
)", | -0.805 |
uyomi | -0.714 |
ingo | -0.713 |
glers | -0.709 |
emale | -0.693 |
Token | developer |
Token ID | 8517 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
smoot | +0.066 |
fres | +0.062 |
ans | +0.060 |
Pac | +0.059 |
chev | +0.058 |
Neg logit contributions | |
)", | -0.102 |
ingo | -0.090 |
uyomi | -0.090 |
glers | -0.090 |
harm | -0.087 |
Token | Yosh |
Token ID | 28563 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
smoot | +0.339 |
fres | +0.318 |
ans | +0.312 |
Pac | +0.307 |
chev | +0.302 |
Neg logit contributions | |
)", | -0.385 |
ingo | -0.331 |
uyomi | -0.330 |
glers | -0.327 |
harm | -0.320 |
Token | io |
Token ID | 952 |
Feature activation | -8.05e-03 |
Pos logit contributions | |
smoot | +0.532 |
fres | +0.500 |
ans | +0.481 |
Pac | +0.477 |
scoop | +0.469 |
Neg logit contributions | |
)", | -0.683 |
ingo | -0.592 |
uyomi | -0.590 |
glers | -0.579 |
harm | -0.573 |
Token | Sak |
Token ID | 13231 |
Feature activation | +5.53e-02 |
Pos logit contributions | |
smoot | +0.004 |
fres | +0.004 |
ans | +0.004 |
Pac | +0.004 |
chev | +0.004 |
Neg logit contributions | |
)", | -0.008 |
ingo | -0.007 |
uyomi | -0.007 |
glers | -0.007 |
emale | -0.007 |