Token | open |
Token ID | 1280 |
Feature activation | +7.38e-02 |
Pos logit contributions | |
quart | +0.160 |
bucket | +0.154 |
strap | +0.146 |
mant | +0.142 |
otaur | +0.141 |
Neg logit contributions | |
awk | -0.221 |
argon | -0.216 |
Cheney | -0.192 |
olicy | -0.184 |
lam | -0.182 |
Token | my |
Token ID | 616 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
quart | +0.141 |
bucket | +0.135 |
otaur | +0.127 |
strap | +0.126 |
mant | +0.125 |
Neg logit contributions | |
awk | -0.184 |
argon | -0.178 |
Cheney | -0.160 |
lam | -0.153 |
olicy | -0.151 |
Token | mouth |
Token ID | 5422 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
quart | +0.048 |
bucket | +0.045 |
strap | +0.041 |
otaur | +0.041 |
mant | +0.040 |
Neg logit contributions | |
awk | -0.109 |
argon | -0.106 |
Cheney | -0.097 |
lam | -0.093 |
olicy | -0.092 |
Token | and |
Token ID | 290 |
Feature activation | +4.16e-02 |
Pos logit contributions | |
quart | +0.572 |
bucket | +0.549 |
strap | +0.515 |
otaur | +0.510 |
mant | +0.506 |
Neg logit contributions | |
awk | -0.759 |
argon | -0.740 |
Cheney | -0.659 |
lam | -0.627 |
olicy | -0.625 |
Token | her |
Token ID | 607 |
Feature activation | +9.42e-02 |
Pos logit contributions | |
quart | +0.075 |
bucket | +0.073 |
strap | +0.069 |
mant | +0.067 |
otaur | +0.066 |
Neg logit contributions | |
awk | -0.109 |
argon | -0.106 |
Cheney | -0.094 |
olicy | -0.091 |
lam | -0.090 |
Token | tongue |
Token ID | 11880 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
quart | +0.137 |
bucket | +0.130 |
strap | +0.119 |
otaur | +0.117 |
mant | +0.116 |
Neg logit contributions | |
awk | -0.280 |
argon | -0.273 |
Cheney | -0.248 |
lam | -0.239 |
olicy | -0.238 |
Token | sl |
Token ID | 1017 |
Feature activation | +6.81e-02 |
Pos logit contributions | |
quart | +1.244 |
bucket | +1.202 |
strap | +1.133 |
mant | +1.111 |
otaur | +1.077 |
Neg logit contributions | |
awk | -1.725 |
argon | -1.691 |
Cheney | -1.490 |
olicy | -1.453 |
lam | -1.419 |
Token | ither |
Token ID | 1555 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
quart | +0.156 |
bucket | +0.152 |
otaur | +0.147 |
strap | +0.146 |
mant | +0.143 |
Neg logit contributions | |
awk | -0.138 |
argon | -0.134 |
Cheney | -0.122 |
olicy | -0.111 |
GOP | -0.109 |
Token | s |
Token ID | 82 |
Feature activation | +5.92e-02 |
Pos logit contributions | |
quart | +0.209 |
bucket | +0.200 |
strap | +0.188 |
otaur | +0.186 |
mant | +0.185 |
Neg logit contributions | |
awk | -0.275 |
argon | -0.268 |
Cheney | -0.238 |
olicy | -0.228 |
lam | -0.227 |
Token | into |
Token ID | 656 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
quart | +0.111 |
bucket | +0.107 |
strap | +0.100 |
mant | +0.098 |
otaur | +0.098 |
Neg logit contributions | |
awk | -0.151 |
argon | -0.147 |
Cheney | -0.131 |
olicy | -0.125 |
lam | -0.125 |
Token | mine |
Token ID | 6164 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
quart | +0.034 |
bucket | +0.032 |
otaur | +0.030 |
strap | +0.030 |
mant | +0.030 |
Neg logit contributions | |
awk | -0.044 |
argon | -0.043 |
Cheney | -0.038 |
lam | -0.037 |
olicy | -0.036 |
Token | a |
Token ID | 257 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
quart | +0.103 |
bucket | +0.097 |
strap | +0.089 |
otaur | +0.088 |
mant | +0.087 |
Neg logit contributions | |
awk | -0.210 |
argon | -0.205 |
Cheney | -0.186 |
lam | -0.179 |
olicy | -0.178 |
Token | week |
Token ID | 1285 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
quart | +0.033 |
bucket | +0.032 |
otaur | +0.029 |
strap | +0.029 |
mant | +0.029 |
Neg logit contributions | |
awk | -0.061 |
argon | -0.060 |
Cheney | -0.054 |
lam | -0.052 |
olicy | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | +4.28e-02 |
Pos logit contributions | |
quart | +0.027 |
bucket | +0.026 |
strap | +0.025 |
otaur | +0.025 |
mant | +0.024 |
Neg logit contributions | |
awk | -0.033 |
argon | -0.032 |
Cheney | -0.028 |
lam | -0.027 |
olicy | -0.027 |
Token | Russian |
Token ID | 3394 |
Feature activation | -7.54e-02 |
Pos logit contributions | |
quart | +0.089 |
bucket | +0.086 |
otaur | +0.081 |
strap | +0.080 |
mant | +0.079 |
Neg logit contributions | |
awk | -0.100 |
argon | -0.097 |
Cheney | -0.085 |
lam | -0.081 |
olicy | -0.081 |
Token | TV |
Token ID | 3195 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
awk | +0.158 |
argon | +0.153 |
Cheney | +0.131 |
lam | +0.126 |
olicy | +0.125 |
Neg logit contributions | |
quart | -0.177 |
bucket | -0.171 |
strap | -0.162 |
otaur | -0.159 |
mant | -0.159 |
Token | stations |
Token ID | 8985 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
quart | +0.366 |
bucket | +0.352 |
strap | +0.336 |
mant | +0.328 |
otaur | +0.328 |
Neg logit contributions | |
awk | -0.369 |
argon | -0.355 |
Cheney | -0.313 |
olicy | -0.299 |
lam | -0.296 |
Token | showed |
Token ID | 3751 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
quart | +1.381 |
bucket | +1.331 |
strap | +1.275 |
mant | +1.235 |
otaur | +1.230 |
Neg logit contributions | |
awk | -1.406 |
argon | -1.379 |
Cheney | -1.182 |
olicy | -1.176 |
lam | -1.121 |
Token | a |
Token ID | 257 |
Feature activation | +4.35e-02 |
Pos logit contributions | |
awk | +0.077 |
argon | +0.075 |
Cheney | +0.067 |
lam | +0.064 |
olicy | +0.064 |
Neg logit contributions | |
quart | -0.052 |
bucket | -0.050 |
strap | -0.047 |
otaur | -0.046 |
mant | -0.046 |
Token | Gaz |
Token ID | 21347 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
quart | +0.079 |
bucket | +0.076 |
strap | +0.071 |
mant | +0.069 |
otaur | +0.069 |
Neg logit contributions | |
awk | -0.115 |
argon | -0.112 |
Cheney | -0.099 |
olicy | -0.096 |
lam | -0.096 |
Token | prom |
Token ID | 16963 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
awk | +0.270 |
argon | +0.262 |
Cheney | +0.237 |
olicy | +0.228 |
lam | +0.223 |
Neg logit contributions | |
quart | -0.199 |
bucket | -0.190 |
strap | -0.178 |
otaur | -0.177 |
ça | -0.173 |
Token | official |
Token ID | 1743 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
awk | +0.275 |
argon | +0.267 |
Cheney | +0.237 |
lam | +0.226 |
olicy | +0.224 |
Neg logit contributions | |
quart | -0.226 |
bucket | -0.217 |
strap | -0.204 |
otaur | -0.203 |
mant | -0.200 |
Token | Russia |
Token ID | 3284 |
Feature activation | -9.17e-02 |
Pos logit contributions | |
awk | +0.035 |
argon | +0.034 |
Cheney | +0.030 |
olicy | +0.029 |
lam | +0.029 |
Neg logit contributions | |
quart | -0.018 |
bucket | -0.017 |
strap | -0.016 |
otaur | -0.016 |
mant | -0.016 |
Token | 116 |
Token ID | 18693 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
awk | +0.240 |
argon | +0.234 |
Cheney | +0.206 |
olicy | +0.199 |
lam | +0.199 |
Neg logit contributions | |
quart | -0.168 |
bucket | -0.160 |
strap | -0.149 |
otaur | -0.147 |
mant | -0.147 |
Token |
|
Token ID | 198 |
Feature activation | -8.01e-03 |
Pos logit contributions | |
quart | +0.019 |
bucket | +0.018 |
otaur | +0.017 |
strap | +0.017 |
mant | +0.017 |
Neg logit contributions | |
awk | -0.028 |
argon | -0.028 |
Cheney | -0.025 |
lam | -0.024 |
olicy | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
awk | +0.020 |
argon | +0.019 |
Cheney | +0.017 |
olicy | +0.017 |
lam | +0.016 |
Neg logit contributions | |
quart | -0.015 |
bucket | -0.015 |
strap | -0.014 |
mant | -0.014 |
otaur | -0.014 |
Token | Re |
Token ID | 3041 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
quart | +0.042 |
bucket | +0.041 |
otaur | +0.038 |
strap | +0.038 |
mant | +0.038 |
Neg logit contributions | |
awk | -0.039 |
argon | -0.037 |
Cheney | -0.033 |
olicy | -0.031 |
lam | -0.031 |
Token | asons |
Token ID | 2812 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
quart | +0.257 |
bucket | +0.247 |
strap | +0.232 |
otaur | +0.232 |
mant | +0.228 |
Neg logit contributions | |
awk | -0.318 |
argon | -0.308 |
Cheney | -0.274 |
lam | -0.262 |
olicy | -0.259 |
Token | for |
Token ID | 329 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
quart | +1.205 |
bucket | +1.163 |
strap | +1.091 |
mant | +1.079 |
otaur | +1.073 |
Neg logit contributions | |
awk | -1.345 |
argon | -1.303 |
Cheney | -1.146 |
lam | -1.089 |
olicy | -1.089 |
Token | national |
Token ID | 2260 |
Feature activation | -7.40e-02 |
Pos logit contributions | |
quart | +0.034 |
bucket | +0.033 |
strap | +0.031 |
mant | +0.030 |
otaur | +0.030 |
Neg logit contributions | |
awk | -0.040 |
argon | -0.039 |
Cheney | -0.035 |
olicy | -0.033 |
lam | -0.033 |
Token | debt |
Token ID | 5057 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
awk | +0.207 |
argon | +0.201 |
Cheney | +0.182 |
lam | +0.175 |
olicy | +0.173 |
Neg logit contributions | |
quart | -0.119 |
bucket | -0.114 |
otaur | -0.105 |
strap | -0.105 |
mant | -0.103 |
Token |
|
Token ID | 198 |
Feature activation | +7.39e-02 |
Pos logit contributions | |
quart | +0.296 |
bucket | +0.284 |
strap | +0.267 |
otaur | +0.266 |
mant | +0.263 |
Neg logit contributions | |
awk | -0.359 |
argon | -0.348 |
Cheney | -0.309 |
lam | -0.295 |
olicy | -0.292 |
Token |
|
Token ID | 198 |
Feature activation | +7.08e-02 |
Pos logit contributions | |
quart | +0.141 |
bucket | +0.136 |
mant | +0.125 |
strap | +0.125 |
otaur | +0.123 |
Neg logit contributions | |
awk | -0.184 |
argon | -0.181 |
Cheney | -0.159 |
olicy | -0.158 |
lam | -0.150 |
Token | calibration |
Token ID | 36537 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
awk | +0.198 |
argon | +0.193 |
Cheney | +0.172 |
lam | +0.165 |
olicy | +0.164 |
Neg logit contributions | |
quart | -0.142 |
bucket | -0.136 |
strap | -0.127 |
otaur | -0.125 |
mant | -0.125 |
Token | changes |
Token ID | 2458 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
awk | +0.438 |
argon | +0.425 |
Cheney | +0.376 |
lam | +0.359 |
olicy | +0.357 |
Neg logit contributions | |
quart | -0.362 |
bucket | -0.349 |
strap | -0.328 |
mant | -0.322 |
otaur | -0.322 |
Token | to |
Token ID | 284 |
Feature activation | +8.93e-02 |
Pos logit contributions | |
quart | +0.267 |
bucket | +0.258 |
strap | +0.241 |
mant | +0.237 |
otaur | +0.236 |
Neg logit contributions | |
awk | -0.353 |
argon | -0.345 |
Cheney | -0.306 |
lam | -0.291 |
olicy | -0.291 |
Token | its |
Token ID | 663 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
quart | +0.158 |
bucket | +0.153 |
strap | +0.142 |
mant | +0.139 |
otaur | +0.137 |
Neg logit contributions | |
awk | -0.238 |
argon | -0.234 |
Cheney | -0.207 |
olicy | -0.200 |
lam | -0.199 |
Token | power |
Token ID | 1176 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
quart | +0.088 |
bucket | +0.085 |
strap | +0.078 |
mant | +0.077 |
otaur | +0.077 |
Neg logit contributions | |
awk | -0.124 |
argon | -0.122 |
Cheney | -0.108 |
lam | -0.104 |
olicy | -0.103 |
Token | train |
Token ID | 27432 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
quart | +0.313 |
bucket | +0.300 |
strap | +0.280 |
otaur | +0.276 |
mant | +0.274 |
Neg logit contributions | |
awk | -0.457 |
argon | -0.446 |
Cheney | -0.399 |
lam | -0.381 |
olicy | -0.380 |
Token | , |
Token ID | 11 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
quart | +1.051 |
bucket | +1.020 |
strap | +0.950 |
mant | +0.933 |
otaur | +0.916 |
Neg logit contributions | |
awk | -1.416 |
argon | -1.381 |
Cheney | -1.217 |
lam | -1.168 |
olicy | -1.159 |
Token | dri |
Token ID | 1454 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
quart | +0.020 |
bucket | +0.020 |
strap | +0.018 |
mant | +0.018 |
otaur | +0.018 |
Neg logit contributions | |
awk | -0.026 |
argon | -0.026 |
Cheney | -0.023 |
lam | -0.022 |
olicy | -0.022 |
Token | vel |
Token ID | 626 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
quart | +0.494 |
bucket | +0.480 |
strap | +0.453 |
otaur | +0.451 |
mant | +0.444 |
Neg logit contributions | |
awk | -0.471 |
argon | -0.456 |
Cheney | -0.401 |
lam | -0.374 |
olicy | -0.373 |
Token | ine |
Token ID | 500 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
quart | +0.081 |
bucket | +0.078 |
strap | +0.075 |
otaur | +0.074 |
mant | +0.073 |
Neg logit contributions | |
awk | -0.087 |
argon | -0.084 |
Cheney | -0.074 |
olicy | -0.070 |
lam | -0.070 |
Token | , |
Token ID | 11 |
Feature activation | +9.81e-03 |
Pos logit contributions | |
quart | +0.440 |
bucket | +0.425 |
strap | +0.398 |
otaur | +0.391 |
mant | +0.391 |
Neg logit contributions | |
awk | -0.557 |
argon | -0.543 |
Cheney | -0.482 |
lam | -0.459 |
olicy | -0.456 |
Token | hard |
Token ID | 1327 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
quart | +0.267 |
bucket | +0.257 |
strap | +0.240 |
mant | +0.237 |
otaur | +0.234 |
Neg logit contributions | |
awk | -0.326 |
argon | -0.317 |
Cheney | -0.279 |
olicy | -0.268 |
lam | -0.265 |
Token | and |
Token ID | 290 |
Feature activation | +7.59e-02 |
Pos logit contributions | |
quart | +0.337 |
bucket | +0.324 |
strap | +0.304 |
mant | +0.300 |
otaur | +0.296 |
Neg logit contributions | |
awk | -0.422 |
argon | -0.411 |
Cheney | -0.363 |
olicy | -0.347 |
lam | -0.346 |
Token | you |
Token ID | 345 |
Feature activation | +6.35e-02 |
Pos logit contributions | |
quart | +0.143 |
bucket | +0.136 |
strap | +0.127 |
mant | +0.125 |
otaur | +0.124 |
Neg logit contributions | |
awk | -0.196 |
argon | -0.191 |
Cheney | -0.168 |
olicy | -0.162 |
lam | -0.161 |
Token | couldn |
Token ID | 3521 |
Feature activation | -6.58e-03 |
Pos logit contributions | |
quart | +0.126 |
bucket | +0.122 |
strap | +0.115 |
mant | +0.112 |
otaur | +0.111 |
Neg logit contributions | |
awk | -0.156 |
argon | -0.152 |
Cheney | -0.135 |
olicy | -0.129 |
lam | -0.127 |
Token | 't |
Token ID | 470 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
awk | +0.019 |
argon | +0.019 |
Cheney | +0.017 |
olicy | +0.016 |
lam | +0.016 |
Neg logit contributions | |
quart | -0.010 |
bucket | -0.009 |
strap | -0.009 |
mant | -0.009 |
otaur | -0.009 |
Token | fault |
Token ID | 8046 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
quart | +0.131 |
bucket | +0.128 |
strap | +0.121 |
mant | +0.118 |
otaur | +0.114 |
Neg logit contributions | |
awk | -0.164 |
argon | -0.160 |
Cheney | -0.143 |
olicy | -0.137 |
GOP | -0.135 |
Token | anybody |
Token ID | 9599 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
quart | +1.255 |
bucket | +1.212 |
strap | +1.137 |
mant | +1.131 |
otaur | +1.120 |
Neg logit contributions | |
awk | -1.202 |
argon | -1.168 |
Cheney | -0.998 |
olicy | -0.951 |
lam | -0.946 |
Token | . |
Token ID | 13 |
Feature activation | +6.48e-02 |
Pos logit contributions | |
quart | +0.291 |
bucket | +0.279 |
strap | +0.261 |
mant | +0.258 |
otaur | +0.255 |
Neg logit contributions | |
awk | -0.342 |
argon | -0.336 |
Cheney | -0.294 |
olicy | -0.282 |
lam | -0.279 |
Token | They |
Token ID | 1119 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
quart | +0.140 |
bucket | +0.135 |
mant | +0.126 |
otaur | +0.126 |
strap | +0.125 |
Neg logit contributions | |
awk | -0.146 |
argon | -0.142 |
Cheney | -0.122 |
olicy | -0.118 |
lam | -0.118 |
Token | showed |
Token ID | 3751 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
quart | +0.235 |
bucket | +0.225 |
strap | +0.210 |
mant | +0.207 |
otaur | +0.205 |
Neg logit contributions | |
awk | -0.317 |
argon | -0.310 |
Cheney | -0.276 |
olicy | -0.265 |
lam | -0.263 |
Token | character |
Token ID | 2095 |
Feature activation | -4.62e-02 |
Pos logit contributions | |
awk | +0.318 |
argon | +0.309 |
Cheney | +0.272 |
olicy | +0.260 |
lam | +0.260 |
Neg logit contributions | |
quart | -0.257 |
bucket | -0.247 |
strap | -0.231 |
mant | -0.228 |
otaur | -0.227 |
Token | to |
Token ID | 284 |
Feature activation | -6.75e-02 |
Pos logit contributions | |
awk | +0.338 |
argon | +0.327 |
Cheney | +0.292 |
lam | +0.282 |
olicy | +0.276 |
Neg logit contributions | |
quart | -0.271 |
bucket | -0.257 |
otaur | -0.245 |
strap | -0.240 |
mant | -0.239 |
Token | start |
Token ID | 923 |
Feature activation | -6.35e-02 |
Pos logit contributions | |
awk | +0.167 |
argon | +0.163 |
Cheney | +0.144 |
olicy | +0.138 |
lam | +0.137 |
Neg logit contributions | |
quart | -0.133 |
bucket | -0.128 |
strap | -0.123 |
mant | -0.119 |
otaur | -0.117 |
Token | developing |
Token ID | 5922 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
awk | +0.159 |
argon | +0.154 |
Cheney | +0.138 |
lam | +0.132 |
olicy | +0.131 |
Neg logit contributions | |
quart | -0.121 |
bucket | -0.117 |
strap | -0.109 |
otaur | -0.108 |
mant | -0.108 |
Token | in |
Token ID | 287 |
Feature activation | -8.93e-03 |
Pos logit contributions | |
quart | +0.073 |
bucket | +0.070 |
strap | +0.066 |
otaur | +0.066 |
mant | +0.065 |
Neg logit contributions | |
awk | -0.098 |
argon | -0.095 |
Cheney | -0.085 |
lam | -0.081 |
olicy | -0.080 |
Token | AWS |
Token ID | 30865 |
Feature activation | +1.00e-03 |
Pos logit contributions | |
awk | +0.024 |
argon | +0.023 |
Cheney | +0.021 |
lam | +0.020 |
olicy | +0.019 |
Neg logit contributions | |
quart | -0.016 |
bucket | -0.015 |
otaur | -0.014 |
strap | -0.014 |
mant | -0.014 |
Token | Lamb |
Token ID | 21114 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
quart | +0.002 |
bucket | +0.002 |
strap | +0.002 |
otaur | +0.002 |
mant | +0.002 |
Neg logit contributions | |
awk | -0.002 |
argon | -0.002 |
Cheney | -0.002 |
lam | -0.002 |
olicy | -0.002 |
Token | da |
Token ID | 6814 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
quart | +1.358 |
bucket | +1.312 |
otaur | +1.255 |
strap | +1.243 |
mant | +1.205 |
Neg logit contributions | |
awk | -1.077 |
argon | -1.049 |
Cheney | -0.906 |
olicy | -0.850 |
lam | -0.838 |
Token | with |
Token ID | 351 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
awk | +0.250 |
argon | +0.242 |
Cheney | +0.215 |
lam | +0.205 |
olicy | +0.203 |
Neg logit contributions | |
quart | -0.208 |
bucket | -0.201 |
strap | -0.188 |
otaur | -0.187 |
mant | -0.185 |
Token | server |
Token ID | 4382 |
Feature activation | -9.89e-02 |
Pos logit contributions | |
awk | +0.049 |
argon | +0.047 |
Cheney | +0.043 |
lam | +0.041 |
olicy | +0.040 |
Neg logit contributions | |
quart | -0.034 |
bucket | -0.032 |
strap | -0.030 |
otaur | -0.030 |
mant | -0.030 |
Token | less |
Token ID | 1203 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
awk | +0.234 |
argon | +0.228 |
Cheney | +0.205 |
olicy | +0.193 |
lam | +0.187 |
Neg logit contributions | |
quart | -0.201 |
bucket | -0.196 |
strap | -0.183 |
otaur | -0.180 |
mant | -0.179 |
Token | framework |
Token ID | 9355 |
Feature activation | -6.44e-02 |
Pos logit contributions | |
awk | +0.036 |
argon | +0.035 |
Cheney | +0.032 |
lam | +0.030 |
olicy | +0.030 |
Neg logit contributions | |
quart | -0.024 |
bucket | -0.023 |
strap | -0.022 |
otaur | -0.021 |
mant | -0.021 |
Token | City |
Token ID | 2254 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
quart | +0.140 |
bucket | +0.133 |
strap | +0.125 |
otaur | +0.124 |
mant | +0.123 |
Neg logit contributions | |
awk | -0.173 |
argon | -0.168 |
Cheney | -0.149 |
lam | -0.142 |
olicy | -0.140 |
Token | with |
Token ID | 351 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
awk | +0.094 |
argon | +0.091 |
Cheney | +0.081 |
lam | +0.077 |
olicy | +0.077 |
Neg logit contributions | |
quart | -0.077 |
bucket | -0.074 |
strap | -0.069 |
mant | -0.068 |
otaur | -0.068 |
Token | Tang |
Token ID | 18816 |
Feature activation | -5.95e-02 |
Pos logit contributions | |
quart | +0.038 |
bucket | +0.036 |
strap | +0.034 |
otaur | +0.034 |
mant | +0.034 |
Neg logit contributions | |
awk | -0.051 |
argon | -0.050 |
Cheney | -0.044 |
lam | -0.043 |
olicy | -0.042 |
Token | Shen |
Token ID | 22323 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
awk | +0.146 |
argon | +0.142 |
Cheney | +0.125 |
olicy | +0.119 |
lam | +0.119 |
Neg logit contributions | |
quart | -0.118 |
bucket | -0.112 |
strap | -0.105 |
otaur | -0.104 |
mant | -0.103 |
Token | , |
Token ID | 11 |
Feature activation | +4.12e-03 |
Pos logit contributions | |
quart | +0.085 |
bucket | +0.082 |
strap | +0.077 |
otaur | +0.077 |
mant | +0.076 |
Neg logit contributions | |
awk | -0.104 |
argon | -0.101 |
Cheney | -0.090 |
olicy | -0.085 |
lam | -0.085 |
Token | Spl |
Token ID | 13341 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
quart | +0.008 |
bucket | +0.008 |
strap | +0.007 |
otaur | +0.007 |
mant | +0.007 |
Neg logit contributions | |
awk | -0.010 |
argon | -0.010 |
Cheney | -0.009 |
lam | -0.008 |
olicy | -0.008 |
Token | inter |
Token ID | 3849 |
Feature activation | +9.99e-02 |
Pos logit contributions | |
quart | +1.117 |
bucket | +1.077 |
otaur | +1.025 |
strap | +0.999 |
mant | +0.984 |
Neg logit contributions | |
awk | -1.270 |
argon | -1.226 |
Cheney | -1.121 |
olicy | -1.056 |
lam | -1.037 |
Token | , |
Token ID | 11 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
quart | +0.206 |
bucket | +0.198 |
strap | +0.186 |
otaur | +0.186 |
mant | +0.184 |
Neg logit contributions | |
awk | -0.235 |
argon | -0.227 |
Cheney | -0.202 |
lam | -0.192 |
olicy | -0.190 |
Token | and |
Token ID | 290 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
quart | +0.052 |
bucket | +0.050 |
strap | +0.047 |
otaur | +0.046 |
mant | +0.046 |
Neg logit contributions | |
awk | -0.061 |
argon | -0.059 |
Cheney | -0.052 |
lam | -0.050 |
olicy | -0.050 |
Token | a |
Token ID | 257 |
Feature activation | +6.66e-02 |
Pos logit contributions | |
quart | +0.051 |
bucket | +0.049 |
strap | +0.046 |
otaur | +0.046 |
mant | +0.045 |
Neg logit contributions | |
awk | -0.063 |
argon | -0.061 |
Cheney | -0.054 |
lam | -0.052 |
olicy | -0.052 |
Token | few |
Token ID | 1178 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
quart | +0.124 |
bucket | +0.118 |
strap | +0.110 |
otaur | +0.108 |
mant | +0.108 |
Neg logit contributions | |
awk | -0.172 |
argon | -0.167 |
Cheney | -0.150 |
lam | -0.143 |
olicy | -0.143 |
Token | from |
Token ID | 422 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
awk | +0.484 |
argon | +0.469 |
Cheney | +0.412 |
lam | +0.392 |
olicy | +0.389 |
Neg logit contributions | |
quart | -0.455 |
bucket | -0.438 |
strap | -0.413 |
otaur | -0.410 |
mant | -0.408 |
Token | his |
Token ID | 465 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
quart | +0.080 |
bucket | +0.077 |
strap | +0.072 |
mant | +0.071 |
otaur | +0.071 |
Neg logit contributions | |
awk | -0.097 |
argon | -0.094 |
Cheney | -0.082 |
lam | -0.079 |
olicy | -0.079 |
Token | fel |
Token ID | 10756 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
quart | +0.044 |
bucket | +0.042 |
strap | +0.040 |
mant | +0.039 |
otaur | +0.039 |
Neg logit contributions | |
awk | -0.056 |
argon | -0.054 |
Cheney | -0.047 |
olicy | -0.045 |
lam | -0.045 |
Token | |
Token ID | 3907 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
quart | +0.250 |
bucket | +0.238 |
strap | +0.224 |
otaur | +0.224 |
mant | +0.221 |
Neg logit contributions | |
awk | -0.313 |
argon | -0.304 |
Cheney | -0.271 |
olicy | -0.257 |
lam | -0.256 |
Token | low |
Token ID | 9319 |
Feature activation | -9.71e-02 |
Pos logit contributions | |
awk | +0.079 |
argon | +0.077 |
Cheney | +0.067 |
lam | +0.065 |
olicy | +0.063 |
Neg logit contributions | |
quart | -0.072 |
bucket | -0.070 |
strap | -0.066 |
otaur | -0.065 |
mant | -0.064 |
Token | Demo |
Token ID | 34588 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
awk | +0.233 |
argon | +0.226 |
Cheney | +0.200 |
lam | +0.191 |
olicy | +0.190 |
Neg logit contributions | |
quart | -0.196 |
bucket | -0.188 |
strap | -0.176 |
otaur | -0.176 |
mant | -0.174 |
Token | |
Token ID | 3907 |
Feature activation | -4.58e-02 |
Pos logit contributions | |
quart | +1.014 |
bucket | +0.963 |
strap | +0.902 |
mant | +0.880 |
otaur | +0.874 |
Neg logit contributions | |
awk | -1.413 |
argon | -1.397 |
Cheney | -1.221 |
olicy | -1.177 |
lam | -1.164 |
Token | cr |
Token ID | 6098 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
awk | +0.068 |
argon | +0.064 |
Cheney | +0.052 |
lam | +0.048 |
olicy | +0.047 |
Neg logit contributions | |
quart | -0.135 |
bucket | -0.131 |
strap | -0.126 |
otaur | -0.126 |
mant | -0.125 |
Token | ats |
Token ID | 1381 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
quart | +0.503 |
bucket | +0.487 |
strap | +0.462 |
otaur | +0.461 |
mant | +0.455 |
Neg logit contributions | |
awk | -0.448 |
argon | -0.432 |
Cheney | -0.376 |
lam | -0.356 |
olicy | -0.351 |
Token | . |
Token ID | 13 |
Feature activation | -8.65e-03 |
Pos logit contributions | |
quart | +0.400 |
bucket | +0.384 |
strap | +0.361 |
otaur | +0.358 |
mant | +0.356 |
Neg logit contributions | |
awk | -0.488 |
argon | -0.474 |
Cheney | -0.420 |
lam | -0.399 |
olicy | -0.399 |
Token | At |
Token ID | 1629 |
Feature activation | +3.74e-03 |
Pos logit contributions | |
awk | +0.018 |
argon | +0.018 |
Cheney | +0.015 |
olicy | +0.015 |
lam | +0.015 |
Neg logit contributions | |
quart | -0.020 |
bucket | -0.019 |
strap | -0.018 |
mant | -0.018 |
otaur | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
quart | +0.145 |
bucket | +0.140 |
otaur | +0.134 |
strap | +0.133 |
mant | +0.132 |
Neg logit contributions | |
awk | -0.138 |
argon | -0.133 |
Cheney | -0.117 |
lam | -0.110 |
olicy | -0.109 |
Token |
|
Token ID | 198 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
quart | +0.062 |
bucket | +0.059 |
strap | +0.055 |
mant | +0.054 |
otaur | +0.054 |
Neg logit contributions | |
awk | -0.079 |
argon | -0.078 |
Cheney | -0.068 |
olicy | -0.068 |
lam | -0.065 |
Token | 3 |
Token ID | 18 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
quart | +0.142 |
bucket | +0.138 |
otaur | +0.131 |
strap | +0.131 |
mant | +0.130 |
Neg logit contributions | |
awk | -0.107 |
argon | -0.103 |
Cheney | -0.088 |
lam | -0.083 |
olicy | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
quart | +0.065 |
bucket | +0.063 |
strap | +0.058 |
mant | +0.057 |
otaur | +0.057 |
Neg logit contributions | |
awk | -0.093 |
argon | -0.092 |
Cheney | -0.081 |
olicy | -0.081 |
lam | -0.077 |
Token | Z |
Token ID | 1168 |
Feature activation | +4.41e-03 |
Pos logit contributions | |
quart | +0.058 |
bucket | +0.056 |
strap | +0.053 |
otaur | +0.052 |
mant | +0.052 |
Neg logit contributions | |
awk | -0.067 |
argon | -0.065 |
Cheney | -0.057 |
lam | -0.054 |
olicy | -0.054 |
Token | ander |
Token ID | 4066 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
quart | +0.007 |
bucket | +0.006 |
strap | +0.006 |
otaur | +0.006 |
mant | +0.006 |
Neg logit contributions | |
awk | -0.012 |
argon | -0.012 |
Cheney | -0.011 |
olicy | -0.011 |
lam | -0.011 |
Token | F |
Token ID | 376 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
quart | +1.137 |
bucket | +1.086 |
strap | +1.027 |
otaur | +1.013 |
mant | +1.011 |
Neg logit contributions | |
awk | -1.200 |
argon | -1.168 |
Cheney | -1.000 |
olicy | -0.971 |
lam | -0.968 |
Token | ag |
Token ID | 363 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
quart | +0.071 |
bucket | +0.067 |
strap | +0.064 |
otaur | +0.063 |
mant | +0.062 |
Neg logit contributions | |
awk | -0.097 |
argon | -0.094 |
Cheney | -0.088 |
olicy | -0.083 |
lam | -0.081 |
Token | erson |
Token ID | 882 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
quart | +0.051 |
bucket | +0.048 |
strap | +0.046 |
otaur | +0.046 |
ça | +0.045 |
Neg logit contributions | |
awk | -0.055 |
argon | -0.054 |
Cheney | -0.048 |
olicy | -0.045 |
Exec | -0.045 |
Token | ( |
Token ID | 357 |
Feature activation | +6.94e-02 |
Pos logit contributions | |
quart | +0.465 |
bucket | +0.443 |
strap | +0.415 |
mant | +0.410 |
otaur | +0.401 |
Neg logit contributions | |
awk | -0.578 |
argon | -0.567 |
Cheney | -0.493 |
olicy | -0.490 |
lam | -0.475 |
Token | 46 |
Token ID | 3510 |
Feature activation | +8.29e-02 |
Pos logit contributions | |
quart | +0.195 |
bucket | +0.189 |
otaur | +0.181 |
strap | +0.180 |
mant | +0.179 |
Neg logit contributions | |
awk | -0.107 |
argon | -0.102 |
Cheney | -0.087 |
olicy | -0.083 |
lam | -0.077 |
Token | Group |
Token ID | 4912 |
Feature activation | -4.93e-02 |
Pos logit contributions | |
awk | +0.342 |
argon | +0.331 |
Cheney | +0.289 |
olicy | +0.273 |
lam | +0.271 |
Neg logit contributions | |
quart | -0.341 |
bucket | -0.327 |
strap | -0.309 |
mant | -0.307 |
otaur | -0.305 |
Token | will |
Token ID | 481 |
Feature activation | +4.87e-02 |
Pos logit contributions | |
awk | +0.126 |
argon | +0.122 |
Cheney | +0.109 |
lam | +0.104 |
olicy | +0.104 |
Neg logit contributions | |
quart | -0.092 |
bucket | -0.088 |
strap | -0.083 |
otaur | -0.082 |
mant | -0.081 |
Token | release |
Token ID | 2650 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
quart | +0.077 |
bucket | +0.073 |
strap | +0.069 |
mant | +0.066 |
otaur | +0.065 |
Neg logit contributions | |
awk | -0.139 |
argon | -0.136 |
Cheney | -0.123 |
olicy | -0.118 |
lam | -0.118 |
Token | the |
Token ID | 262 |
Feature activation | +8.94e-02 |
Pos logit contributions | |
quart | +0.276 |
bucket | +0.264 |
strap | +0.248 |
otaur | +0.246 |
mant | +0.244 |
Neg logit contributions | |
awk | -0.335 |
argon | -0.325 |
Cheney | -0.288 |
lam | -0.275 |
olicy | -0.273 |
Token | limited |
Token ID | 3614 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
quart | +0.153 |
bucket | +0.146 |
strap | +0.135 |
otaur | +0.132 |
mant | +0.132 |
Neg logit contributions | |
awk | -0.245 |
argon | -0.238 |
Cheney | -0.213 |
lam | -0.205 |
olicy | -0.205 |
Token | edition |
Token ID | 8313 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
quart | +0.214 |
bucket | +0.204 |
strap | +0.189 |
otaur | +0.188 |
mant | +0.185 |
Neg logit contributions | |
awk | -0.366 |
argon | -0.356 |
Cheney | -0.321 |
lam | -0.309 |
olicy | -0.306 |
Token | Visitors |
Token ID | 44535 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
quart | +1.068 |
bucket | +1.029 |
strap | +0.963 |
otaur | +0.949 |
mant | +0.942 |
Neg logit contributions | |
awk | -1.263 |
argon | -1.218 |
Cheney | -1.070 |
lam | -1.028 |
olicy | -1.022 |
Token | , |
Token ID | 11 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
quart | +0.211 |
bucket | +0.203 |
otaur | +0.190 |
strap | +0.190 |
mant | +0.187 |
Neg logit contributions | |
awk | -0.262 |
argon | -0.253 |
Cheney | -0.226 |
lam | -0.216 |
olicy | -0.213 |
Token | five |
Token ID | 1936 |
Feature activation | -8.72e-03 |
Pos logit contributions | |
quart | +0.094 |
bucket | +0.090 |
strap | +0.085 |
otaur | +0.084 |
mant | +0.083 |
Neg logit contributions | |
awk | -0.114 |
argon | -0.110 |
Cheney | -0.097 |
lam | -0.093 |
olicy | -0.092 |
Token | 7 |
Token ID | 767 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
awk | +0.022 |
argon | +0.022 |
Cheney | +0.019 |
lam | +0.018 |
olicy | +0.018 |
Neg logit contributions | |
quart | -0.016 |
bucket | -0.016 |
strap | -0.015 |
otaur | -0.015 |
mant | -0.014 |
Token | " |
Token ID | 1 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
quart | +0.056 |
bucket | +0.053 |
strap | +0.050 |
otaur | +0.050 |
mant | +0.049 |
Neg logit contributions | |
awk | -0.063 |
argon | -0.061 |
Cheney | -0.054 |
lam | -0.052 |
olicy | -0.051 |
Token | edy |
Token ID | 4716 |
Feature activation | -5.76e-02 |
Pos logit contributions | |
quart | +0.411 |
bucket | +0.397 |
strap | +0.376 |
otaur | +0.375 |
mant | +0.370 |
Neg logit contributions | |
awk | -0.384 |
argon | -0.371 |
Cheney | -0.323 |
lam | -0.306 |
olicy | -0.303 |
Token | Ro |
Token ID | 5564 |
Feature activation | -3.02e-03 |
Pos logit contributions | |
awk | +0.135 |
argon | +0.131 |
Cheney | +0.115 |
lam | +0.109 |
olicy | +0.109 |
Neg logit contributions | |
quart | -0.119 |
bucket | -0.115 |
strap | -0.108 |
otaur | -0.108 |
mant | -0.107 |
Token | asts |
Token ID | 5773 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
awk | +0.006 |
argon | +0.006 |
Cheney | +0.005 |
lam | +0.005 |
olicy | +0.005 |
Neg logit contributions | |
quart | -0.007 |
bucket | -0.007 |
strap | -0.007 |
otaur | -0.007 |
mant | -0.007 |
Token | - |
Token ID | 12 |
Feature activation | +8.39e-02 |
Pos logit contributions | |
quart | +0.481 |
bucket | +0.463 |
strap | +0.433 |
otaur | +0.432 |
mant | +0.427 |
Neg logit contributions | |
awk | -0.558 |
argon | -0.545 |
Cheney | -0.477 |
olicy | -0.455 |
lam | -0.453 |
Token | Pr |
Token ID | 6836 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
quart | +0.189 |
bucket | +0.183 |
strap | +0.173 |
otaur | +0.173 |
mant | +0.171 |
Neg logit contributions | |
awk | -0.178 |
argon | -0.172 |
Cheney | -0.151 |
olicy | -0.143 |
lam | -0.141 |
Token | ison |
Token ID | 1653 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
quart | +0.376 |
bucket | +0.362 |
otaur | +0.342 |
strap | +0.341 |
mant | +0.336 |
Neg logit contributions | |
awk | -0.428 |
argon | -0.412 |
Cheney | -0.367 |
lam | -0.348 |
olicy | -0.346 |
Token | Stories |
Token ID | 18152 |
Feature activation | -4.05e-02 |
Pos logit contributions | |
quart | +1.162 |
bucket | +1.123 |
strap | +1.063 |
otaur | +1.060 |
mant | +1.041 |
Neg logit contributions | |
awk | -1.135 |
argon | -1.091 |
Cheney | -0.943 |
olicy | -0.897 |
lam | -0.893 |
Token | - |
Token ID | 12 |
Feature activation | +9.21e-02 |
Pos logit contributions | |
awk | +0.098 |
argon | +0.095 |
Cheney | +0.085 |
lam | +0.081 |
olicy | +0.080 |
Neg logit contributions | |
quart | -0.081 |
bucket | -0.077 |
otaur | -0.073 |
strap | -0.073 |
mant | -0.072 |
Token | M |
Token ID | 44 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
quart | +0.207 |
bucket | +0.201 |
strap | +0.190 |
otaur | +0.189 |
mant | +0.188 |
Neg logit contributions | |
awk | -0.196 |
argon | -0.190 |
Cheney | -0.166 |
olicy | -0.157 |
lam | -0.155 |
Token | VP |
Token ID | 8859 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
quart | +0.098 |
bucket | +0.095 |
strap | +0.091 |
otaur | +0.090 |
mant | +0.089 |
Neg logit contributions | |
awk | -0.091 |
argon | -0.088 |
Cheney | -0.078 |
lam | -0.073 |
olicy | -0.072 |
Token | From |
Token ID | 3574 |
Feature activation | -8.06e-02 |
Pos logit contributions | |
awk | +0.072 |
argon | +0.070 |
Cheney | +0.062 |
lam | +0.059 |
olicy | +0.059 |
Neg logit contributions | |
quart | -0.063 |
bucket | -0.060 |
strap | -0.057 |
otaur | -0.056 |
mant | -0.056 |
Token | iazep |
Token ID | 48826 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
awk | +0.530 |
argon | +0.519 |
Cheney | +0.466 |
olicy | +0.451 |
lam | +0.439 |
Neg logit contributions | |
quart | -0.360 |
bucket | -0.343 |
otaur | -0.329 |
strap | -0.325 |
mant | -0.310 |
Token | ine |
Token ID | 500 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
quart | +0.032 |
bucket | +0.031 |
strap | +0.029 |
otaur | +0.029 |
mant | +0.029 |
Neg logit contributions | |
awk | -0.031 |
argon | -0.030 |
Cheney | -0.026 |
lam | -0.025 |
olicy | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
quart | +0.526 |
bucket | +0.499 |
strap | +0.472 |
otaur | +0.461 |
mant | +0.461 |
Neg logit contributions | |
awk | -0.717 |
argon | -0.700 |
Cheney | -0.617 |
olicy | -0.598 |
lam | -0.589 |
Token |
|
Token ID | 198 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
quart | +0.055 |
bucket | +0.053 |
otaur | +0.050 |
strap | +0.050 |
mant | +0.049 |
Neg logit contributions | |
awk | -0.061 |
argon | -0.060 |
Cheney | -0.052 |
olicy | -0.050 |
lam | -0.050 |
Token |
|
Token ID | 198 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
awk | +0.061 |
argon | +0.060 |
Cheney | +0.052 |
olicy | +0.052 |
lam | +0.050 |
Neg logit contributions | |
quart | -0.048 |
bucket | -0.046 |
strap | -0.042 |
mant | -0.042 |
otaur | -0.042 |
Token | Copyright |
Token ID | 15269 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
awk | +0.032 |
argon | +0.031 |
Cheney | +0.027 |
olicy | +0.026 |
lam | +0.025 |
Neg logit contributions | |
quart | -0.035 |
bucket | -0.033 |
otaur | -0.032 |
strap | -0.032 |
mant | -0.031 |
Token | © |
Token ID | 10673 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
quart | +0.740 |
bucket | +0.697 |
strap | +0.637 |
otaur | +0.636 |
mant | +0.624 |
Neg logit contributions | |
awk | -1.552 |
argon | -1.510 |
Cheney | -1.376 |
lam | -1.327 |
olicy | -1.315 |
Token | 2016 |
Token ID | 1584 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
quart | +0.412 |
bucket | +0.384 |
strap | +0.351 |
otaur | +0.351 |
mant | +0.344 |
Neg logit contributions | |
awk | -0.885 |
argon | -0.860 |
Cheney | -0.782 |
lam | -0.754 |
olicy | -0.751 |
Token | Else |
Token ID | 25974 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
quart | +0.257 |
bucket | +0.246 |
strap | +0.233 |
otaur | +0.232 |
mant | +0.229 |
Neg logit contributions | |
awk | -0.287 |
argon | -0.276 |
Cheney | -0.243 |
lam | -0.231 |
olicy | -0.231 |
Token | vier |
Token ID | 49663 |
Feature activation | -8.07e-02 |
Pos logit contributions | |
quart | +0.254 |
bucket | +0.244 |
strap | +0.229 |
otaur | +0.229 |
mant | +0.225 |
Neg logit contributions | |
awk | -0.329 |
argon | -0.318 |
Cheney | -0.284 |
lam | -0.272 |
olicy | -0.269 |
Token | B |
Token ID | 347 |
Feature activation | +2.44e-03 |
Pos logit contributions | |
awk | +0.178 |
argon | +0.172 |
Cheney | +0.151 |
lam | +0.143 |
olicy | +0.141 |
Neg logit contributions | |
quart | -0.178 |
bucket | -0.172 |
otaur | -0.163 |
strap | -0.163 |
mant | -0.161 |
Token | when |
Token ID | 618 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
awk | +0.065 |
argon | +0.063 |
Cheney | +0.056 |
olicy | +0.053 |
lam | +0.053 |
Neg logit contributions | |
quart | -0.057 |
bucket | -0.055 |
strap | -0.052 |
mant | -0.052 |
otaur | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | -4.90e-02 |
Pos logit contributions | |
quart | +0.027 |
bucket | +0.025 |
strap | +0.024 |
mant | +0.023 |
otaur | +0.023 |
Neg logit contributions | |
awk | -0.039 |
argon | -0.038 |
Cheney | -0.034 |
olicy | -0.032 |
lam | -0.032 |
Token | content |
Token ID | 2695 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
awk | +0.130 |
argon | +0.126 |
Cheney | +0.113 |
olicy | +0.108 |
lam | +0.108 |
Neg logit contributions | |
quart | -0.088 |
bucket | -0.084 |
strap | -0.078 |
mant | -0.077 |
otaur | -0.077 |
Token | remains |
Token ID | 3793 |
Feature activation | +4.00e-02 |
Pos logit contributions | |
quart | +0.058 |
bucket | +0.056 |
strap | +0.052 |
otaur | +0.052 |
mant | +0.051 |
Neg logit contributions | |
awk | -0.076 |
argon | -0.074 |
Cheney | -0.066 |
lam | -0.063 |
olicy | -0.063 |
Token | slightly |
Token ID | 4622 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
quart | +0.074 |
bucket | +0.071 |
strap | +0.066 |
mant | +0.065 |
otaur | +0.065 |
Neg logit contributions | |
awk | -0.103 |
argon | -0.101 |
Cheney | -0.089 |
lam | -0.086 |
olicy | -0.085 |
Token | vacant |
Token ID | 23957 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
awk | +0.411 |
argon | +0.401 |
Cheney | +0.357 |
lam | +0.342 |
olicy | +0.341 |
Neg logit contributions | |
quart | -0.291 |
bucket | -0.278 |
strap | -0.259 |
otaur | -0.256 |
mant | -0.256 |
Token | . |
Token ID | 13 |
Feature activation | +9.92e-03 |
Pos logit contributions | |
quart | +1.028 |
bucket | +0.988 |
strap | +0.922 |
mant | +0.917 |
otaur | +0.912 |
Neg logit contributions | |
awk | -1.257 |
argon | -1.225 |
Cheney | -1.086 |
olicy | -1.034 |
lam | -1.033 |
Token | � |
Token ID | 564 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
quart | +0.022 |
bucket | +0.021 |
mant | +0.020 |
strap | +0.019 |
otaur | +0.019 |
Neg logit contributions | |
awk | -0.022 |
argon | -0.021 |
Cheney | -0.018 |
olicy | -0.018 |
lam | -0.018 |
Token | � |
Token ID | 250 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
awk | +0.034 |
argon | +0.033 |
Cheney | +0.030 |
lam | +0.028 |
olicy | +0.028 |
Neg logit contributions | |
quart | -0.026 |
bucket | -0.025 |
strap | -0.023 |
otaur | -0.023 |
mant | -0.023 |
Token | A |
Token ID | 32 |
Feature activation | +9.48e-02 |
Pos logit contributions | |
awk | +0.032 |
argon | +0.031 |
Cheney | +0.027 |
olicy | +0.025 |
lam | +0.025 |
Neg logit contributions | |
quart | -0.036 |
bucket | -0.034 |
otaur | -0.033 |
strap | -0.033 |
mant | -0.032 |
Token | Village |
Token ID | 14812 |
Feature activation | -9.19e-02 |
Pos logit contributions | |
quart | +0.179 |
bucket | +0.172 |
strap | +0.160 |
otaur | +0.159 |
mant | +0.158 |
Neg logit contributions | |
awk | -0.241 |
argon | -0.234 |
Cheney | -0.210 |
olicy | -0.199 |
lam | -0.199 |
Token | that |
Token ID | 326 |
Feature activation | +4.68e-02 |
Pos logit contributions | |
quart | +0.046 |
bucket | +0.044 |
strap | +0.041 |
otaur | +0.041 |
mant | +0.040 |
Neg logit contributions | |
awk | -0.068 |
argon | -0.066 |
Cheney | -0.059 |
lam | -0.057 |
olicy | -0.057 |
Token | the |
Token ID | 262 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
quart | +0.091 |
bucket | +0.087 |
strap | +0.082 |
otaur | +0.081 |
mant | +0.081 |
Neg logit contributions | |
awk | -0.116 |
argon | -0.112 |
Cheney | -0.099 |
lam | -0.095 |
olicy | -0.095 |
Token | US |
Token ID | 1294 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
awk | +0.062 |
argon | +0.060 |
Cheney | +0.053 |
lam | +0.051 |
olicy | +0.051 |
Neg logit contributions | |
quart | -0.050 |
bucket | -0.048 |
strap | -0.045 |
otaur | -0.044 |
mant | -0.044 |
Token | had |
Token ID | 550 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
quart | +0.408 |
bucket | +0.391 |
strap | +0.368 |
mant | +0.361 |
otaur | +0.360 |
Neg logit contributions | |
awk | -0.485 |
argon | -0.471 |
Cheney | -0.413 |
lam | -0.396 |
olicy | -0.394 |
Token | put |
Token ID | 1234 |
Feature activation | -9.04e-02 |
Pos logit contributions | |
awk | +0.086 |
argon | +0.084 |
Cheney | +0.074 |
olicy | +0.071 |
lam | +0.071 |
Neg logit contributions | |
quart | -0.066 |
bucket | -0.063 |
strap | -0.059 |
mant | -0.058 |
otaur | -0.058 |
Token | diplomatic |
Token ID | 13093 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
awk | +0.224 |
argon | +0.217 |
Cheney | +0.192 |
lam | +0.184 |
olicy | +0.183 |
Neg logit contributions | |
quart | -0.177 |
bucket | -0.169 |
strap | -0.159 |
mant | -0.157 |
otaur | -0.156 |
Token | pressure |
Token ID | 3833 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
quart | +0.975 |
bucket | +0.928 |
strap | +0.865 |
mant | +0.858 |
otaur | +0.830 |
Neg logit contributions | |
awk | -1.327 |
argon | -1.296 |
Cheney | -1.134 |
olicy | -1.098 |
lam | -1.098 |
Token | on |
Token ID | 319 |
Feature activation | +8.79e-02 |
Pos logit contributions | |
awk | +0.338 |
argon | +0.328 |
Cheney | +0.289 |
lam | +0.275 |
olicy | +0.273 |
Neg logit contributions | |
quart | -0.295 |
bucket | -0.284 |
strap | -0.267 |
otaur | -0.266 |
mant | -0.263 |
Token | allies |
Token ID | 7681 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
quart | +0.147 |
bucket | +0.140 |
strap | +0.130 |
otaur | +0.128 |
mant | +0.127 |
Neg logit contributions | |
awk | -0.242 |
argon | -0.235 |
Cheney | -0.210 |
lam | -0.203 |
olicy | -0.202 |
Token | to |
Token ID | 284 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
quart | +0.049 |
bucket | +0.047 |
strap | +0.044 |
otaur | +0.044 |
mant | +0.043 |
Neg logit contributions | |
awk | -0.062 |
argon | -0.060 |
Cheney | -0.053 |
lam | -0.051 |
olicy | -0.051 |
Token | open |
Token ID | 1280 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
quart | +0.057 |
bucket | +0.055 |
strap | +0.052 |
mant | +0.050 |
otaur | +0.049 |
Neg logit contributions | |
awk | -0.077 |
argon | -0.075 |
Cheney | -0.066 |
olicy | -0.064 |
lam | -0.063 |
Token | ][ |
Token ID | 7131 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
quart | +0.096 |
bucket | +0.091 |
otaur | +0.087 |
strap | +0.086 |
mant | +0.085 |
Neg logit contributions | |
awk | -0.122 |
argon | -0.118 |
Cheney | -0.105 |
lam | -0.101 |
olicy | -0.099 |
Token | b |
Token ID | 65 |
Feature activation | -4.54e-02 |
Pos logit contributions | |
quart | +1.102 |
bucket | +1.075 |
otaur | +1.023 |
strap | +1.020 |
dden | +1.000 |
Neg logit contributions | |
awk | -0.867 |
argon | -0.829 |
Cheney | -0.745 |
olicy | -0.698 |
lam | -0.666 |
Token | ] |
Token ID | 60 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
awk | +0.113 |
argon | +0.110 |
Cheney | +0.099 |
olicy | +0.095 |
lam | +0.093 |
Neg logit contributions | |
quart | -0.086 |
bucket | -0.082 |
strap | -0.077 |
otaur | -0.077 |
mant | -0.076 |
Token | Mega |
Token ID | 43471 |
Feature activation | +9.42e-02 |
Pos logit contributions | |
quart | +0.483 |
bucket | +0.466 |
otaur | +0.443 |
strap | +0.441 |
mant | +0.435 |
Neg logit contributions | |
awk | -0.452 |
argon | -0.435 |
Cheney | -0.384 |
olicy | -0.360 |
lam | -0.359 |
Token | Pony |
Token ID | 30377 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
quart | +0.233 |
bucket | +0.227 |
strap | +0.215 |
otaur | +0.215 |
mant | +0.212 |
Neg logit contributions | |
awk | -0.182 |
argon | -0.175 |
Cheney | -0.151 |
lam | -0.141 |
olicy | -0.140 |
Token | [/ |
Token ID | 13412 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
quart | +0.425 |
bucket | +0.408 |
strap | +0.382 |
otaur | +0.382 |
mant | +0.376 |
Neg logit contributions | |
awk | -0.550 |
argon | -0.535 |
Cheney | -0.476 |
lam | -0.454 |
olicy | -0.453 |
Token | b |
Token ID | 65 |
Feature activation | -8.38e-02 |
Pos logit contributions | |
quart | +1.169 |
bucket | +1.155 |
otaur | +1.078 |
dden | +1.066 |
strap | +1.065 |
Neg logit contributions | |
awk | -1.038 |
argon | -1.011 |
Cheney | -0.917 |
olicy | -0.897 |
Exec | -0.837 |
Token | ][/ |
Token ID | 44926 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
awk | +0.320 |
argon | +0.315 |
Cheney | +0.292 |
olicy | +0.284 |
lam | +0.283 |
Neg logit contributions | |
quart | -0.049 |
bucket | -0.042 |
strap | -0.033 |
otaur | -0.032 |
mant | -0.031 |
Token | color |
Token ID | 8043 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
quart | +0.809 |
bucket | +0.788 |
otaur | +0.744 |
dden | +0.742 |
strap | +0.735 |
Neg logit contributions | |
awk | -0.675 |
argon | -0.648 |
Cheney | -0.592 |
olicy | -0.565 |
Exec | -0.538 |
Token | ] |
Token ID | 60 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
awk | +0.357 |
argon | +0.348 |
Cheney | +0.309 |
olicy | +0.296 |
lam | +0.294 |
Neg logit contributions | |
quart | -0.285 |
bucket | -0.274 |
strap | -0.257 |
otaur | -0.256 |
mant | -0.254 |
Token | - |
Token ID | 532 |
Feature activation | +6.03e-02 |
Pos logit contributions | |
quart | +0.479 |
bucket | +0.462 |
otaur | +0.439 |
strap | +0.438 |
mant | +0.433 |
Neg logit contributions | |
awk | -0.446 |
argon | -0.427 |
Cheney | -0.375 |
lam | -0.356 |
olicy | -0.348 |
Token | along |
Token ID | 1863 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
quart | +0.207 |
bucket | +0.197 |
strap | +0.182 |
otaur | +0.181 |
mant | +0.179 |
Neg logit contributions | |
awk | -0.357 |
argon | -0.347 |
Cheney | -0.313 |
lam | -0.301 |
olicy | -0.299 |
Token | " |
Token ID | 1 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
awk | +0.141 |
argon | +0.137 |
Cheney | +0.122 |
lam | +0.116 |
olicy | +0.116 |
Neg logit contributions | |
quart | -0.105 |
bucket | -0.101 |
strap | -0.094 |
otaur | -0.094 |
mant | -0.093 |
Token | that |
Token ID | 326 |
Feature activation | +6.64e-02 |
Pos logit contributions | |
quart | +0.118 |
bucket | +0.113 |
strap | +0.106 |
otaur | +0.105 |
mant | +0.104 |
Neg logit contributions | |
awk | -0.162 |
argon | -0.157 |
Cheney | -0.139 |
lam | -0.134 |
olicy | -0.133 |
Token | WikiLeaks |
Token ID | 19766 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
quart | +0.134 |
bucket | +0.129 |
strap | +0.121 |
otaur | +0.120 |
mant | +0.119 |
Neg logit contributions | |
awk | -0.160 |
argon | -0.155 |
Cheney | -0.136 |
lam | -0.131 |
olicy | -0.130 |
Token | possesses |
Token ID | 22194 |
Feature activation | +4.60e-02 |
Pos logit contributions | |
quart | +0.022 |
bucket | +0.021 |
strap | +0.020 |
otaur | +0.020 |
mant | +0.019 |
Neg logit contributions | |
awk | -0.028 |
argon | -0.027 |
Cheney | -0.024 |
lam | -0.023 |
olicy | -0.023 |
Token | classified |
Token ID | 10090 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
quart | +0.090 |
bucket | +0.087 |
strap | +0.081 |
mant | +0.080 |
otaur | +0.079 |
Neg logit contributions | |
awk | -0.115 |
argon | -0.111 |
Cheney | -0.098 |
lam | -0.094 |
olicy | -0.094 |
Token | US |
Token ID | 1294 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
quart | +1.066 |
bucket | +1.034 |
mant | +0.964 |
strap | +0.962 |
otaur | +0.939 |
Neg logit contributions | |
awk | -1.215 |
argon | -1.170 |
Cheney | -1.011 |
olicy | -0.988 |
lam | -0.982 |
Token | state |
Token ID | 1181 |
Feature activation | +4.07e-03 |
Pos logit contributions | |
quart | +0.238 |
bucket | +0.231 |
mant | +0.215 |
strap | +0.214 |
otaur | +0.211 |
Neg logit contributions | |
awk | -0.287 |
argon | -0.277 |
Cheney | -0.245 |
lam | -0.235 |
olicy | -0.231 |
Token | department |
Token ID | 5011 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
quart | +0.007 |
bucket | +0.007 |
strap | +0.006 |
mant | +0.006 |
otaur | +0.006 |
Neg logit contributions | |
awk | -0.011 |
argon | -0.011 |
Cheney | -0.010 |
lam | -0.009 |
olicy | -0.009 |
Token | documents |
Token ID | 4963 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
quart | +0.765 |
bucket | +0.745 |
mant | +0.690 |
strap | +0.683 |
otaur | +0.665 |
Neg logit contributions | |
awk | -0.996 |
argon | -0.960 |
Cheney | -0.838 |
lam | -0.818 |
olicy | -0.806 |
Token | . |
Token ID | 13 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
awk | +0.082 |
argon | +0.079 |
Cheney | +0.070 |
olicy | +0.067 |
lam | +0.067 |
Neg logit contributions | |
quart | -0.066 |
bucket | -0.063 |
strap | -0.059 |
mant | -0.058 |
otaur | -0.058 |
Token | For |
Token ID | 1890 |
Feature activation | -9.31e-02 |
Pos logit contributions | |
quart | +0.014 |
bucket | +0.013 |
otaur | +0.012 |
strap | +0.012 |
mant | +0.012 |
Neg logit contributions | |
awk | -0.012 |
argon | -0.012 |
Cheney | -0.010 |
olicy | -0.010 |
lam | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -6.49e-03 |
Pos logit contributions | |
awk | +0.233 |
argon | +0.226 |
Cheney | +0.201 |
lam | +0.192 |
olicy | +0.191 |
Neg logit contributions | |
quart | -0.179 |
bucket | -0.171 |
strap | -0.160 |
otaur | -0.160 |
mant | -0.158 |
Token | elabor |
Token ID | 12628 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
awk | +0.017 |
argon | +0.017 |
Cheney | +0.015 |
lam | +0.014 |
olicy | +0.014 |
Neg logit contributions | |
quart | -0.012 |
bucket | -0.011 |
strap | -0.010 |
mant | -0.010 |
otaur | -0.010 |
Token | ations |
Token ID | 602 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
awk | +0.389 |
argon | +0.376 |
Cheney | +0.334 |
lam | +0.320 |
olicy | +0.316 |
Neg logit contributions | |
quart | -0.321 |
bucket | -0.309 |
strap | -0.290 |
otaur | -0.290 |
mant | -0.286 |
Token | we |
Token ID | 356 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
awk | +0.296 |
argon | +0.287 |
Cheney | +0.254 |
lam | +0.243 |
olicy | +0.241 |
Neg logit contributions | |
quart | -0.240 |
bucket | -0.230 |
strap | -0.215 |
otaur | -0.215 |
mant | -0.213 |
Token | classified |
Token ID | 10090 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
awk | +0.036 |
argon | +0.035 |
Cheney | +0.031 |
olicy | +0.029 |
lam | +0.029 |
Neg logit contributions | |
quart | -0.030 |
bucket | -0.028 |
strap | -0.027 |
otaur | -0.026 |
mant | -0.026 |
Token | as |
Token ID | 355 |
Feature activation | -4.47e-02 |
Pos logit contributions | |
quart | +0.991 |
bucket | +0.934 |
strap | +0.873 |
mant | +0.865 |
otaur | +0.852 |
Neg logit contributions | |
awk | -1.291 |
argon | -1.256 |
Cheney | -1.104 |
olicy | -1.069 |
lam | -1.057 |
Token | reflecting |
Token ID | 20252 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
awk | +0.110 |
argon | +0.107 |
Cheney | +0.094 |
lam | +0.089 |
olicy | +0.089 |
Neg logit contributions | |
quart | -0.090 |
bucket | -0.086 |
strap | -0.080 |
mant | -0.080 |
otaur | -0.079 |
Token | possible |
Token ID | 1744 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
awk | +0.035 |
argon | +0.034 |
Cheney | +0.030 |
olicy | +0.029 |
lam | +0.029 |
Neg logit contributions | |
quart | -0.028 |
bucket | -0.027 |
strap | -0.025 |
mant | -0.025 |
otaur | -0.025 |
Token | non |
Token ID | 1729 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
awk | +0.312 |
argon | +0.303 |
Cheney | +0.267 |
olicy | +0.256 |
lam | +0.255 |
Neg logit contributions | |
quart | -0.246 |
bucket | -0.234 |
strap | -0.219 |
mant | -0.217 |
otaur | -0.216 |
Token | - |
Token ID | 12 |
Feature activation | -7.22e-03 |
Pos logit contributions | |
quart | +0.101 |
bucket | +0.097 |
otaur | +0.092 |
strap | +0.091 |
mant | +0.091 |
Neg logit contributions | |
awk | -0.099 |
argon | -0.095 |
Cheney | -0.084 |
lam | -0.079 |
olicy | -0.079 |
Token | rit |
Token ID | 799 |
Feature activation | +6.89e-02 |
Pos logit contributions | |
awk | +0.007 |
argon | +0.007 |
Cheney | +0.006 |
lam | +0.006 |
olicy | +0.006 |
Neg logit contributions | |
quart | -0.008 |
bucket | -0.008 |
otaur | -0.008 |
strap | -0.008 |
mant | -0.008 |
Token | origin |
Token ID | 8159 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
quart | +0.141 |
bucket | +0.135 |
strap | +0.127 |
mant | +0.126 |
otaur | +0.126 |
Neg logit contributions | |
awk | -0.164 |
argon | -0.159 |
Cheney | -0.141 |
olicy | -0.134 |
lam | -0.134 |
Token | el |
Token ID | 417 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
quart | +0.039 |
bucket | +0.037 |
otaur | +0.035 |
strap | +0.035 |
mant | +0.035 |
Neg logit contributions | |
awk | -0.035 |
argon | -0.034 |
Cheney | -0.030 |
lam | -0.028 |
olicy | -0.028 |
Token | des |
Token ID | 748 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
quart | +0.046 |
bucket | +0.044 |
strap | +0.041 |
mant | +0.041 |
otaur | +0.041 |
Neg logit contributions | |
awk | -0.054 |
argon | -0.053 |
Cheney | -0.047 |
olicy | -0.044 |
lam | -0.044 |
Token | Cors |
Token ID | 26978 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
quart | +0.331 |
bucket | +0.315 |
strap | +0.296 |
mant | +0.295 |
otaur | +0.292 |
Neg logit contributions | |
awk | -0.401 |
argon | -0.388 |
Cheney | -0.344 |
lam | -0.328 |
olicy | -0.327 |
Token | aires |
Token ID | 17693 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
quart | +0.204 |
bucket | +0.195 |
otaur | +0.180 |
strap | +0.180 |
mant | +0.177 |
Neg logit contributions | |
awk | -0.351 |
argon | -0.341 |
Cheney | -0.308 |
lam | -0.297 |
olicy | -0.294 |
Token | [...] |
Token ID | 26894 |
Feature activation | -8.25e-02 |
Pos logit contributions | |
quart | +1.011 |
bucket | +0.958 |
strap | +0.901 |
mant | +0.898 |
otaur | +0.870 |
Neg logit contributions | |
awk | -1.244 |
argon | -1.211 |
Cheney | -1.065 |
olicy | -1.021 |
lam | -1.012 |
Token | En |
Token ID | 2039 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
awk | +0.196 |
argon | +0.191 |
Cheney | +0.168 |
lam | +0.160 |
olicy | +0.159 |
Neg logit contributions | |
quart | -0.170 |
bucket | -0.162 |
strap | -0.153 |
mant | -0.151 |
otaur | -0.151 |
Token | cas |
Token ID | 6124 |
Feature activation | -3.96e-02 |
Pos logit contributions | |
awk | +0.359 |
argon | +0.347 |
Cheney | +0.307 |
lam | +0.292 |
olicy | +0.289 |
Neg logit contributions | |
quart | -0.317 |
bucket | -0.304 |
strap | -0.287 |
otaur | -0.286 |
mant | -0.283 |
Token | de |
Token ID | 390 |
Feature activation | +7.31e-02 |
Pos logit contributions | |
awk | +0.096 |
argon | +0.093 |
Cheney | +0.082 |
lam | +0.078 |
olicy | +0.078 |
Neg logit contributions | |
quart | -0.080 |
bucket | -0.076 |
strap | -0.072 |
otaur | -0.071 |
mant | -0.071 |
Token | d |
Token ID | 288 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
quart | +0.151 |
bucket | +0.144 |
strap | +0.136 |
mant | +0.134 |
otaur | +0.134 |
Neg logit contributions | |
awk | -0.174 |
argon | -0.169 |
Cheney | -0.149 |
lam | -0.142 |
olicy | -0.141 |
Token | SELECT |
Token ID | 33493 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
quart | +0.174 |
bucket | +0.166 |
otaur | +0.157 |
strap | +0.156 |
mant | +0.154 |
Neg logit contributions | |
awk | -0.234 |
argon | -0.226 |
Cheney | -0.203 |
lam | -0.194 |
olicy | -0.192 |
Token | library |
Token ID | 5888 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
quart | +0.286 |
bucket | +0.275 |
strap | +0.254 |
otaur | +0.253 |
mant | +0.250 |
Neg logit contributions | |
awk | -0.394 |
argon | -0.381 |
Cheney | -0.341 |
lam | -0.326 |
olicy | -0.323 |
Token | , |
Token ID | 837 |
Feature activation | -5.42e-02 |
Pos logit contributions | |
quart | +0.580 |
bucket | +0.560 |
strap | +0.532 |
otaur | +0.532 |
mant | +0.526 |
Neg logit contributions | |
awk | -0.509 |
argon | -0.490 |
Cheney | -0.427 |
lam | -0.403 |
olicy | -0.397 |
Token | sum |
Token ID | 2160 |
Feature activation | +7.92e-02 |
Pos logit contributions | |
awk | +0.146 |
argon | +0.141 |
Cheney | +0.127 |
lam | +0.121 |
olicy | +0.121 |
Neg logit contributions | |
quart | -0.095 |
bucket | -0.091 |
strap | -0.084 |
otaur | -0.083 |
mant | -0.083 |
Token | ( |
Token ID | 357 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
quart | +0.170 |
bucket | +0.164 |
otaur | +0.154 |
strap | +0.153 |
mant | +0.151 |
Neg logit contributions | |
awk | -0.181 |
argon | -0.175 |
Cheney | -0.155 |
lam | -0.145 |
olicy | -0.144 |
Token | count |
Token ID | 954 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
quart | +0.254 |
bucket | +0.245 |
strap | +0.227 |
otaur | +0.225 |
mant | +0.224 |
Neg logit contributions | |
awk | -0.321 |
argon | -0.312 |
Cheney | -0.278 |
lam | -0.264 |
olicy | -0.263 |
Token | ) |
Token ID | 1267 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
quart | +1.188 |
bucket | +1.153 |
otaur | +1.089 |
strap | +1.085 |
mant | +1.076 |
Neg logit contributions | |
awk | -1.041 |
argon | -1.005 |
Cheney | -0.871 |
lam | -0.819 |
olicy | -0.813 |
Token | count |
Token ID | 954 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
quart | +0.288 |
bucket | +0.279 |
strap | +0.255 |
otaur | +0.253 |
mant | +0.253 |
Neg logit contributions | |
awk | -0.424 |
argon | -0.414 |
Cheney | -0.369 |
olicy | -0.353 |
lam | -0.353 |
Token | FROM |
Token ID | 16034 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
quart | +0.824 |
bucket | +0.797 |
otaur | +0.731 |
strap | +0.730 |
mant | +0.728 |
Neg logit contributions | |
awk | -1.047 |
argon | -1.017 |
Cheney | -0.906 |
lam | -0.857 |
olicy | -0.857 |
Token | cl |
Token ID | 537 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
quart | +0.253 |
bucket | +0.244 |
strap | +0.227 |
otaur | +0.225 |
mant | +0.224 |
Neg logit contributions | |
awk | -0.314 |
argon | -0.304 |
Cheney | -0.272 |
lam | -0.259 |
olicy | -0.257 |
Token | ojure |
Token ID | 32511 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
quart | +0.048 |
bucket | +0.046 |
otaur | +0.043 |
strap | +0.043 |
mant | +0.042 |
Neg logit contributions | |
awk | -0.072 |
argon | -0.070 |
Cheney | -0.064 |
olicy | -0.061 |
lam | -0.060 |
Token | according |
Token ID | 1864 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
quart | +0.064 |
bucket | +0.062 |
strap | +0.057 |
mant | +0.057 |
otaur | +0.056 |
Neg logit contributions | |
awk | -0.078 |
argon | -0.075 |
Cheney | -0.067 |
lam | -0.064 |
olicy | -0.063 |
Token | to |
Token ID | 284 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
awk | +0.316 |
argon | +0.306 |
Cheney | +0.274 |
olicy | +0.266 |
lam | +0.263 |
Neg logit contributions | |
quart | -0.187 |
bucket | -0.179 |
strap | -0.164 |
mant | -0.163 |
otaur | -0.161 |
Token | the |
Token ID | 262 |
Feature activation | -4.93e-03 |
Pos logit contributions | |
awk | +0.044 |
argon | +0.042 |
Cheney | +0.037 |
lam | +0.036 |
olicy | +0.035 |
Neg logit contributions | |
quart | -0.035 |
bucket | -0.034 |
strap | -0.031 |
otaur | -0.031 |
mant | -0.031 |
Token | report |
Token ID | 989 |
Feature activation | +9.05e-02 |
Pos logit contributions | |
awk | +0.012 |
argon | +0.012 |
Cheney | +0.011 |
lam | +0.010 |
olicy | +0.010 |
Neg logit contributions | |
quart | -0.010 |
bucket | -0.009 |
strap | -0.009 |
mant | -0.008 |
otaur | -0.008 |
Token | from |
Token ID | 422 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
quart | +0.172 |
bucket | +0.165 |
strap | +0.154 |
otaur | +0.154 |
mant | +0.151 |
Neg logit contributions | |
awk | -0.228 |
argon | -0.221 |
Cheney | -0.197 |
lam | -0.189 |
olicy | -0.187 |
Token | Xin |
Token ID | 25426 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
quart | +0.051 |
bucket | +0.049 |
strap | +0.046 |
otaur | +0.045 |
mant | +0.045 |
Neg logit contributions | |
awk | -0.066 |
argon | -0.064 |
Cheney | -0.057 |
lam | -0.054 |
olicy | -0.054 |
Token | hua |
Token ID | 33061 |
Feature activation | -8.39e-02 |
Pos logit contributions | |
quart | +1.181 |
bucket | +1.130 |
strap | +1.081 |
otaur | +1.078 |
mant | +1.058 |
Neg logit contributions | |
awk | -1.029 |
argon | -1.001 |
Cheney | -0.863 |
olicy | -0.804 |
lam | -0.793 |
Token | . |
Token ID | 764 |
Feature activation | +8.65e-03 |
Pos logit contributions | |
awk | +0.167 |
argon | +0.160 |
Cheney | +0.139 |
lam | +0.131 |
olicy | +0.129 |
Neg logit contributions | |
quart | -0.204 |
bucket | -0.197 |
otaur | -0.187 |
strap | -0.187 |
mant | -0.185 |
Token |
|
Token ID | 198 |
Feature activation | -4.70e-02 |
Pos logit contributions | |
quart | +0.019 |
bucket | +0.018 |
otaur | +0.017 |
strap | +0.017 |
mant | +0.017 |
Neg logit contributions | |
awk | -0.019 |
argon | -0.019 |
Cheney | -0.016 |
lam | -0.016 |
olicy | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -3.97e-02 |
Pos logit contributions | |
awk | +0.116 |
argon | +0.115 |
Cheney | +0.101 |
olicy | +0.100 |
lam | +0.095 |
Neg logit contributions | |
quart | -0.090 |
bucket | -0.087 |
strap | -0.080 |
mant | -0.080 |
otaur | -0.079 |
Token | The |
Token ID | 464 |
Feature activation | -4.83e-02 |
Pos logit contributions | |
awk | +0.083 |
argon | +0.081 |
Cheney | +0.071 |
olicy | +0.067 |
lam | +0.066 |
Neg logit contributions | |
quart | -0.091 |
bucket | -0.088 |
otaur | -0.083 |
strap | -0.083 |
mant | -0.082 |
Token | hole |
Token ID | 13207 |
Feature activation | +8.68e-02 |
Pos logit contributions | |
awk | +0.358 |
argon | +0.348 |
Cheney | +0.324 |
olicy | +0.307 |
Exec | +0.302 |
Neg logit contributions | |
quart | -0.197 |
bucket | -0.191 |
otaur | -0.175 |
strap | -0.174 |
mant | -0.172 |
Token | images |
Token ID | 4263 |
Feature activation | +4.99e-02 |
Pos logit contributions | |
quart | +0.123 |
bucket | +0.116 |
otaur | +0.107 |
strap | +0.106 |
mant | +0.104 |
Neg logit contributions | |
awk | -0.260 |
argon | -0.253 |
Cheney | -0.231 |
lam | -0.223 |
olicy | -0.220 |
Token | for |
Token ID | 329 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
quart | +0.103 |
bucket | +0.099 |
strap | +0.093 |
otaur | +0.092 |
mant | +0.092 |
Neg logit contributions | |
awk | -0.118 |
argon | -0.115 |
Cheney | -0.101 |
olicy | -0.096 |
lam | -0.096 |
Token | a |
Token ID | 257 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
awk | +0.051 |
argon | +0.050 |
Cheney | +0.044 |
lam | +0.042 |
olicy | +0.042 |
Neg logit contributions | |
quart | -0.038 |
bucket | -0.037 |
strap | -0.034 |
otaur | -0.034 |
mant | -0.034 |
Token | typical |
Token ID | 7226 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
awk | +0.050 |
argon | +0.049 |
Cheney | +0.044 |
olicy | +0.042 |
lam | +0.042 |
Neg logit contributions | |
quart | -0.029 |
bucket | -0.028 |
strap | -0.026 |
mant | -0.025 |
otaur | -0.025 |
Token | Canon |
Token ID | 19507 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
awk | +0.028 |
argon | +0.027 |
Cheney | +0.024 |
lam | +0.023 |
olicy | +0.023 |
Neg logit contributions | |
quart | -0.018 |
bucket | -0.017 |
strap | -0.016 |
otaur | -0.016 |
mant | -0.016 |
Token | 16 |
Token ID | 1467 |
Feature activation | -9.28e-02 |
Pos logit contributions | |
awk | +1.511 |
argon | +1.463 |
Cheney | +1.313 |
lam | +1.261 |
olicy | +1.239 |
Neg logit contributions | |
quart | -1.078 |
bucket | -1.031 |
otaur | -0.972 |
strap | -0.963 |
mant | -0.949 |
Token | - |
Token ID | 12 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
awk | +0.201 |
argon | +0.192 |
Cheney | +0.169 |
lam | +0.163 |
hs | +0.159 |
Neg logit contributions | |
quart | -0.205 |
bucket | -0.199 |
otaur | -0.195 |
strap | -0.188 |
mant | -0.186 |
Token | 35 |
Token ID | 2327 |
Feature activation | +6.24e-02 |
Pos logit contributions | |
awk | +0.021 |
argon | +0.020 |
Cheney | +0.015 |
lam | +0.014 |
olicy | +0.013 |
Neg logit contributions | |
quart | -0.053 |
bucket | -0.052 |
strap | -0.050 |
otaur | -0.050 |
mant | -0.050 |
Token | f |
Token ID | 277 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
quart | +0.138 |
bucket | +0.133 |
otaur | +0.127 |
strap | +0.125 |
mant | +0.124 |
Neg logit contributions | |
awk | -0.137 |
argon | -0.132 |
Cheney | -0.116 |
lam | -0.111 |
olicy | -0.108 |
Token | / |
Token ID | 14 |
Feature activation | -9.65e-02 |
Pos logit contributions | |
quart | +0.021 |
bucket | +0.020 |
strap | +0.019 |
mant | +0.018 |
otaur | +0.018 |
Neg logit contributions | |
awk | -0.025 |
argon | -0.025 |
Cheney | -0.022 |
olicy | -0.021 |
lam | -0.020 |
Token | close |
Token ID | 19836 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
awk | +0.172 |
argon | +0.167 |
Cheney | +0.141 |
lam | +0.130 |
olicy | +0.129 |
Neg logit contributions | |
quart | -0.264 |
bucket | -0.257 |
strap | -0.245 |
otaur | -0.244 |
mant | -0.242 |
Token | _ |
Token ID | 62 |
Feature activation | -9.14e-02 |
Pos logit contributions | |
awk | +0.144 |
argon | +0.140 |
Cheney | +0.126 |
lam | +0.121 |
olicy | +0.119 |
Neg logit contributions | |
quart | -0.096 |
bucket | -0.091 |
strap | -0.085 |
otaur | -0.085 |
mant | -0.084 |
Token | and |
Token ID | 392 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
awk | +0.185 |
argon | +0.179 |
Cheney | +0.156 |
lam | +0.145 |
olicy | +0.144 |
Neg logit contributions | |
quart | -0.217 |
bucket | -0.211 |
otaur | -0.200 |
strap | -0.200 |
mant | -0.197 |
Token | _ |
Token ID | 62 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
quart | +0.099 |
bucket | +0.096 |
otaur | +0.091 |
strap | +0.091 |
mant | +0.089 |
Neg logit contributions | |
awk | -0.084 |
argon | -0.082 |
Cheney | -0.071 |
lam | -0.066 |
olicy | -0.066 |
Token | ev |
Token ID | 1990 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
awk | +0.197 |
argon | +0.191 |
Cheney | +0.167 |
olicy | +0.154 |
lam | +0.153 |
Neg logit contributions | |
quart | -0.248 |
bucket | -0.241 |
strap | -0.230 |
otaur | -0.229 |
mant | -0.227 |
Token | ict |
Token ID | 713 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
awk | +0.077 |
argon | +0.074 |
Cheney | +0.064 |
lam | +0.060 |
olicy | +0.059 |
Neg logit contributions | |
quart | -0.095 |
bucket | -0.092 |
otaur | -0.087 |
strap | -0.087 |
mant | -0.086 |
Token | _ |
Token ID | 62 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
awk | +1.320 |
argon | +1.270 |
Cheney | +1.128 |
lam | +1.076 |
olicy | +1.058 |
Neg logit contributions | |
quart | -1.162 |
bucket | -1.109 |
strap | -1.053 |
otaur | -1.052 |
mant | -1.035 |
Token | from |
Token ID | 6738 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
awk | +0.229 |
argon | +0.222 |
Cheney | +0.194 |
olicy | +0.179 |
lam | +0.179 |
Neg logit contributions | |
quart | -0.280 |
bucket | -0.272 |
otaur | -0.258 |
strap | -0.258 |
mant | -0.255 |
Token | _ |
Token ID | 62 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
quart | +0.067 |
bucket | +0.065 |
strap | +0.062 |
otaur | +0.062 |
mant | +0.061 |
Neg logit contributions | |
awk | -0.052 |
argon | -0.050 |
Cheney | -0.043 |
lam | -0.041 |
olicy | -0.040 |
Token | os |
Token ID | 418 |
Feature activation | -6.20e-02 |
Pos logit contributions | |
awk | +0.265 |
argon | +0.255 |
Cheney | +0.221 |
lam | +0.207 |
olicy | +0.205 |
Neg logit contributions | |
quart | -0.326 |
bucket | -0.316 |
strap | -0.300 |
otaur | -0.300 |
mant | -0.296 |
Token | _ |
Token ID | 62 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
awk | +0.134 |
argon | +0.129 |
Cheney | +0.113 |
lam | +0.107 |
olicy | +0.106 |
Neg logit contributions | |
quart | -0.140 |
bucket | -0.135 |
otaur | -0.128 |
strap | -0.127 |
mant | -0.126 |
Token | students |
Token ID | 2444 |
Feature activation | +5.75e-02 |
Pos logit contributions | |
quart | +0.204 |
bucket | +0.195 |
strap | +0.183 |
mant | +0.180 |
otaur | +0.180 |
Neg logit contributions | |
awk | -0.275 |
argon | -0.267 |
Cheney | -0.239 |
lam | -0.229 |
olicy | -0.227 |
Token | recently |
Token ID | 2904 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
quart | +0.112 |
bucket | +0.107 |
strap | +0.101 |
otaur | +0.100 |
mant | +0.099 |
Neg logit contributions | |
awk | -0.143 |
argon | -0.139 |
Cheney | -0.123 |
olicy | -0.118 |
lam | -0.117 |
Token | won |
Token ID | 1839 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
awk | +0.095 |
argon | +0.093 |
Cheney | +0.083 |
olicy | +0.080 |
lam | +0.079 |
Neg logit contributions | |
quart | -0.064 |
bucket | -0.060 |
strap | -0.057 |
mant | -0.055 |
otaur | -0.055 |
Token | an |
Token ID | 281 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
awk | +0.090 |
argon | +0.087 |
Cheney | +0.078 |
lam | +0.074 |
olicy | +0.073 |
Neg logit contributions | |
quart | -0.072 |
bucket | -0.069 |
strap | -0.064 |
otaur | -0.064 |
mant | -0.064 |
Token | Air |
Token ID | 3701 |
Feature activation | +8.14e-02 |
Pos logit contributions | |
awk | +0.033 |
argon | +0.032 |
Cheney | +0.028 |
lam | +0.027 |
olicy | +0.026 |
Neg logit contributions | |
quart | -0.027 |
bucket | -0.026 |
strap | -0.025 |
otaur | -0.025 |
mant | -0.024 |
Token | Force |
Token ID | 5221 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
quart | +0.177 |
bucket | +0.171 |
otaur | +0.161 |
strap | +0.161 |
mant | +0.159 |
Neg logit contributions | |
awk | -0.182 |
argon | -0.176 |
Cheney | -0.155 |
lam | -0.147 |
olicy | -0.145 |
Token | - |
Token ID | 12 |
Feature activation | +7.00e-02 |
Pos logit contributions | |
awk | +1.282 |
argon | +1.237 |
Cheney | +1.103 |
lam | +1.046 |
olicy | +1.032 |
Neg logit contributions | |
quart | -1.150 |
bucket | -1.103 |
otaur | -1.047 |
strap | -1.039 |
mant | -1.028 |
Token | sponsored |
Token ID | 25427 |
Feature activation | -9.50e-02 |
Pos logit contributions | |
quart | +0.142 |
bucket | +0.136 |
strap | +0.128 |
otaur | +0.128 |
mant | +0.126 |
Neg logit contributions | |
awk | -0.167 |
argon | -0.162 |
Cheney | -0.144 |
lam | -0.137 |
olicy | -0.136 |
Token | competition |
Token ID | 5449 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
awk | +0.240 |
argon | +0.233 |
Cheney | +0.207 |
lam | +0.198 |
olicy | +0.196 |
Neg logit contributions | |
quart | -0.181 |
bucket | -0.174 |
strap | -0.163 |
otaur | -0.161 |
mant | -0.160 |
Token | with |
Token ID | 351 |
Feature activation | +5.97e-03 |
Pos logit contributions | |
quart | +0.245 |
bucket | +0.235 |
strap | +0.220 |
otaur | +0.219 |
mant | +0.217 |
Neg logit contributions | |
awk | -0.324 |
argon | -0.313 |
Cheney | -0.281 |
lam | -0.266 |
olicy | -0.265 |
Token | Ohio |
Token ID | 6835 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
quart | +0.012 |
bucket | +0.011 |
strap | +0.011 |
otaur | +0.011 |
mant | +0.011 |
Neg logit contributions | |
awk | -0.015 |
argon | -0.014 |
Cheney | -0.013 |
lam | -0.012 |
olicy | -0.012 |
Token | AM |
Token ID | 2390 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
argon | +0.379 |
awk | +0.377 |
Cheney | +0.320 |
olicy | +0.311 |
lam | +0.308 |
Neg logit contributions | |
quart | -0.424 |
bucket | -0.405 |
strap | -0.384 |
otaur | -0.380 |
mant | -0.378 |
Token | / |
Token ID | 14 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
quart | +0.067 |
bucket | +0.064 |
strap | +0.061 |
otaur | +0.060 |
mant | +0.060 |
Neg logit contributions | |
awk | -0.078 |
argon | -0.075 |
Cheney | -0.066 |
olicy | -0.063 |
lam | -0.063 |
Token | THE |
Token ID | 10970 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
awk | +0.248 |
argon | +0.238 |
Cheney | +0.209 |
olicy | +0.194 |
lam | +0.192 |
Neg logit contributions | |
quart | -0.290 |
bucket | -0.281 |
otaur | -0.268 |
strap | -0.267 |
mant | -0.263 |
Token | NEWS |
Token ID | 28840 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
awk | +0.182 |
argon | +0.175 |
Cheney | +0.145 |
olicy | +0.138 |
lam | +0.136 |
Neg logit contributions | |
quart | -0.270 |
bucket | -0.261 |
otaur | -0.250 |
strap | -0.248 |
mant | -0.247 |
Token | J |
Token ID | 449 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
awk | +0.467 |
argon | +0.451 |
Cheney | +0.404 |
lam | +0.387 |
olicy | +0.380 |
Neg logit contributions | |
quart | -0.353 |
bucket | -0.339 |
strap | -0.318 |
otaur | -0.318 |
mant | -0.314 |
Token | OUR |
Token ID | 11698 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
awk | +0.151 |
argon | +0.147 |
Cheney | +0.133 |
lam | +0.127 |
olicy | +0.126 |
Neg logit contributions | |
quart | -0.112 |
bucket | -0.107 |
otaur | -0.101 |
strap | -0.100 |
mant | -0.098 |
Token | N |
Token ID | 45 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
awk | +1.165 |
argon | +1.132 |
Cheney | +0.980 |
lam | +0.924 |
olicy | +0.923 |
Neg logit contributions | |
quart | -1.272 |
bucket | -1.220 |
strap | -1.162 |
otaur | -1.160 |
mant | -1.145 |
Token | AL |
Token ID | 1847 |
Feature activation | -7.08e-02 |
Pos logit contributions | |
awk | +0.338 |
argon | +0.330 |
Cheney | +0.284 |
lam | +0.274 |
olicy | +0.272 |
Neg logit contributions | |
quart | -0.342 |
bucket | -0.329 |
otaur | -0.312 |
strap | -0.310 |
mant | -0.306 |
Token | ) |
Token ID | 8 |
Feature activation | -5.37e-02 |
Pos logit contributions | |
awk | +0.158 |
argon | +0.153 |
Cheney | +0.135 |
lam | +0.128 |
olicy | +0.126 |
Neg logit contributions | |
quart | -0.154 |
bucket | -0.149 |
otaur | -0.141 |
strap | -0.140 |
mant | -0.139 |
Token | Buy |
Token ID | 14518 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
awk | +0.123 |
argon | +0.119 |
Cheney | +0.105 |
lam | +0.100 |
olicy | +0.099 |
Neg logit contributions | |
quart | -0.114 |
bucket | -0.110 |
otaur | -0.103 |
strap | -0.103 |
mant | -0.102 |
Token | Photo |
Token ID | 5555 |
Feature activation | +5.73e-02 |
Pos logit contributions | |
awk | +0.066 |
argon | +0.065 |
olicy | +0.059 |
Cheney | +0.057 |
lam | +0.057 |
Neg logit contributions | |
quart | -0.028 |
bucket | -0.027 |
strap | -0.023 |
mant | -0.023 |
otaur | -0.023 |
Token | Cot |
Token ID | 42266 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
awk | +0.300 |
argon | +0.291 |
Cheney | +0.251 |
olicy | +0.242 |
lam | +0.242 |
Neg logit contributions | |
quart | -0.276 |
bucket | -0.266 |
strap | -0.251 |
otaur | -0.251 |
mant | -0.248 |
Token | é |
Token ID | 2634 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
awk | +1.413 |
argon | +1.376 |
Cheney | +1.243 |
lam | +1.188 |
olicy | +1.185 |
Neg logit contributions | |
quart | -0.838 |
bucket | -0.798 |
strap | -0.739 |
otaur | -0.739 |
mant | -0.723 |
Token | , |
Token ID | 11 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
awk | +0.117 |
argon | +0.114 |
Cheney | +0.100 |
olicy | +0.095 |
lam | +0.095 |
Neg logit contributions | |
quart | -0.101 |
bucket | -0.097 |
strap | -0.091 |
otaur | -0.091 |
mant | -0.090 |
Token | founder |
Token ID | 9119 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
quart | +0.037 |
bucket | +0.036 |
strap | +0.034 |
otaur | +0.033 |
mant | +0.033 |
Neg logit contributions | |
awk | -0.048 |
argon | -0.047 |
Cheney | -0.041 |
lam | -0.040 |
olicy | -0.039 |
Token | of |
Token ID | 286 |
Feature activation | -6.63e-02 |
Pos logit contributions | |
awk | +0.413 |
argon | +0.400 |
Cheney | +0.358 |
lam | +0.341 |
olicy | +0.337 |
Neg logit contributions | |
quart | -0.330 |
bucket | -0.317 |
strap | -0.297 |
otaur | -0.297 |
mant | -0.294 |
Token | Cot |
Token ID | 42266 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
awk | +0.159 |
argon | +0.154 |
Cheney | +0.136 |
lam | +0.130 |
olicy | +0.128 |
Neg logit contributions | |
quart | -0.134 |
bucket | -0.129 |
strap | -0.121 |
otaur | -0.121 |
mant | -0.120 |
Token | é |
Token ID | 2634 |
Feature activation | -7.33e-02 |
Pos logit contributions | |
awk | +1.487 |
argon | +1.442 |
Cheney | +1.302 |
lam | +1.251 |
olicy | +1.237 |
Neg logit contributions | |
quart | -0.939 |
bucket | -0.896 |
otaur | -0.833 |
strap | -0.833 |
mant | -0.821 |
Token | Or |
Token ID | 1471 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
awk | +0.168 |
argon | +0.163 |
Cheney | +0.143 |
lam | +0.136 |
olicy | +0.134 |
Neg logit contributions | |
quart | -0.156 |
bucket | -0.149 |
strap | -0.141 |
otaur | -0.141 |
mant | -0.139 |
Token | phan |
Token ID | 19080 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
quart | +0.054 |
bucket | +0.052 |
otaur | +0.050 |
strap | +0.050 |
mant | +0.049 |
Neg logit contributions | |
awk | -0.049 |
argon | -0.047 |
Cheney | -0.041 |
lam | -0.039 |
olicy | -0.039 |
Token | Consulting |
Token ID | 41005 |
Feature activation | -9.82e-02 |
Pos logit contributions | |
quart | +0.595 |
bucket | +0.570 |
otaur | +0.539 |
strap | +0.536 |
mant | +0.529 |
Neg logit contributions | |
awk | -0.637 |
argon | -0.621 |
Cheney | -0.544 |
lam | -0.517 |
olicy | -0.512 |
Token | in |
Token ID | 287 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
awk | +0.235 |
argon | +0.227 |
Cheney | +0.200 |
lam | +0.191 |
olicy | +0.189 |
Neg logit contributions | |
quart | -0.200 |
bucket | -0.191 |
strap | -0.180 |
otaur | -0.179 |
mant | -0.177 |
Token | ū |
Token ID | 20317 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
awk | +0.360 |
argon | +0.348 |
Cheney | +0.309 |
lam | +0.293 |
olicy | +0.290 |
Neg logit contributions | |
quart | -0.318 |
bucket | -0.306 |
strap | -0.289 |
otaur | -0.288 |
mant | -0.285 |
Token | ke |
Token ID | 885 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
awk | +0.534 |
argon | +0.514 |
Cheney | +0.449 |
lam | +0.422 |
olicy | +0.418 |
Neg logit contributions | |
quart | -0.597 |
bucket | -0.576 |
strap | -0.547 |
otaur | -0.546 |
mant | -0.541 |
Token | k |
Token ID | 74 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
awk | +0.573 |
argon | +0.554 |
Cheney | +0.488 |
lam | +0.460 |
olicy | +0.457 |
Neg logit contributions | |
quart | -0.569 |
bucket | -0.548 |
strap | -0.518 |
otaur | -0.516 |
mant | -0.513 |
Token | ahi |
Token ID | 32810 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
awk | +0.356 |
argon | +0.345 |
Cheney | +0.306 |
lam | +0.289 |
olicy | +0.287 |
Neg logit contributions | |
quart | -0.324 |
bucket | -0.312 |
strap | -0.294 |
otaur | -0.293 |
mant | -0.291 |
Token | e |
Token ID | 304 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
quart | +0.033 |
bucket | +0.031 |
strap | +0.029 |
otaur | +0.029 |
mant | +0.029 |
Neg logit contributions | |
awk | -0.036 |
argon | -0.035 |
Cheney | -0.031 |
lam | -0.029 |
olicy | -0.029 |
Token | pi |
Token ID | 31028 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
awk | +0.618 |
argon | +0.597 |
Cheney | +0.525 |
lam | +0.497 |
olicy | +0.492 |
Neg logit contributions | |
quart | -0.610 |
bucket | -0.588 |
strap | -0.556 |
otaur | -0.555 |
mant | -0.549 |
Token | ha |
Token ID | 3099 |
Feature activation | -5.34e-02 |
Pos logit contributions | |
awk | +1.338 |
argon | +1.293 |
Cheney | +1.148 |
lam | +1.103 |
olicy | +1.084 |
Neg logit contributions | |
quart | -1.076 |
bucket | -1.035 |
otaur | -0.974 |
strap | -0.972 |
mant | -0.954 |
Token | a |
Token ID | 257 |
Feature activation | -8.57e-02 |
Pos logit contributions | |
awk | +0.125 |
argon | +0.121 |
Cheney | +0.107 |
lam | +0.102 |
olicy | +0.101 |
Neg logit contributions | |
quart | -0.111 |
bucket | -0.106 |
strap | -0.100 |
otaur | -0.100 |
mant | -0.099 |
Token | i |
Token ID | 72 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
awk | +0.197 |
argon | +0.191 |
Cheney | +0.169 |
lam | +0.160 |
olicy | +0.159 |
Neg logit contributions | |
quart | -0.181 |
bucket | -0.174 |
strap | -0.164 |
otaur | -0.164 |
mant | -0.162 |
Token | Ka |
Token ID | 11611 |
Feature activation | -9.84e-02 |
Pos logit contributions | |
awk | +0.450 |
argon | +0.435 |
Cheney | +0.386 |
lam | +0.368 |
olicy | +0.363 |
Neg logit contributions | |
quart | -0.388 |
bucket | -0.373 |
otaur | -0.351 |
strap | -0.351 |
mant | -0.346 |
Token | Pap |
Token ID | 14185 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
awk | +0.237 |
argon | +0.230 |
Cheney | +0.205 |
lam | +0.195 |
olicy | +0.193 |
Neg logit contributions | |
quart | -0.197 |
bucket | -0.189 |
strap | -0.178 |
otaur | -0.177 |
mant | -0.175 |
Token | of |
Token ID | 286 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
awk | +0.177 |
argon | +0.172 |
Cheney | +0.153 |
lam | +0.147 |
olicy | +0.145 |
Neg logit contributions | |
quart | -0.133 |
bucket | -0.127 |
strap | -0.119 |
otaur | -0.119 |
mant | -0.117 |
Token | the |
Token ID | 262 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
quart | +0.082 |
bucket | +0.080 |
mant | +0.076 |
strap | +0.075 |
otaur | +0.074 |
Neg logit contributions | |
awk | -0.076 |
argon | -0.074 |
Cheney | -0.063 |
olicy | -0.062 |
lam | -0.061 |
Token | United |
Token ID | 1578 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
quart | +0.076 |
bucket | +0.074 |
strap | +0.070 |
mant | +0.069 |
otaur | +0.069 |
Neg logit contributions | |
awk | -0.077 |
argon | -0.074 |
Cheney | -0.063 |
lam | -0.062 |
olicy | -0.062 |
Token | States |
Token ID | 1829 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
awk | +0.235 |
argon | +0.227 |
Cheney | +0.193 |
olicy | +0.187 |
lam | +0.183 |
Neg logit contributions | |
quart | -0.299 |
bucket | -0.286 |
strap | -0.275 |
mant | -0.270 |
otaur | -0.268 |
Token | Air |
Token ID | 3701 |
Feature activation | +9.16e-02 |
Pos logit contributions | |
quart | +0.043 |
bucket | +0.042 |
strap | +0.039 |
otaur | +0.039 |
mant | +0.039 |
Neg logit contributions | |
awk | -0.050 |
argon | -0.048 |
Cheney | -0.042 |
lam | -0.040 |
olicy | -0.040 |
Token | Force |
Token ID | 5221 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
quart | +0.197 |
bucket | +0.190 |
strap | +0.179 |
otaur | +0.179 |
mant | +0.177 |
Neg logit contributions | |
awk | -0.207 |
argon | -0.200 |
Cheney | -0.176 |
lam | -0.168 |
olicy | -0.166 |
Token | in |
Token ID | 287 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
awk | +1.319 |
argon | +1.276 |
Cheney | +1.133 |
lam | +1.083 |
olicy | +1.071 |
Neg logit contributions | |
quart | -1.096 |
bucket | -1.054 |
strap | -0.990 |
otaur | -0.988 |
mant | -0.976 |
Token | Dayton |
Token ID | 24450 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
quart | +0.121 |
bucket | +0.116 |
strap | +0.110 |
otaur | +0.110 |
mant | +0.109 |
Neg logit contributions | |
awk | -0.111 |
argon | -0.108 |
Cheney | -0.092 |
lam | -0.089 |
olicy | -0.089 |
Token | , |
Token ID | 11 |
Feature activation | +5.83e-02 |
Pos logit contributions | |
quart | +0.027 |
bucket | +0.026 |
strap | +0.024 |
otaur | +0.024 |
mant | +0.024 |
Neg logit contributions | |
awk | -0.031 |
argon | -0.030 |
Cheney | -0.027 |
lam | -0.026 |
olicy | -0.025 |
Token | Ohio |
Token ID | 6835 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
quart | +0.120 |
bucket | +0.116 |
strap | +0.109 |
otaur | +0.109 |
mant | +0.107 |
Neg logit contributions | |
awk | -0.137 |
argon | -0.133 |
Cheney | -0.117 |
lam | -0.112 |
olicy | -0.111 |
Token | . |
Token ID | 13 |
Feature activation | +5.93e-02 |
Pos logit contributions | |
quart | +0.351 |
bucket | +0.337 |
strap | +0.317 |
otaur | +0.314 |
mant | +0.312 |
Neg logit contributions | |
awk | -0.428 |
argon | -0.414 |
Cheney | -0.368 |
lam | -0.352 |
olicy | -0.349 |
Token | { |
Token ID | 1391 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
quart | +0.032 |
bucket | +0.031 |
strap | +0.029 |
otaur | +0.028 |
mant | +0.028 |
Neg logit contributions | |
awk | -0.043 |
argon | -0.042 |
Cheney | -0.037 |
lam | -0.036 |
olicy | -0.036 |
Token | 1 |
Token ID | 16 |
Feature activation | +5.03e-02 |
Pos logit contributions | |
awk | +0.583 |
argon | +0.559 |
Cheney | +0.474 |
lam | +0.438 |
olicy | +0.435 |
Neg logit contributions | |
quart | -0.892 |
bucket | -0.868 |
strap | -0.824 |
otaur | -0.822 |
mant | -0.816 |
Token | , |
Token ID | 11 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
quart | +0.106 |
bucket | +0.102 |
strap | +0.097 |
otaur | +0.097 |
mant | +0.096 |
Neg logit contributions | |
awk | -0.115 |
argon | -0.111 |
Cheney | -0.099 |
lam | -0.094 |
olicy | -0.092 |
Token | 6 |
Token ID | 21 |
Feature activation | +9.26e-02 |
Pos logit contributions | |
awk | +0.273 |
argon | +0.263 |
Cheney | +0.223 |
lam | +0.211 |
olicy | +0.210 |
Neg logit contributions | |
quart | -0.367 |
bucket | -0.355 |
strap | -0.336 |
otaur | -0.335 |
mant | -0.332 |
Token | }, |
Token ID | 5512 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
quart | +0.168 |
bucket | +0.161 |
otaur | +0.149 |
strap | +0.149 |
mant | +0.147 |
Neg logit contributions | |
awk | -0.242 |
argon | -0.234 |
Cheney | -0.210 |
lam | -0.201 |
olicy | -0.200 |
Token | { |
Token ID | 90 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
quart | +0.457 |
bucket | +0.442 |
strap | +0.414 |
otaur | +0.412 |
mant | +0.408 |
Neg logit contributions | |
awk | -0.503 |
argon | -0.484 |
Cheney | -0.428 |
lam | -0.406 |
olicy | -0.403 |
Token | 1 |
Token ID | 16 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
awk | +0.900 |
argon | +0.856 |
Cheney | +0.721 |
lam | +0.666 |
olicy | +0.659 |
Neg logit contributions | |
quart | -1.468 |
bucket | -1.426 |
strap | -1.362 |
otaur | -1.361 |
mant | -1.348 |
Token | , |
Token ID | 11 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
quart | +0.056 |
bucket | +0.054 |
strap | +0.050 |
otaur | +0.049 |
mant | +0.049 |
Neg logit contributions | |
awk | -0.078 |
argon | -0.076 |
Cheney | -0.067 |
olicy | -0.066 |
lam | -0.064 |
Token | 7 |
Token ID | 22 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
awk | +0.325 |
argon | +0.314 |
Cheney | +0.269 |
lam | +0.255 |
olicy | +0.254 |
Neg logit contributions | |
quart | -0.396 |
bucket | -0.382 |
strap | -0.361 |
otaur | -0.360 |
mant | -0.357 |
Token | }, |
Token ID | 5512 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
awk | +0.145 |
argon | +0.141 |
Cheney | +0.126 |
lam | +0.121 |
olicy | +0.120 |
Neg logit contributions | |
quart | -0.104 |
bucket | -0.099 |
strap | -0.093 |
otaur | -0.093 |
mant | -0.091 |
Token | { |
Token ID | 90 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
quart | +0.659 |
bucket | +0.643 |
otaur | +0.620 |
strap | +0.620 |
mant | +0.615 |
Neg logit contributions | |
awk | -0.211 |
argon | -0.195 |
Cheney | -0.145 |
lam | -0.126 |
olicy | -0.121 |
Token | { |
Token ID | 90 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
quart | +0.659 |
bucket | +0.643 |
otaur | +0.620 |
strap | +0.620 |
mant | +0.615 |
Neg logit contributions | |
awk | -0.211 |
argon | -0.195 |
Cheney | -0.145 |
lam | -0.126 |
olicy | -0.121 |
Token | 2 |
Token ID | 17 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
awk | +0.814 |
argon | +0.777 |
Cheney | +0.631 |
lam | +0.593 |
olicy | +0.569 |
Neg logit contributions | |
quart | -1.507 |
bucket | -1.465 |
strap | -1.408 |
otaur | -1.404 |
mant | -1.395 |
Token | , |
Token ID | 11 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
awk | +0.094 |
argon | +0.093 |
Cheney | +0.082 |
olicy | +0.081 |
lam | +0.078 |
Neg logit contributions | |
quart | -0.067 |
bucket | -0.064 |
strap | -0.059 |
otaur | -0.059 |
mant | -0.058 |
Token | 6 |
Token ID | 21 |
Feature activation | +5.96e-02 |
Pos logit contributions | |
awk | +0.280 |
argon | +0.268 |
Cheney | +0.220 |
lam | +0.205 |
olicy | +0.204 |
Neg logit contributions | |
quart | -0.489 |
bucket | -0.473 |
strap | -0.452 |
otaur | -0.451 |
mant | -0.447 |
Token | }, |
Token ID | 5512 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
quart | +0.109 |
bucket | +0.104 |
strap | +0.098 |
otaur | +0.097 |
mant | +0.096 |
Neg logit contributions | |
awk | -0.154 |
argon | -0.149 |
Cheney | -0.134 |
lam | -0.128 |
olicy | -0.127 |
Token | { |
Token ID | 90 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
quart | +0.627 |
bucket | +0.612 |
strap | +0.591 |
otaur | +0.591 |
mant | +0.586 |
Neg logit contributions | |
awk | -0.192 |
argon | -0.178 |
Cheney | -0.130 |
lam | -0.112 |
olicy | -0.108 |
Token | 2 |
Token ID | 17 |
Feature activation | -5.99e-02 |
Pos logit contributions | |
awk | +0.954 |
argon | +0.914 |
Cheney | +0.765 |
lam | +0.728 |
bb | +0.702 |
Neg logit contributions | |
quart | -1.410 |
bucket | -1.372 |
strap | -1.313 |
otaur | -1.309 |
mant | -1.298 |
Token | , |
Token ID | 11 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
awk | +0.154 |
argon | +0.152 |
Cheney | +0.135 |
olicy | +0.133 |
lam | +0.128 |
Neg logit contributions | |
quart | -0.109 |
bucket | -0.104 |
strap | -0.096 |
otaur | -0.095 |
mant | -0.095 |
Token | 7 |
Token ID | 22 |
Feature activation | -8.90e-02 |
Pos logit contributions | |
awk | +0.273 |
argon | +0.263 |
Cheney | +0.211 |
olicy | +0.196 |
lam | +0.196 |
Neg logit contributions | |
quart | -0.532 |
bucket | -0.516 |
strap | -0.493 |
otaur | -0.492 |
mant | -0.489 |
Token | } |
Token ID | 92 |
Feature activation | +8.62e-02 |
Pos logit contributions | |
awk | +0.230 |
argon | +0.223 |
Cheney | +0.201 |
lam | +0.192 |
olicy | +0.190 |
Neg logit contributions | |
quart | -0.162 |
bucket | -0.155 |
strap | -0.146 |
otaur | -0.145 |
mant | -0.143 |
Token | and |
Token ID | 290 |
Feature activation | -4.83e-02 |
Pos logit contributions | |
quart | +0.175 |
bucket | +0.169 |
strap | +0.158 |
otaur | +0.157 |
mant | +0.156 |
Neg logit contributions | |
awk | -0.206 |
argon | -0.200 |
Cheney | -0.177 |
lam | -0.169 |
olicy | -0.168 |
Token |
|
Token ID | 198 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
quart | +0.007 |
bucket | +0.007 |
strap | +0.007 |
mant | +0.007 |
otaur | +0.006 |
Neg logit contributions | |
awk | -0.009 |
argon | -0.009 |
Cheney | -0.008 |
olicy | -0.008 |
lam | -0.008 |
Token | Opp |
Token ID | 27524 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
quart | +0.058 |
bucket | +0.056 |
otaur | +0.053 |
strap | +0.053 |
mant | +0.052 |
Neg logit contributions | |
awk | -0.053 |
argon | -0.051 |
Cheney | -0.045 |
olicy | -0.042 |
lam | -0.042 |
Token | onent |
Token ID | 3471 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
quart | +0.033 |
bucket | +0.032 |
strap | +0.030 |
otaur | +0.030 |
mant | +0.030 |
Neg logit contributions | |
awk | -0.031 |
argon | -0.030 |
Cheney | -0.026 |
lam | -0.025 |
olicy | -0.024 |
Token | : |
Token ID | 25 |
Feature activation | -5.52e-03 |
Pos logit contributions | |
awk | +0.489 |
argon | +0.473 |
Cheney | +0.425 |
lam | +0.408 |
olicy | +0.401 |
Neg logit contributions | |
quart | -0.352 |
bucket | -0.336 |
otaur | -0.318 |
strap | -0.316 |
mant | -0.311 |
Token | Air |
Token ID | 3701 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
awk | +0.013 |
argon | +0.012 |
Cheney | +0.011 |
olicy | +0.010 |
lam | +0.010 |
Neg logit contributions | |
quart | -0.012 |
bucket | -0.011 |
strap | -0.011 |
otaur | -0.010 |
mant | -0.010 |
Token | Force |
Token ID | 5221 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
quart | +0.034 |
bucket | +0.032 |
otaur | +0.031 |
strap | +0.031 |
mant | +0.030 |
Neg logit contributions | |
awk | -0.034 |
argon | -0.032 |
Cheney | -0.029 |
lam | -0.027 |
olicy | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
awk | +1.209 |
argon | +1.166 |
Cheney | +1.032 |
lam | +0.979 |
olicy | +0.963 |
Neg logit contributions | |
quart | -1.130 |
bucket | -1.091 |
otaur | -1.035 |
strap | -1.031 |
mant | -1.019 |
Token |
|
Token ID | 198 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
quart | +0.052 |
bucket | +0.051 |
strap | +0.047 |
mant | +0.046 |
otaur | +0.046 |
Neg logit contributions | |
awk | -0.067 |
argon | -0.066 |
Cheney | -0.058 |
olicy | -0.057 |
lam | -0.055 |
Token | Date |
Token ID | 10430 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
quart | +0.089 |
bucket | +0.086 |
otaur | +0.081 |
strap | +0.081 |
mant | +0.080 |
Neg logit contributions | |
awk | -0.080 |
argon | -0.078 |
Cheney | -0.068 |
olicy | -0.065 |
lam | -0.064 |
Token | : |
Token ID | 25 |
Feature activation | +5.10e-02 |
Pos logit contributions | |
awk | +0.028 |
argon | +0.027 |
Cheney | +0.024 |
lam | +0.023 |
olicy | +0.023 |
Neg logit contributions | |
quart | -0.022 |
bucket | -0.021 |
strap | -0.019 |
otaur | -0.019 |
mant | -0.019 |
Token | Nov |
Token ID | 5267 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
quart | +0.100 |
bucket | +0.095 |
strap | +0.089 |
mant | +0.087 |
otaur | +0.086 |
Neg logit contributions | |
awk | -0.127 |
argon | -0.124 |
Cheney | -0.107 |
olicy | -0.106 |
lam | -0.105 |
Token | , |
Token ID | 11 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
awk | +0.211 |
argon | +0.204 |
Cheney | +0.182 |
lam | +0.173 |
olicy | +0.171 |
Neg logit contributions | |
quart | -0.181 |
bucket | -0.174 |
otaur | -0.164 |
strap | -0.164 |
mant | -0.162 |
Token | there |
Token ID | 612 |
Feature activation | -4.06e-02 |
Pos logit contributions | |
awk | +0.072 |
argon | +0.070 |
Cheney | +0.061 |
lam | +0.059 |
olicy | +0.059 |
Neg logit contributions | |
quart | -0.055 |
bucket | -0.053 |
strap | -0.049 |
mant | -0.048 |
otaur | -0.048 |
Token | was |
Token ID | 373 |
Feature activation | -8.90e-02 |
Pos logit contributions | |
awk | +0.107 |
argon | +0.104 |
Cheney | +0.094 |
lam | +0.090 |
olicy | +0.089 |
Neg logit contributions | |
quart | -0.072 |
bucket | -0.069 |
strap | -0.064 |
otaur | -0.064 |
mant | -0.063 |
Token | a |
Token ID | 257 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
awk | +0.229 |
argon | +0.222 |
Cheney | +0.198 |
lam | +0.189 |
olicy | +0.188 |
Neg logit contributions | |
quart | -0.165 |
bucket | -0.159 |
strap | -0.148 |
otaur | -0.147 |
mant | -0.145 |
Token | small |
Token ID | 1402 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
awk | +0.061 |
argon | +0.060 |
Cheney | +0.053 |
lam | +0.051 |
olicy | +0.051 |
Neg logit contributions | |
quart | -0.044 |
bucket | -0.042 |
strap | -0.039 |
mant | -0.039 |
otaur | -0.039 |
Token | shack |
Token ID | 32772 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
awk | +0.076 |
argon | +0.074 |
Cheney | +0.066 |
lam | +0.063 |
olicy | +0.063 |
Neg logit contributions | |
quart | -0.052 |
bucket | -0.050 |
strap | -0.046 |
otaur | -0.046 |
mant | -0.045 |
Token | at |
Token ID | 379 |
Feature activation | -5.96e-02 |
Pos logit contributions | |
awk | +1.279 |
argon | +1.236 |
Cheney | +1.101 |
lam | +1.054 |
olicy | +1.038 |
Neg logit contributions | |
quart | -1.045 |
bucket | -1.004 |
otaur | -0.945 |
strap | -0.943 |
mant | -0.930 |
Token | the |
Token ID | 262 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
awk | +0.142 |
argon | +0.138 |
Cheney | +0.122 |
lam | +0.117 |
olicy | +0.115 |
Neg logit contributions | |
quart | -0.121 |
bucket | -0.116 |
otaur | -0.109 |
strap | -0.109 |
mant | -0.108 |
Token | river |
Token ID | 7850 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
awk | +0.098 |
argon | +0.096 |
Cheney | +0.086 |
lam | +0.083 |
olicy | +0.083 |
Neg logit contributions | |
quart | -0.056 |
bucket | -0.054 |
strap | -0.050 |
otaur | -0.049 |
mant | -0.049 |
Token | for |
Token ID | 329 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
quart | +0.372 |
bucket | +0.356 |
otaur | +0.333 |
strap | +0.333 |
mant | +0.328 |
Neg logit contributions | |
awk | -0.510 |
argon | -0.494 |
Cheney | -0.443 |
lam | -0.424 |
olicy | -0.419 |
Token | emergency |
Token ID | 6334 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
awk | +0.123 |
argon | +0.119 |
Cheney | +0.106 |
lam | +0.102 |
olicy | +0.102 |
Neg logit contributions | |
quart | -0.090 |
bucket | -0.086 |
strap | -0.081 |
otaur | -0.079 |
mant | -0.079 |
Token | { |
Token ID | 90 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
quart | +0.457 |
bucket | +0.442 |
strap | +0.414 |
otaur | +0.412 |
mant | +0.408 |
Neg logit contributions | |
awk | -0.503 |
argon | -0.484 |
Cheney | -0.428 |
lam | -0.406 |
olicy | -0.403 |
Token | 1 |
Token ID | 16 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
awk | +0.900 |
argon | +0.856 |
Cheney | +0.721 |
lam | +0.666 |
olicy | +0.659 |
Neg logit contributions | |
quart | -1.468 |
bucket | -1.426 |
strap | -1.362 |
otaur | -1.361 |
mant | -1.348 |
Token | , |
Token ID | 11 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
quart | +0.056 |
bucket | +0.054 |
strap | +0.050 |
otaur | +0.049 |
mant | +0.049 |
Neg logit contributions | |
awk | -0.078 |
argon | -0.076 |
Cheney | -0.067 |
olicy | -0.066 |
lam | -0.064 |
Token | 7 |
Token ID | 22 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
awk | +0.325 |
argon | +0.314 |
Cheney | +0.269 |
lam | +0.255 |
olicy | +0.254 |
Neg logit contributions | |
quart | -0.396 |
bucket | -0.382 |
strap | -0.361 |
otaur | -0.360 |
mant | -0.357 |
Token | }, |
Token ID | 5512 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
awk | +0.145 |
argon | +0.141 |
Cheney | +0.126 |
lam | +0.121 |
olicy | +0.120 |
Neg logit contributions | |
quart | -0.104 |
bucket | -0.099 |
strap | -0.093 |
otaur | -0.093 |
mant | -0.091 |
Token | { |
Token ID | 90 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
quart | +0.659 |
bucket | +0.643 |
otaur | +0.620 |
strap | +0.620 |
mant | +0.615 |
Neg logit contributions | |
awk | -0.211 |
argon | -0.195 |
Cheney | -0.145 |
lam | -0.126 |
olicy | -0.121 |
Token | 2 |
Token ID | 17 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
awk | +0.814 |
argon | +0.777 |
Cheney | +0.631 |
lam | +0.593 |
olicy | +0.569 |
Neg logit contributions | |
quart | -1.507 |
bucket | -1.465 |
strap | -1.408 |
otaur | -1.404 |
mant | -1.395 |
Token | , |
Token ID | 11 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
awk | +0.094 |
argon | +0.093 |
Cheney | +0.082 |
olicy | +0.081 |
lam | +0.078 |
Neg logit contributions | |
quart | -0.067 |
bucket | -0.064 |
strap | -0.059 |
otaur | -0.059 |
mant | -0.058 |
Token | 6 |
Token ID | 21 |
Feature activation | +5.96e-02 |
Pos logit contributions | |
awk | +0.280 |
argon | +0.268 |
Cheney | +0.220 |
lam | +0.205 |
olicy | +0.204 |
Neg logit contributions | |
quart | -0.489 |
bucket | -0.473 |
strap | -0.452 |
otaur | -0.451 |
mant | -0.447 |
Token | }, |
Token ID | 5512 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
quart | +0.109 |
bucket | +0.104 |
strap | +0.098 |
otaur | +0.097 |
mant | +0.096 |
Neg logit contributions | |
awk | -0.154 |
argon | -0.149 |
Cheney | -0.134 |
lam | -0.128 |
olicy | -0.127 |
Token | { |
Token ID | 90 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
quart | +0.627 |
bucket | +0.612 |
strap | +0.591 |
otaur | +0.591 |
mant | +0.586 |
Neg logit contributions | |
awk | -0.192 |
argon | -0.178 |
Cheney | -0.130 |
lam | -0.112 |
olicy | -0.108 |
Token | at |
Token ID | 265 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
quart | +0.102 |
bucket | +0.099 |
strap | +0.094 |
otaur | +0.093 |
mant | +0.092 |
Neg logit contributions | |
awk | -0.095 |
argon | -0.092 |
Cheney | -0.081 |
lam | -0.076 |
olicy | -0.076 |
Token | - |
Token ID | 12 |
Feature activation | +2.73e-03 |
Pos logit contributions | |
awk | +0.081 |
argon | +0.079 |
Cheney | +0.070 |
lam | +0.067 |
olicy | +0.066 |
Neg logit contributions | |
quart | -0.066 |
bucket | -0.064 |
otaur | -0.060 |
strap | -0.060 |
mant | -0.059 |
Token | a |
Token ID | 64 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
quart | +0.006 |
bucket | +0.006 |
strap | +0.005 |
otaur | +0.005 |
mant | +0.005 |
Neg logit contributions | |
awk | -0.006 |
argon | -0.006 |
Cheney | -0.005 |
olicy | -0.005 |
lam | -0.005 |
Token | - |
Token ID | 12 |
Feature activation | -7.27e-03 |
Pos logit contributions | |
awk | +0.317 |
argon | +0.306 |
Cheney | +0.275 |
olicy | +0.261 |
lam | +0.258 |
Neg logit contributions | |
quart | -0.266 |
bucket | -0.256 |
strap | -0.242 |
otaur | -0.238 |
mant | -0.236 |
Token | gl |
Token ID | 4743 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
awk | +0.009 |
argon | +0.008 |
Cheney | +0.006 |
olicy | +0.006 |
lam | +0.005 |
Neg logit contributions | |
quart | -0.023 |
bucket | -0.023 |
strap | -0.022 |
otaur | -0.022 |
mant | -0.022 |
Token | ance |
Token ID | 590 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
awk | +0.103 |
argon | +0.100 |
Cheney | +0.091 |
lam | +0.085 |
olicy | +0.085 |
Neg logit contributions | |
quart | -0.080 |
bucket | -0.077 |
otaur | -0.073 |
strap | -0.073 |
mant | -0.070 |
Token | " |
Token ID | 1 |
Feature activation | -7.70e-02 |
Pos logit contributions | |
awk | +1.157 |
argon | +1.115 |
Cheney | +0.980 |
lam | +0.931 |
olicy | +0.917 |
Neg logit contributions | |
quart | -1.158 |
bucket | -1.116 |
otaur | -1.057 |
strap | -1.055 |
mant | -1.043 |
Token | met |
Token ID | 1138 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
awk | +0.201 |
argon | +0.196 |
Cheney | +0.175 |
lam | +0.168 |
olicy | +0.167 |
Neg logit contributions | |
quart | -0.140 |
bucket | -0.134 |
strap | -0.126 |
otaur | -0.123 |
mant | -0.122 |
Token | ering |
Token ID | 1586 |
Feature activation | -6.45e-02 |
Pos logit contributions | |
awk | +0.291 |
argon | +0.280 |
Cheney | +0.244 |
lam | +0.231 |
olicy | +0.228 |
Neg logit contributions | |
quart | -0.322 |
bucket | -0.311 |
strap | -0.294 |
otaur | -0.294 |
mant | -0.291 |
Token | with |
Token ID | 351 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
awk | +0.163 |
argon | +0.158 |
Cheney | +0.141 |
lam | +0.135 |
olicy | +0.134 |
Neg logit contributions | |
quart | -0.123 |
bucket | -0.119 |
strap | -0.111 |
otaur | -0.109 |
mant | -0.109 |
Token | peak |
Token ID | 9103 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
awk | +0.257 |
argon | +0.250 |
Cheney | +0.223 |
lam | +0.213 |
olicy | +0.212 |
Neg logit contributions | |
quart | -0.189 |
bucket | -0.181 |
strap | -0.169 |
otaur | -0.167 |
mant | -0.166 |
Token | record |
Token ID | 22105 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
awk | +0.004 |
argon | +0.004 |
Cheney | +0.003 |
lam | +0.003 |
olicy | +0.003 |
Neg logit contributions | |
quart | -0.008 |
bucket | -0.008 |
strap | -0.007 |
otaur | -0.007 |
mant | -0.007 |
Token | 356 |
Token ID | 44552 |
Feature activation | -4.75e-02 |
Pos logit contributions | |
awk | +0.644 |
argon | +0.627 |
Cheney | +0.562 |
lam | +0.539 |
olicy | +0.534 |
Neg logit contributions | |
quart | -0.433 |
bucket | -0.414 |
strap | -0.385 |
otaur | -0.383 |
mant | -0.378 |
Token | yards |
Token ID | 5695 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
awk | +0.124 |
argon | +0.121 |
Cheney | +0.108 |
lam | +0.103 |
olicy | +0.103 |
Neg logit contributions | |
quart | -0.086 |
bucket | -0.083 |
strap | -0.077 |
otaur | -0.077 |
mant | -0.076 |
Token | against |
Token ID | 1028 |
Feature activation | -9.69e-02 |
Pos logit contributions | |
quart | +0.220 |
bucket | +0.212 |
strap | +0.199 |
otaur | +0.199 |
mant | +0.196 |
Neg logit contributions | |
awk | -0.250 |
argon | -0.242 |
Cheney | -0.214 |
lam | -0.204 |
olicy | -0.202 |
Token | Air |
Token ID | 3701 |
Feature activation | +7.30e-02 |
Pos logit contributions | |
awk | +0.217 |
argon | +0.211 |
Cheney | +0.184 |
lam | +0.175 |
olicy | +0.174 |
Neg logit contributions | |
quart | -0.211 |
bucket | -0.203 |
strap | -0.192 |
otaur | -0.191 |
mant | -0.189 |
Token | Force |
Token ID | 5221 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
quart | +0.154 |
bucket | +0.148 |
strap | +0.139 |
otaur | +0.139 |
mant | +0.137 |
Neg logit contributions | |
awk | -0.169 |
argon | -0.163 |
Cheney | -0.144 |
lam | -0.137 |
olicy | -0.136 |
Token | , |
Token ID | 11 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
awk | +1.195 |
argon | +1.148 |
Cheney | +1.022 |
lam | +0.971 |
olicy | +0.958 |
Neg logit contributions | |
quart | -1.085 |
bucket | -1.047 |
otaur | -0.993 |
strap | -0.989 |
mant | -0.976 |
Token | Mord |
Token ID | 29548 |
Feature activation | +6.11e-02 |
Pos logit contributions | |
awk | +0.077 |
argon | +0.075 |
Cheney | +0.066 |
lam | +0.063 |
olicy | +0.062 |
Neg logit contributions | |
quart | -0.071 |
bucket | -0.069 |
strap | -0.065 |
otaur | -0.064 |
mant | -0.064 |
Token | ica |
Token ID | 3970 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
quart | +0.140 |
bucket | +0.136 |
otaur | +0.130 |
strap | +0.129 |
mant | +0.128 |
Neg logit contributions | |
awk | -0.128 |
argon | -0.123 |
Cheney | -0.107 |
olicy | -0.101 |
lam | -0.101 |
Token | threatened |
Token ID | 8556 |
Feature activation | -7.13e-02 |
Pos logit contributions | |
awk | +0.042 |
argon | +0.041 |
Cheney | +0.036 |
lam | +0.035 |
olicy | +0.035 |
Neg logit contributions | |
quart | -0.031 |
bucket | -0.029 |
strap | -0.027 |
otaur | -0.027 |
mant | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
awk | +0.176 |
argon | +0.170 |
Cheney | +0.153 |
lam | +0.146 |
olicy | +0.143 |
Neg logit contributions | |
quart | -0.139 |
bucket | -0.133 |
otaur | -0.125 |
strap | -0.125 |
mant | -0.123 |
Token | :" |
Token ID | 11097 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
awk | +1.031 |
argon | +0.996 |
Cheney | +0.886 |
lam | +0.855 |
olicy | +0.838 |
Neg logit contributions | |
quart | -0.795 |
bucket | -0.766 |
otaur | -0.725 |
strap | -0.721 |
mant | -0.705 |
Token | is |
Token ID | 318 |
Feature activation | -5.84e-02 |
Pos logit contributions | |
quart | +0.140 |
bucket | +0.134 |
strap | +0.124 |
mant | +0.123 |
otaur | +0.123 |
Neg logit contributions | |
awk | -0.191 |
argon | -0.185 |
Cheney | -0.166 |
lam | -0.159 |
olicy | -0.157 |
Token | used |
Token ID | 973 |
Feature activation | +2.10e-03 |
Pos logit contributions | |
awk | +0.146 |
argon | +0.142 |
Cheney | +0.126 |
lam | +0.120 |
olicy | +0.120 |
Neg logit contributions | |
quart | -0.113 |
bucket | -0.108 |
strap | -0.100 |
mant | -0.100 |
otaur | -0.099 |
Token | : |
Token ID | 25 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
quart | +0.004 |
bucket | +0.004 |
strap | +0.004 |
otaur | +0.004 |
mant | +0.004 |
Neg logit contributions | |
awk | -0.005 |
argon | -0.005 |
Cheney | -0.004 |
lam | -0.004 |
olicy | -0.004 |
Token | vim |
Token ID | 43907 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
awk | +0.379 |
argon | +0.370 |
Cheney | +0.324 |
lam | +0.307 |
olicy | +0.306 |
Neg logit contributions | |
quart | -0.363 |
bucket | -0.350 |
strap | -0.330 |
mant | -0.328 |
otaur | -0.326 |
Token | { |
Token ID | 90 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
awk | +0.979 |
argon | +0.949 |
Cheney | +0.853 |
lam | +0.818 |
olicy | +0.808 |
Neg logit contributions | |
quart | -0.673 |
bucket | -0.644 |
otaur | -0.601 |
strap | -0.600 |
mant | -0.590 |
Token | vers |
Token ID | 690 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
awk | +1.019 |
argon | +0.979 |
Cheney | +0.847 |
lam | +0.796 |
olicy | +0.785 |
Neg logit contributions | |
quart | -1.264 |
bucket | -1.223 |
otaur | -1.163 |
strap | -1.163 |
mant | -1.150 |
Token | }: |
Token ID | 38362 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
awk | +0.261 |
argon | +0.253 |
Cheney | +0.224 |
lam | +0.213 |
olicy | +0.211 |
Neg logit contributions | |
quart | -0.233 |
bucket | -0.224 |
strap | -0.211 |
otaur | -0.211 |
mant | -0.208 |
Token | version |
Token ID | 2196 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
quart | +0.361 |
bucket | +0.348 |
strap | +0.328 |
otaur | +0.327 |
mant | +0.325 |
Neg logit contributions | |
awk | -0.346 |
argon | -0.336 |
Cheney | -0.298 |
lam | -0.279 |
olicy | -0.276 |
Token | { |
Token ID | 1391 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
quart | +0.326 |
bucket | +0.312 |
strap | +0.290 |
otaur | +0.290 |
mant | +0.289 |
Neg logit contributions | |
awk | -0.429 |
argon | -0.415 |
Cheney | -0.373 |
lam | -0.355 |
olicy | -0.351 |
Token | vers |
Token ID | 690 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
awk | +0.593 |
argon | +0.570 |
Cheney | +0.495 |
lam | +0.462 |
olicy | +0.457 |
Neg logit contributions | |
quart | -0.756 |
bucket | -0.731 |
otaur | -0.696 |
strap | -0.694 |
mant | -0.687 |
Token | file |
Token ID | 2393 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
awk | +0.415 |
argon | +0.404 |
Cheney | +0.357 |
lam | +0.340 |
olicy | +0.339 |
Neg logit contributions | |
quart | -0.330 |
bucket | -0.322 |
strap | -0.298 |
otaur | -0.293 |
mant | -0.293 |
Token | with |
Token ID | 351 |
Feature activation | -9.79e-02 |
Pos logit contributions | |
awk | +0.645 |
argon | +0.627 |
Cheney | +0.554 |
lam | +0.528 |
olicy | +0.527 |
Neg logit contributions | |
quart | -0.543 |
bucket | -0.526 |
strap | -0.491 |
mant | -0.486 |
otaur | -0.482 |
Token | | |
Token ID | 930 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
awk | +0.246 |
argon | +0.240 |
Cheney | +0.213 |
lam | +0.204 |
olicy | +0.203 |
Neg logit contributions | |
quart | -0.187 |
bucket | -0.180 |
strap | -0.167 |
mant | -0.167 |
otaur | -0.164 |
Token | : |
Token ID | 25 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
awk | +0.623 |
argon | +0.610 |
Cheney | +0.537 |
olicy | +0.501 |
lam | +0.498 |
Neg logit contributions | |
quart | -0.667 |
bucket | -0.647 |
strap | -0.607 |
otaur | -0.606 |
mant | -0.603 |
Token | mk |
Token ID | 28015 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
awk | +0.348 |
argon | +0.337 |
Cheney | +0.294 |
lam | +0.274 |
olicy | +0.273 |
Neg logit contributions | |
quart | -0.402 |
bucket | -0.390 |
strap | -0.369 |
otaur | -0.368 |
mant | -0.365 |
Token | vim |
Token ID | 31124 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
awk | +0.593 |
argon | +0.571 |
Cheney | +0.491 |
lam | +0.459 |
olicy | +0.453 |
Neg logit contributions | |
quart | -0.780 |
bucket | -0.756 |
strap | -0.719 |
otaur | -0.718 |
mant | -0.711 |
Token | rc |
Token ID | 6015 |
Feature activation | -4.67e-02 |
Pos logit contributions | |
awk | +1.214 |
argon | +1.175 |
Cheney | +1.042 |
lam | +0.990 |
olicy | +0.980 |
Neg logit contributions | |
quart | -1.067 |
bucket | -1.027 |
strap | -0.966 |
otaur | -0.964 |
mant | -0.953 |
Token | | |
Token ID | 91 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
awk | +0.116 |
argon | +0.113 |
Cheney | +0.101 |
lam | +0.096 |
olicy | +0.095 |
Neg logit contributions | |
quart | -0.090 |
bucket | -0.086 |
strap | -0.081 |
otaur | -0.080 |
mant | -0.080 |
Token | , |
Token ID | 11 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
awk | +0.726 |
argon | +0.711 |
Cheney | +0.638 |
olicy | +0.601 |
lam | +0.600 |
Neg logit contributions | |
quart | -0.589 |
bucket | -0.568 |
strap | -0.528 |
otaur | -0.525 |
mant | -0.523 |
Token | | |
Token ID | 930 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
awk | +0.350 |
argon | +0.341 |
Cheney | +0.302 |
olicy | +0.289 |
lam | +0.285 |
Neg logit contributions | |
quart | -0.297 |
bucket | -0.286 |
strap | -0.268 |
mant | -0.265 |
otaur | -0.263 |
Token | : |
Token ID | 25 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
awk | +0.849 |
argon | +0.828 |
Cheney | +0.748 |
lam | +0.713 |
olicy | +0.711 |
Neg logit contributions | |
quart | -0.548 |
bucket | -0.523 |
strap | -0.485 |
otaur | -0.485 |
mant | -0.479 |
Token | that |
Token ID | 326 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
awk | +0.216 |
argon | +0.209 |
Cheney | +0.188 |
lam | +0.180 |
olicy | +0.177 |
Neg logit contributions | |
quart | -0.156 |
bucket | -0.149 |
otaur | -0.140 |
strap | -0.140 |
mant | -0.137 |
Token | he |
Token ID | 339 |
Feature activation | -8.65e-02 |
Pos logit contributions | |
quart | +0.050 |
bucket | +0.048 |
strap | +0.045 |
mant | +0.044 |
otaur | +0.044 |
Neg logit contributions | |
awk | -0.059 |
argon | -0.057 |
Cheney | -0.050 |
olicy | -0.048 |
lam | -0.048 |
Token | is |
Token ID | 318 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
awk | +0.214 |
argon | +0.209 |
Cheney | +0.184 |
olicy | +0.178 |
lam | +0.177 |
Neg logit contributions | |
quart | -0.169 |
bucket | -0.162 |
strap | -0.153 |
mant | -0.150 |
otaur | -0.149 |
Token | no |
Token ID | 645 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
awk | +0.032 |
argon | +0.031 |
Cheney | +0.027 |
olicy | +0.026 |
lam | +0.026 |
Neg logit contributions | |
quart | -0.024 |
bucket | -0.023 |
strap | -0.021 |
mant | -0.021 |
otaur | -0.021 |
Token | te |
Token ID | 573 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
awk | +0.332 |
argon | +0.324 |
Cheney | +0.289 |
lam | +0.281 |
olicy | +0.280 |
Neg logit contributions | |
quart | -0.194 |
bucket | -0.187 |
strap | -0.172 |
mant | -0.169 |
otaur | -0.166 |
Token | chie |
Token ID | 3043 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
quart | +0.570 |
bucket | +0.552 |
strap | +0.523 |
otaur | +0.518 |
mant | +0.509 |
Neg logit contributions | |
awk | -0.586 |
argon | -0.566 |
Cheney | -0.504 |
olicy | -0.477 |
lam | -0.475 |
Token | . |
Token ID | 13 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
awk | +1.231 |
argon | +1.191 |
Cheney | +1.054 |
lam | +1.009 |
olicy | +1.001 |
Neg logit contributions | |
quart | -1.054 |
bucket | -1.013 |
strap | -0.951 |
otaur | -0.942 |
mant | -0.937 |
Token | " |
Token ID | 366 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
quart | +0.041 |
bucket | +0.039 |
otaur | +0.037 |
strap | +0.037 |
mant | +0.037 |
Neg logit contributions | |
awk | -0.040 |
argon | -0.039 |
Cheney | -0.033 |
olicy | -0.032 |
lam | -0.032 |
Token | I |
Token ID | 40 |
Feature activation | -5.51e-02 |
Pos logit contributions | |
awk | +0.124 |
argon | +0.120 |
Cheney | +0.104 |
olicy | +0.102 |
lam | +0.099 |
Neg logit contributions | |
quart | -0.139 |
bucket | -0.134 |
mant | -0.126 |
otaur | -0.126 |
strap | -0.125 |
Token | consider |
Token ID | 2074 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
awk | +0.134 |
argon | +0.130 |
Cheney | +0.115 |
olicy | +0.111 |
lam | +0.109 |
Neg logit contributions | |
quart | -0.111 |
bucket | -0.107 |
strap | -0.101 |
mant | -0.099 |
otaur | -0.097 |
Token | myself |
Token ID | 3589 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
quart | +0.115 |
bucket | +0.111 |
strap | +0.104 |
mant | +0.103 |
otaur | +0.102 |
Neg logit contributions | |
awk | -0.123 |
argon | -0.118 |
Cheney | -0.103 |
lam | -0.100 |
olicy | -0.099 |
Token | a |
Token ID | 257 |
Feature activation | -6.17e-02 |
Pos logit contributions | |
quart | +0.115 |
bucket | +0.109 |
strap | +0.102 |
mant | +0.101 |
otaur | +0.100 |
Neg logit contributions | |
awk | -0.157 |
argon | -0.151 |
Cheney | -0.134 |
olicy | -0.129 |
lam | -0.128 |
Token | white |
Token ID | 2330 |
Feature activation | -8.70e-02 |
Pos logit contributions | |
awk | +0.158 |
argon | +0.153 |
Cheney | +0.135 |
lam | +0.131 |
olicy | +0.130 |
Neg logit contributions | |
quart | -0.117 |
bucket | -0.112 |
strap | -0.105 |
mant | -0.103 |
otaur | -0.103 |
Token | , |
Token ID | 11 |
Feature activation | -6.10e-02 |
Pos logit contributions | |
awk | +0.222 |
argon | +0.215 |
Cheney | +0.190 |
lam | +0.183 |
olicy | +0.183 |
Neg logit contributions | |
quart | -0.164 |
bucket | -0.158 |
strap | -0.147 |
otaur | -0.146 |
mant | -0.145 |
Token | straight |
Token ID | 3892 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
awk | +0.165 |
argon | +0.161 |
Cheney | +0.144 |
lam | +0.139 |
olicy | +0.138 |
Neg logit contributions | |
quart | -0.105 |
bucket | -0.100 |
strap | -0.093 |
otaur | -0.092 |
mant | -0.091 |
Token | , |
Token ID | 11 |
Feature activation | -3.84e-02 |
Pos logit contributions | |
quart | +0.087 |
bucket | +0.083 |
strap | +0.078 |
otaur | +0.077 |
mant | +0.076 |
Neg logit contributions | |
awk | -0.121 |
argon | -0.118 |
Cheney | -0.105 |
olicy | -0.100 |
lam | -0.100 |
Token | cis |
Token ID | 33325 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
awk | +0.102 |
argon | +0.099 |
Cheney | +0.088 |
lam | +0.085 |
olicy | +0.085 |
Neg logit contributions | |
quart | -0.068 |
bucket | -0.065 |
strap | -0.061 |
otaur | -0.060 |
mant | -0.060 |
Token | g |
Token ID | 70 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
awk | +1.310 |
argon | +1.268 |
Cheney | +1.136 |
lam | +1.095 |
olicy | +1.069 |
Neg logit contributions | |
quart | -0.958 |
bucket | -0.919 |
otaur | -0.861 |
strap | -0.860 |
mant | -0.849 |
Token | endered |
Token ID | 30398 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
awk | +0.042 |
argon | +0.041 |
Cheney | +0.036 |
lam | +0.034 |
olicy | +0.034 |
Neg logit contributions | |
quart | -0.035 |
bucket | -0.034 |
otaur | -0.032 |
strap | -0.032 |
mant | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
awk | +0.682 |
argon | +0.661 |
Cheney | +0.587 |
lam | +0.562 |
olicy | +0.561 |
Neg logit contributions | |
quart | -0.519 |
bucket | -0.498 |
strap | -0.466 |
otaur | -0.462 |
mant | -0.458 |
Token | American |
Token ID | 1605 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
awk | +0.062 |
argon | +0.060 |
Cheney | +0.053 |
lam | +0.051 |
olicy | +0.051 |
Neg logit contributions | |
quart | -0.045 |
bucket | -0.043 |
strap | -0.040 |
otaur | -0.040 |
mant | -0.039 |
Token | man |
Token ID | 582 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
quart | +0.219 |
bucket | +0.210 |
strap | +0.197 |
otaur | +0.196 |
mant | +0.193 |
Neg logit contributions | |
awk | -0.288 |
argon | -0.280 |
Cheney | -0.250 |
lam | -0.239 |
olicy | -0.237 |
Token |
|
Token ID | 198 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
awk | +0.087 |
argon | +0.086 |
Cheney | +0.075 |
olicy | +0.075 |
lam | +0.071 |
Neg logit contributions | |
quart | -0.068 |
bucket | -0.065 |
strap | -0.060 |
mant | -0.060 |
otaur | -0.059 |
Token | https |
Token ID | 5450 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
awk | +0.075 |
argon | +0.072 |
Cheney | +0.064 |
olicy | +0.059 |
lam | +0.059 |
Neg logit contributions | |
quart | -0.082 |
bucket | -0.079 |
otaur | -0.075 |
strap | -0.075 |
mant | -0.074 |
Token | :// |
Token ID | 1378 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
quart | +0.213 |
bucket | +0.206 |
otaur | +0.190 |
strap | +0.189 |
mant | +0.188 |
Neg logit contributions | |
awk | -0.305 |
argon | -0.298 |
Cheney | -0.269 |
olicy | -0.259 |
lam | -0.249 |
Token | www |
Token ID | 2503 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
quart | +0.232 |
bucket | +0.223 |
otaur | +0.210 |
strap | +0.210 |
mant | +0.207 |
Neg logit contributions | |
awk | -0.262 |
argon | -0.253 |
Cheney | -0.225 |
lam | -0.213 |
olicy | -0.211 |
Token | . |
Token ID | 13 |
Feature activation | -7.53e-02 |
Pos logit contributions | |
awk | +0.518 |
argon | +0.504 |
Cheney | +0.455 |
olicy | +0.445 |
lam | +0.427 |
Neg logit contributions | |
quart | -0.365 |
bucket | -0.352 |
strap | -0.325 |
otaur | -0.325 |
mant | -0.323 |
Token | eff |
Token ID | 14822 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
awk | +0.125 |
argon | +0.119 |
Cheney | +0.100 |
lam | +0.092 |
olicy | +0.091 |
Neg logit contributions | |
quart | -0.207 |
bucket | -0.201 |
otaur | -0.192 |
strap | -0.192 |
mant | -0.190 |
Token | . |
Token ID | 13 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
awk | +1.271 |
argon | +1.246 |
Cheney | +1.131 |
olicy | +1.049 |
lam | +1.040 |
Neg logit contributions | |
quart | -0.988 |
bucket | -0.950 |
otaur | -0.888 |
strap | -0.882 |
mant | -0.879 |
Token | org |
Token ID | 2398 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
awk | +0.097 |
argon | +0.096 |
Cheney | +0.088 |
olicy | +0.081 |
lam | +0.078 |
Neg logit contributions | |
quart | -0.084 |
bucket | -0.082 |
otaur | -0.078 |
strap | -0.076 |
mant | -0.075 |
Token | / |
Token ID | 14 |
Feature activation | -8.85e-03 |
Pos logit contributions | |
awk | +0.103 |
argon | +0.099 |
Cheney | +0.089 |
olicy | +0.085 |
lam | +0.083 |
Neg logit contributions | |
quart | -0.086 |
bucket | -0.082 |
mant | -0.076 |
strap | -0.076 |
otaur | -0.076 |
Token | document |
Token ID | 22897 |
Feature activation | +2.67e-03 |
Pos logit contributions | |
awk | +0.017 |
argon | +0.016 |
Cheney | +0.014 |
olicy | +0.013 |
lam | +0.013 |
Neg logit contributions | |
quart | -0.022 |
bucket | -0.021 |
strap | -0.020 |
otaur | -0.020 |
mant | -0.020 |
Token | / |
Token ID | 14 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
quart | +0.006 |
bucket | +0.006 |
otaur | +0.005 |
strap | +0.005 |
mant | +0.005 |
Neg logit contributions | |
awk | -0.006 |
argon | -0.006 |
Cheney | -0.005 |
lam | -0.005 |
olicy | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
awk | +0.013 |
argon | +0.013 |
Cheney | +0.011 |
olicy | +0.011 |
lam | +0.011 |
Neg logit contributions | |
quart | -0.009 |
bucket | -0.009 |
strap | -0.008 |
otaur | -0.008 |
mant | -0.008 |
Token | 6 |
Token ID | 718 |
Feature activation | +7.82e-02 |
Pos logit contributions | |
awk | +0.376 |
argon | +0.363 |
Cheney | +0.326 |
lam | +0.311 |
olicy | +0.307 |
Neg logit contributions | |
quart | -0.283 |
bucket | -0.272 |
otaur | -0.255 |
strap | -0.255 |
mant | -0.252 |
Token | }, |
Token ID | 5512 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
quart | +0.129 |
bucket | +0.122 |
otaur | +0.114 |
strap | +0.114 |
mant | +0.111 |
Neg logit contributions | |
awk | -0.216 |
argon | -0.211 |
Cheney | -0.190 |
olicy | -0.185 |
lam | -0.182 |
Token | ... |
Token ID | 986 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
quart | +0.438 |
bucket | +0.423 |
strap | +0.391 |
mant | +0.387 |
otaur | +0.382 |
Neg logit contributions | |
awk | -0.552 |
argon | -0.540 |
Cheney | -0.467 |
olicy | -0.462 |
lam | -0.454 |
Token | , |
Token ID | 11 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
awk | +0.416 |
argon | +0.402 |
Cheney | +0.357 |
lam | +0.340 |
olicy | +0.336 |
Neg logit contributions | |
quart | -0.366 |
bucket | -0.352 |
otaur | -0.332 |
strap | -0.332 |
mant | -0.328 |
Token | { |
Token ID | 90 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
awk | +0.209 |
argon | +0.200 |
Cheney | +0.172 |
lam | +0.161 |
olicy | +0.159 |
Neg logit contributions | |
quart | -0.283 |
bucket | -0.274 |
strap | -0.262 |
otaur | -0.262 |
mant | -0.259 |
Token | 10 |
Token ID | 940 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
awk | +0.902 |
argon | +0.863 |
Cheney | +0.723 |
lam | +0.687 |
olicy | +0.664 |
Neg logit contributions | |
quart | -1.355 |
bucket | -1.317 |
strap | -1.260 |
otaur | -1.256 |
mant | -1.247 |
Token | , |
Token ID | 11 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
awk | +0.102 |
argon | +0.101 |
Cheney | +0.089 |
olicy | +0.088 |
lam | +0.085 |
Neg logit contributions | |
quart | -0.072 |
bucket | -0.068 |
strap | -0.063 |
mant | -0.063 |
otaur | -0.062 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
awk | +0.389 |
argon | +0.381 |
Cheney | +0.339 |
lam | +0.326 |
olicy | +0.325 |
Neg logit contributions | |
quart | -0.264 |
bucket | -0.251 |
strap | -0.235 |
otaur | -0.230 |
mant | -0.229 |
Token | } |
Token ID | 92 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
awk | +0.049 |
argon | +0.048 |
Cheney | +0.043 |
olicy | +0.042 |
lam | +0.041 |
Neg logit contributions | |
quart | -0.027 |
bucket | -0.026 |
strap | -0.024 |
otaur | -0.024 |
mant | -0.023 |
Token | < |
Token ID | 1279 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
quart | +0.285 |
bucket | +0.274 |
otaur | +0.260 |
strap | +0.260 |
mant | +0.257 |
Neg logit contributions | |
awk | -0.301 |
argon | -0.290 |
Cheney | -0.257 |
lam | -0.244 |
olicy | -0.241 |
Token | fn |
Token ID | 24714 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
awk | +0.245 |
argon | +0.237 |
Cheney | +0.210 |
lam | +0.201 |
olicy | +0.197 |
Neg logit contributions | |
quart | -0.226 |
bucket | -0.216 |
otaur | -0.205 |
strap | -0.205 |
mant | -0.202 |
Token | apply |
Token ID | 4174 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
quart | +0.096 |
bucket | +0.094 |
strap | +0.089 |
otaur | +0.087 |
mant | +0.087 |
Neg logit contributions | |
awk | -0.091 |
argon | -0.088 |
Cheney | -0.076 |
lam | -0.073 |
olicy | -0.072 |
Token | _ |
Token ID | 62 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
awk | +0.334 |
argon | +0.326 |
Cheney | +0.282 |
olicy | +0.263 |
lam | +0.263 |
Neg logit contributions | |
quart | -0.378 |
bucket | -0.368 |
otaur | -0.347 |
strap | -0.345 |
mant | -0.343 |
Token | move |
Token ID | 21084 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
awk | +0.237 |
argon | +0.228 |
Cheney | +0.195 |
lam | +0.184 |
olicy | +0.181 |
Neg logit contributions | |
quart | -0.313 |
bucket | -0.303 |
strap | -0.289 |
otaur | -0.289 |
mant | -0.286 |
Token | ( |
Token ID | 357 |
Feature activation | +7.28e-02 |
Pos logit contributions | |
awk | +0.383 |
argon | +0.367 |
Cheney | +0.321 |
lam | +0.309 |
olicy | +0.303 |
Neg logit contributions | |
quart | -0.401 |
bucket | -0.385 |
strap | -0.367 |
otaur | -0.365 |
mant | -0.361 |
Token | & |
Token ID | 1222 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
quart | +0.149 |
bucket | +0.145 |
strap | +0.135 |
otaur | +0.135 |
mant | +0.133 |
Neg logit contributions | |
awk | -0.172 |
argon | -0.167 |
Cheney | -0.148 |
lam | -0.141 |
olicy | -0.139 |
Token | mut |
Token ID | 4517 |
Feature activation | +7.30e-02 |
Pos logit contributions | |
quart | +0.717 |
bucket | +0.694 |
strap | +0.654 |
otaur | +0.653 |
mant | +0.646 |
Neg logit contributions | |
awk | -0.704 |
argon | -0.680 |
Cheney | -0.595 |
lam | -0.565 |
olicy | -0.557 |
Token | self |
Token ID | 2116 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
quart | +0.156 |
bucket | +0.152 |
strap | +0.142 |
otaur | +0.141 |
mant | +0.140 |
Neg logit contributions | |
awk | -0.168 |
argon | -0.164 |
Cheney | -0.142 |
lam | -0.136 |
olicy | -0.135 |
Token | ) |
Token ID | 1267 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
quart | +1.061 |
bucket | +1.027 |
strap | +0.977 |
otaur | +0.977 |
mant | +0.967 |
Neg logit contributions | |
awk | -0.830 |
argon | -0.797 |
Cheney | -0.686 |
lam | -0.645 |
olicy | -0.635 |
Token | { |
Token ID | 1391 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
awk | +0.097 |
argon | +0.094 |
Cheney | +0.085 |
lam | +0.080 |
olicy | +0.080 |
Neg logit contributions | |
quart | -0.075 |
bucket | -0.071 |
otaur | -0.067 |
strap | -0.067 |
mant | -0.066 |
Token | let |
Token ID | 1309 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
awk | +0.530 |
argon | +0.517 |
Cheney | +0.451 |
lam | +0.433 |
olicy | +0.427 |
Neg logit contributions | |
quart | -0.453 |
bucket | -0.442 |
strap | -0.415 |
otaur | -0.409 |
mant | -0.406 |
Token | to |
Token ID | 284 |
Feature activation | -6.75e-02 |
Pos logit contributions | |
awk | +0.338 |
argon | +0.327 |
Cheney | +0.292 |
lam | +0.282 |
olicy | +0.276 |
Neg logit contributions | |
quart | -0.271 |
bucket | -0.257 |
otaur | -0.245 |
strap | -0.240 |
mant | -0.239 |
Token | start |
Token ID | 923 |
Feature activation | -6.35e-02 |
Pos logit contributions | |
awk | +0.167 |
argon | +0.163 |
Cheney | +0.144 |
olicy | +0.138 |
lam | +0.137 |
Neg logit contributions | |
quart | -0.133 |
bucket | -0.128 |
strap | -0.123 |
mant | -0.119 |
otaur | -0.117 |
Token | developing |
Token ID | 5922 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
awk | +0.159 |
argon | +0.154 |
Cheney | +0.138 |
lam | +0.132 |
olicy | +0.131 |
Neg logit contributions | |
quart | -0.121 |
bucket | -0.117 |
strap | -0.109 |
otaur | -0.108 |
mant | -0.108 |
Token | in |
Token ID | 287 |
Feature activation | -8.93e-03 |
Pos logit contributions | |
quart | +0.073 |
bucket | +0.070 |
strap | +0.066 |
otaur | +0.066 |
mant | +0.065 |
Neg logit contributions | |
awk | -0.098 |
argon | -0.095 |
Cheney | -0.085 |
lam | -0.081 |
olicy | -0.080 |
Token | AWS |
Token ID | 30865 |
Feature activation | +1.00e-03 |
Pos logit contributions | |
awk | +0.024 |
argon | +0.023 |
Cheney | +0.021 |
lam | +0.020 |
olicy | +0.019 |
Neg logit contributions | |
quart | -0.016 |
bucket | -0.015 |
otaur | -0.014 |
strap | -0.014 |
mant | -0.014 |
Token | Lamb |
Token ID | 21114 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
quart | +0.002 |
bucket | +0.002 |
strap | +0.002 |
otaur | +0.002 |
mant | +0.002 |
Neg logit contributions | |
awk | -0.002 |
argon | -0.002 |
Cheney | -0.002 |
lam | -0.002 |
olicy | -0.002 |
Token | da |
Token ID | 6814 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
quart | +1.358 |
bucket | +1.312 |
otaur | +1.255 |
strap | +1.243 |
mant | +1.205 |
Neg logit contributions | |
awk | -1.077 |
argon | -1.049 |
Cheney | -0.906 |
olicy | -0.850 |
lam | -0.838 |
Token | with |
Token ID | 351 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
awk | +0.250 |
argon | +0.242 |
Cheney | +0.215 |
lam | +0.205 |
olicy | +0.203 |
Neg logit contributions | |
quart | -0.208 |
bucket | -0.201 |
strap | -0.188 |
otaur | -0.187 |
mant | -0.185 |
Token | server |
Token ID | 4382 |
Feature activation | -9.89e-02 |
Pos logit contributions | |
awk | +0.049 |
argon | +0.047 |
Cheney | +0.043 |
lam | +0.041 |
olicy | +0.040 |
Neg logit contributions | |
quart | -0.034 |
bucket | -0.032 |
strap | -0.030 |
otaur | -0.030 |
mant | -0.030 |
Token | less |
Token ID | 1203 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
awk | +0.234 |
argon | +0.228 |
Cheney | +0.205 |
olicy | +0.193 |
lam | +0.187 |
Neg logit contributions | |
quart | -0.201 |
bucket | -0.196 |
strap | -0.183 |
otaur | -0.180 |
mant | -0.179 |
Token | framework |
Token ID | 9355 |
Feature activation | -6.44e-02 |
Pos logit contributions | |
awk | +0.036 |
argon | +0.035 |
Cheney | +0.032 |
lam | +0.030 |
olicy | +0.030 |
Neg logit contributions | |
quart | -0.024 |
bucket | -0.023 |
strap | -0.022 |
otaur | -0.021 |
mant | -0.021 |
Token | � |
Token ID | 30266 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
quart | +0.082 |
bucket | +0.079 |
strap | +0.074 |
otaur | +0.074 |
mant | +0.073 |
Neg logit contributions | |
awk | -0.094 |
argon | -0.090 |
Cheney | -0.080 |
lam | -0.076 |
olicy | -0.076 |
Token | � |
Token ID | 109 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
quart | +0.373 |
bucket | +0.357 |
otaur | +0.332 |
strap | +0.331 |
mant | +0.327 |
Neg logit contributions | |
awk | -0.565 |
argon | -0.549 |
Cheney | -0.494 |
lam | -0.473 |
olicy | -0.469 |
Token | 方 |
Token ID | 43095 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
quart | +0.196 |
bucket | +0.184 |
strap | +0.168 |
otaur | +0.167 |
mant | +0.164 |
Neg logit contributions | |
awk | -0.434 |
argon | -0.423 |
Cheney | -0.386 |
lam | -0.372 |
olicy | -0.370 |
Token | � |
Token ID | 23877 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
quart | +0.427 |
bucket | +0.407 |
otaur | +0.379 |
strap | +0.378 |
mant | +0.375 |
Neg logit contributions | |
awk | -0.628 |
argon | -0.610 |
Cheney | -0.546 |
lam | -0.523 |
olicy | -0.523 |
Token | � |
Token ID | 229 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
quart | +0.890 |
bucket | +0.859 |
otaur | +0.805 |
strap | +0.803 |
mant | +0.794 |
Neg logit contributions | |
awk | -1.045 |
argon | -1.021 |
Cheney | -0.903 |
lam | -0.857 |
olicy | -0.852 |
Token | � |
Token ID | 162 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
awk | +0.692 |
argon | +0.672 |
Cheney | +0.606 |
lam | +0.581 |
olicy | +0.576 |
Neg logit contributions | |
quart | -0.440 |
bucket | -0.419 |
strap | -0.389 |
otaur | -0.389 |
mant | -0.383 |
Token | � |
Token ID | 252 |
Feature activation | -5.50e-02 |
Pos logit contributions | |
quart | +0.628 |
bucket | +0.599 |
strap | +0.560 |
otaur | +0.560 |
mant | +0.553 |
Neg logit contributions | |
awk | -0.852 |
argon | -0.827 |
Cheney | -0.740 |
lam | -0.703 |
olicy | -0.703 |
Token | � |
Token ID | 250 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
awk | +0.148 |
argon | +0.143 |
Cheney | +0.129 |
lam | +0.124 |
olicy | +0.123 |
Neg logit contributions | |
quart | -0.095 |
bucket | -0.091 |
strap | -0.084 |
otaur | -0.084 |
mant | -0.083 |
Token | � |
Token ID | 40367 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
quart | +0.041 |
bucket | +0.039 |
strap | +0.036 |
otaur | +0.036 |
mant | +0.036 |
Neg logit contributions | |
awk | -0.061 |
argon | -0.059 |
Cheney | -0.053 |
lam | -0.051 |
olicy | -0.051 |
Token | � |
Token ID | 253 |
Feature activation | -6.27e-02 |
Pos logit contributions | |
quart | +0.568 |
bucket | +0.546 |
otaur | +0.510 |
strap | +0.510 |
mant | +0.504 |
Neg logit contributions | |
awk | -0.698 |
argon | -0.677 |
Cheney | -0.601 |
lam | -0.571 |
olicy | -0.569 |
Token | � |
Token ID | 161 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
awk | +0.166 |
argon | +0.161 |
Cheney | +0.145 |
lam | +0.139 |
olicy | +0.138 |
Neg logit contributions | |
quart | -0.111 |
bucket | -0.106 |
strap | -0.098 |
otaur | -0.098 |
mant | -0.097 |
Token | everyday |
Token ID | 10908 |
Feature activation | -1.26e-03 |
Pos logit contributions | |
quart | +0.044 |
bucket | +0.042 |
strap | +0.039 |
mant | +0.039 |
otaur | +0.038 |
Neg logit contributions | |
awk | -0.063 |
argon | -0.061 |
Cheney | -0.054 |
lam | -0.052 |
olicy | -0.052 |
Token | household |
Token ID | 6641 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
awk | +0.003 |
argon | +0.003 |
Cheney | +0.003 |
lam | +0.003 |
olicy | +0.003 |
Neg logit contributions | |
quart | -0.002 |
bucket | -0.002 |
strap | -0.002 |
mant | -0.002 |
otaur | -0.002 |
Token | products |
Token ID | 3186 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
awk | +0.629 |
argon | +0.609 |
Cheney | +0.543 |
lam | +0.518 |
olicy | +0.514 |
Neg logit contributions | |
quart | -0.487 |
bucket | -0.468 |
strap | -0.437 |
otaur | -0.433 |
mant | -0.432 |
Token | . |
Token ID | 13 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
quart | +0.324 |
bucket | +0.311 |
strap | +0.292 |
otaur | +0.289 |
mant | +0.289 |
Neg logit contributions | |
awk | -0.373 |
argon | -0.361 |
Cheney | -0.318 |
lam | -0.303 |
olicy | -0.301 |
Token | It |
Token ID | 632 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
quart | +0.064 |
bucket | +0.062 |
strap | +0.058 |
mant | +0.057 |
otaur | +0.057 |
Neg logit contributions | |
awk | -0.067 |
argon | -0.064 |
Cheney | -0.055 |
olicy | -0.054 |
lam | -0.053 |
Token | stretches |
Token ID | 23687 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
quart | +0.024 |
bucket | +0.023 |
strap | +0.022 |
otaur | +0.021 |
mant | +0.021 |
Neg logit contributions | |
awk | -0.033 |
argon | -0.032 |
Cheney | -0.029 |
lam | -0.028 |
olicy | -0.028 |
Token | under |
Token ID | 739 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
quart | +0.660 |
bucket | +0.635 |
strap | +0.599 |
mant | +0.588 |
otaur | +0.586 |
Neg logit contributions | |
awk | -0.818 |
argon | -0.793 |
Cheney | -0.702 |
lam | -0.668 |
olicy | -0.667 |
Token | stress |
Token ID | 5503 |
Feature activation | -9.62e-02 |
Pos logit contributions | |
quart | +0.224 |
bucket | +0.215 |
strap | +0.200 |
otaur | +0.199 |
mant | +0.196 |
Neg logit contributions | |
awk | -0.338 |
argon | -0.328 |
Cheney | -0.295 |
lam | -0.283 |
olicy | -0.280 |
Token | , |
Token ID | 11 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
awk | +0.231 |
argon | +0.223 |
Cheney | +0.198 |
lam | +0.189 |
olicy | +0.187 |
Neg logit contributions | |
quart | -0.194 |
bucket | -0.187 |
strap | -0.176 |
otaur | -0.175 |
mant | -0.173 |
Token | but |
Token ID | 475 |
Feature activation | +3.64e-02 |
Pos logit contributions | |
quart | +0.023 |
bucket | +0.022 |
strap | +0.021 |
mant | +0.020 |
otaur | +0.020 |
Neg logit contributions | |
awk | -0.032 |
argon | -0.031 |
Cheney | -0.027 |
olicy | -0.026 |
lam | -0.026 |
Token | returns |
Token ID | 5860 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
quart | +0.068 |
bucket | +0.065 |
strap | +0.061 |
mant | +0.060 |
otaur | +0.060 |
Neg logit contributions | |
awk | -0.094 |
argon | -0.091 |
Cheney | -0.081 |
lam | -0.078 |
olicy | -0.077 |
Token | [ |
Token ID | 685 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
awk | +0.086 |
argon | +0.084 |
Cheney | +0.069 |
olicy | +0.067 |
lam | +0.065 |
Neg logit contributions | |
quart | -0.134 |
bucket | -0.130 |
strap | -0.124 |
mant | -0.123 |
otaur | -0.121 |
Token | 10 |
Token ID | 940 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
quart | +0.273 |
bucket | +0.267 |
strap | +0.251 |
mant | +0.250 |
otaur | +0.249 |
Neg logit contributions | |
awk | -0.210 |
argon | -0.205 |
Cheney | -0.178 |
olicy | -0.176 |
licts | -0.163 |
Token | : |
Token ID | 25 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
quart | +0.026 |
bucket | +0.024 |
strap | +0.022 |
mant | +0.022 |
otaur | +0.022 |
Neg logit contributions | |
awk | -0.051 |
argon | -0.050 |
Cheney | -0.045 |
olicy | -0.044 |
lam | -0.043 |
Token | 47 |
Token ID | 2857 |
Feature activation | -6.51e-02 |
Pos logit contributions | |
argon | +0.030 |
awk | +0.029 |
Cheney | +0.024 |
olicy | +0.024 |
lam | +0.021 |
Neg logit contributions | |
quart | -0.058 |
bucket | -0.057 |
otaur | -0.054 |
strap | -0.054 |
ça | -0.053 |
Token | ] |
Token ID | 60 |
Feature activation | -5.16e-04 |
Pos logit contributions | |
awk | +0.166 |
argon | +0.163 |
Cheney | +0.144 |
olicy | +0.144 |
lam | +0.137 |
Neg logit contributions | |
quart | -0.120 |
bucket | -0.114 |
strap | -0.106 |
mant | -0.105 |
otaur | -0.104 |
Token | < |
Token ID | 1279 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
awk | +0.001 |
argon | +0.001 |
Cheney | +0.001 |
lam | +0.001 |
olicy | +0.001 |
Neg logit contributions | |
quart | -0.001 |
bucket | -0.001 |
otaur | -0.001 |
strap | -0.001 |
mant | -0.001 |
Token | sn |
Token ID | 16184 |
Feature activation | +5.17e-03 |
Pos logit contributions | |
quart | +0.814 |
bucket | +0.786 |
otaur | +0.748 |
strap | +0.747 |
mant | +0.740 |
Neg logit contributions | |
awk | -0.695 |
argon | -0.666 |
Cheney | -0.589 |
olicy | -0.547 |
lam | -0.541 |
Token | iping |
Token ID | 34690 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
quart | +0.012 |
bucket | +0.011 |
otaur | +0.011 |
strap | +0.011 |
mant | +0.010 |
Neg logit contributions | |
awk | -0.011 |
argon | -0.011 |
Cheney | -0.009 |
lam | -0.009 |
olicy | -0.009 |
Token | 117 |
Token ID | 17657 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
awk | +0.102 |
argon | +0.098 |
Cheney | +0.085 |
lam | +0.079 |
olicy | +0.079 |
Neg logit contributions | |
quart | -0.127 |
bucket | -0.123 |
otaur | -0.117 |
strap | -0.117 |
mant | -0.115 |
Token | > |
Token ID | 29 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
awk | +0.428 |
argon | +0.411 |
Cheney | +0.365 |
lam | +0.351 |
olicy | +0.344 |
Neg logit contributions | |
quart | -0.347 |
bucket | -0.332 |
otaur | -0.312 |
strap | -0.312 |
mant | -0.308 |
Token | H |
Token ID | 367 |
Feature activation | +7.52e-02 |
Pos logit contributions | |
quart | +0.415 |
bucket | +0.400 |
strap | +0.377 |
mant | +0.370 |
otaur | +0.369 |
Neg logit contributions | |
awk | -0.508 |
argon | -0.495 |
Cheney | -0.435 |
olicy | -0.418 |
lam | -0.415 |
Token | now |
Token ID | 783 |
Feature activation | -4.00e-03 |
Pos logit contributions | |
quart | +0.286 |
bucket | +0.273 |
strap | +0.255 |
otaur | +0.253 |
mant | +0.251 |
Neg logit contributions | |
awk | -0.409 |
argon | -0.400 |
Cheney | -0.355 |
lam | -0.342 |
olicy | -0.342 |
Token | ." |
Token ID | 526 |
Feature activation | -3.70e-02 |
Pos logit contributions | |
awk | +0.009 |
argon | +0.009 |
Cheney | +0.008 |
lam | +0.008 |
hs | +0.008 |
Neg logit contributions | |
quart | -0.008 |
bucket | -0.008 |
otaur | -0.008 |
strap | -0.008 |
mant | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
awk | +0.082 |
argon | +0.079 |
Cheney | +0.069 |
lam | +0.066 |
olicy | +0.066 |
Neg logit contributions | |
quart | -0.081 |
bucket | -0.078 |
strap | -0.074 |
otaur | -0.074 |
mant | -0.073 |
Token |
|
Token ID | 198 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
quart | +0.072 |
bucket | +0.069 |
strap | +0.064 |
mant | +0.064 |
otaur | +0.063 |
Neg logit contributions | |
awk | -0.093 |
argon | -0.092 |
Cheney | -0.081 |
olicy | -0.080 |
lam | -0.076 |
Token | Many |
Token ID | 7085 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
quart | +0.101 |
bucket | +0.097 |
otaur | +0.092 |
strap | +0.092 |
mant | +0.091 |
Neg logit contributions | |
awk | -0.095 |
argon | -0.092 |
Cheney | -0.081 |
olicy | -0.077 |
lam | -0.075 |
Token | girls |
Token ID | 4813 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
awk | +0.079 |
argon | +0.077 |
Cheney | +0.068 |
lam | +0.065 |
olicy | +0.065 |
Neg logit contributions | |
quart | -0.060 |
bucket | -0.058 |
strap | -0.054 |
otaur | -0.054 |
mant | -0.053 |
Token | think |
Token ID | 892 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
quart | +0.258 |
bucket | +0.248 |
strap | +0.237 |
mant | +0.230 |
otaur | +0.228 |
Neg logit contributions | |
awk | -0.326 |
argon | -0.319 |
Cheney | -0.281 |
olicy | -0.271 |
lam | -0.267 |
Token | this |
Token ID | 428 |
Feature activation | -4.05e-02 |
Pos logit contributions | |
quart | +0.058 |
bucket | +0.055 |
strap | +0.052 |
otaur | +0.052 |
mant | +0.051 |
Neg logit contributions | |
awk | -0.076 |
argon | -0.074 |
Cheney | -0.066 |
lam | -0.063 |
olicy | -0.062 |
Token | is |
Token ID | 318 |
Feature activation | -4.53e-02 |
Pos logit contributions | |
awk | +0.104 |
argon | +0.101 |
Cheney | +0.090 |
lam | +0.086 |
olicy | +0.086 |
Neg logit contributions | |
quart | -0.076 |
bucket | -0.073 |
strap | -0.068 |
otaur | -0.067 |
mant | -0.067 |
Token | normal |
Token ID | 3487 |
Feature activation | +9.94e-02 |
Pos logit contributions | |
awk | +0.114 |
argon | +0.111 |
Cheney | +0.098 |
olicy | +0.094 |
lam | +0.093 |
Neg logit contributions | |
quart | -0.086 |
bucket | -0.083 |
strap | -0.078 |
mant | -0.077 |
otaur | -0.076 |
Token | because |
Token ID | 780 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
quart | +0.200 |
bucket | +0.192 |
strap | +0.181 |
mant | +0.179 |
otaur | +0.179 |
Neg logit contributions | |
awk | -0.241 |
argon | -0.233 |
Cheney | -0.206 |
lam | -0.196 |
olicy | -0.196 |
Token | certainly |
Token ID | 3729 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
quart | +0.027 |
bucket | +0.026 |
strap | +0.024 |
mant | +0.024 |
otaur | +0.023 |
Neg logit contributions | |
awk | -0.038 |
argon | -0.037 |
Cheney | -0.033 |
olicy | -0.032 |
lam | -0.031 |
Token | much |
Token ID | 881 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
quart | +0.285 |
bucket | +0.274 |
strap | +0.256 |
mant | +0.252 |
otaur | +0.246 |
Neg logit contributions | |
awk | -0.396 |
argon | -0.388 |
Cheney | -0.341 |
olicy | -0.331 |
lam | -0.326 |
Token | harder |
Token ID | 7069 |
Feature activation | -4.87e-02 |
Pos logit contributions | |
quart | +0.038 |
bucket | +0.036 |
strap | +0.034 |
mant | +0.033 |
otaur | +0.033 |
Neg logit contributions | |
awk | -0.060 |
argon | -0.059 |
Cheney | -0.052 |
olicy | -0.050 |
lam | -0.050 |
Token | than |
Token ID | 621 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
awk | +0.112 |
argon | +0.109 |
Cheney | +0.095 |
lam | +0.091 |
olicy | +0.091 |
Neg logit contributions | |
quart | -0.103 |
bucket | -0.100 |
strap | -0.094 |
otaur | -0.093 |
mant | -0.093 |
Token | any |
Token ID | 597 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
awk | +0.033 |
argon | +0.032 |
Cheney | +0.028 |
olicy | +0.027 |
lam | +0.027 |
Neg logit contributions | |
quart | -0.025 |
bucket | -0.024 |
strap | -0.022 |
mant | -0.022 |
otaur | -0.021 |
Token | other |
Token ID | 584 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
quart | +0.049 |
bucket | +0.047 |
strap | +0.044 |
otaur | +0.044 |
mant | +0.043 |
Neg logit contributions | |
awk | -0.063 |
argon | -0.061 |
Cheney | -0.054 |
lam | -0.051 |
olicy | -0.051 |
Token | project |
Token ID | 1628 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
awk | +0.045 |
argon | +0.044 |
Cheney | +0.040 |
lam | +0.038 |
olicy | +0.038 |
Neg logit contributions | |
quart | -0.028 |
bucket | -0.027 |
strap | -0.025 |
otaur | -0.025 |
mant | -0.025 |
Token | I |
Token ID | 314 |
Feature activation | +1.15e-03 |
Pos logit contributions | |
awk | +0.059 |
argon | +0.057 |
Cheney | +0.051 |
olicy | +0.048 |
lam | +0.048 |
Neg logit contributions | |
quart | -0.045 |
bucket | -0.043 |
strap | -0.040 |
mant | -0.040 |
otaur | -0.040 |
Token | 've |
Token ID | 1053 |
Feature activation | -8.99e-03 |
Pos logit contributions | |
quart | +0.003 |
bucket | +0.002 |
strap | +0.002 |
mant | +0.002 |
otaur | +0.002 |
Neg logit contributions | |
awk | -0.003 |
argon | -0.003 |
Cheney | -0.002 |
olicy | -0.002 |
lam | -0.002 |
Token | ever |
Token ID | 1683 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
awk | +0.020 |
argon | +0.019 |
Cheney | +0.017 |
olicy | +0.016 |
lam | +0.016 |
Neg logit contributions | |
quart | -0.020 |
bucket | -0.020 |
strap | -0.018 |
mant | -0.018 |
otaur | -0.018 |
Token | done |
Token ID | 1760 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
awk | +0.032 |
argon | +0.031 |
Cheney | +0.027 |
olicy | +0.026 |
lam | +0.025 |
Neg logit contributions | |
quart | -0.033 |
bucket | -0.032 |
strap | -0.030 |
otaur | -0.030 |
mant | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
awk | +0.066 |
argon | +0.064 |
Cheney | +0.057 |
lam | +0.055 |
olicy | +0.054 |
Neg logit contributions | |
quart | -0.051 |
bucket | -0.049 |
strap | -0.046 |
otaur | -0.046 |
mant | -0.045 |
Token | slam |
Token ID | 21158 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
awk | +0.071 |
argon | +0.069 |
Cheney | +0.060 |
olicy | +0.057 |
lam | +0.057 |
Neg logit contributions | |
quart | -0.068 |
bucket | -0.066 |
strap | -0.062 |
otaur | -0.061 |
mant | -0.060 |
Token | mer |
Token ID | 647 |
Feature activation | -8.23e-02 |
Pos logit contributions | |
quart | +0.392 |
bucket | +0.377 |
strap | +0.354 |
otaur | +0.354 |
mant | +0.349 |
Neg logit contributions | |
awk | -0.452 |
argon | -0.438 |
Cheney | -0.388 |
lam | -0.369 |
olicy | -0.366 |
Token | for |
Token ID | 329 |
Feature activation | -6.09e-02 |
Pos logit contributions | |
awk | +0.195 |
argon | +0.189 |
Cheney | +0.168 |
lam | +0.160 |
olicy | +0.158 |
Neg logit contributions | |
quart | -0.169 |
bucket | -0.162 |
strap | -0.152 |
otaur | -0.152 |
mant | -0.150 |
Token | drug |
Token ID | 2563 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
awk | +0.148 |
argon | +0.143 |
Cheney | +0.125 |
olicy | +0.120 |
lam | +0.120 |
Neg logit contributions | |
quart | -0.124 |
bucket | -0.119 |
strap | -0.113 |
otaur | -0.110 |
mant | -0.109 |
Token | - |
Token ID | 12 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
quart | +0.238 |
bucket | +0.228 |
strap | +0.214 |
otaur | +0.211 |
mant | +0.209 |
Neg logit contributions | |
awk | -0.318 |
argon | -0.309 |
Cheney | -0.273 |
lam | -0.264 |
olicy | -0.261 |
Token | related |
Token ID | 5363 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
quart | +0.043 |
bucket | +0.042 |
strap | +0.039 |
otaur | +0.039 |
mant | +0.038 |
Neg logit contributions | |
awk | -0.055 |
argon | -0.053 |
Cheney | -0.047 |
olicy | -0.045 |
lam | -0.045 |
Token | charges |
Token ID | 4530 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
quart | +0.415 |
bucket | +0.397 |
strap | +0.372 |
mant | +0.364 |
otaur | +0.361 |
Neg logit contributions | |
awk | -0.572 |
argon | -0.558 |
Cheney | -0.486 |
lam | -0.469 |
olicy | -0.468 |
Token | . |
Token ID | 13 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
awk | +0.288 |
argon | +0.278 |
Cheney | +0.247 |
lam | +0.235 |
olicy | +0.234 |
Neg logit contributions | |
quart | -0.241 |
bucket | -0.231 |
strap | -0.217 |
otaur | -0.215 |
mant | -0.213 |
Token | Today |
Token ID | 6288 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
quart | +0.049 |
bucket | +0.046 |
strap | +0.043 |
mant | +0.043 |
otaur | +0.043 |
Neg logit contributions | |
awk | -0.053 |
argon | -0.052 |
olicy | -0.044 |
Cheney | -0.044 |
lam | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | -9.25e-03 |
Pos logit contributions | |
awk | +0.082 |
argon | +0.079 |
Cheney | +0.070 |
lam | +0.067 |
olicy | +0.066 |
Neg logit contributions | |
quart | -0.068 |
bucket | -0.065 |
otaur | -0.061 |
strap | -0.061 |
mant | -0.060 |
Token | of |
Token ID | 286 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
quart | +0.193 |
bucket | +0.185 |
strap | +0.173 |
otaur | +0.173 |
mant | +0.170 |
Neg logit contributions | |
awk | -0.260 |
argon | -0.252 |
Cheney | -0.226 |
lam | -0.216 |
olicy | -0.214 |
Token | the |
Token ID | 262 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
quart | +0.023 |
bucket | +0.022 |
strap | +0.021 |
otaur | +0.021 |
mant | +0.020 |
Neg logit contributions | |
awk | -0.028 |
argon | -0.027 |
Cheney | -0.024 |
lam | -0.023 |
olicy | -0.023 |
Token | players |
Token ID | 1938 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
awk | +0.094 |
argon | +0.091 |
Cheney | +0.081 |
lam | +0.078 |
olicy | +0.078 |
Neg logit contributions | |
quart | -0.065 |
bucket | -0.062 |
strap | -0.058 |
otaur | -0.057 |
mant | -0.057 |
Token | involved |
Token ID | 2950 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
awk | +0.035 |
argon | +0.034 |
Cheney | +0.030 |
lam | +0.029 |
olicy | +0.029 |
Neg logit contributions | |
quart | -0.028 |
bucket | -0.027 |
strap | -0.025 |
otaur | -0.025 |
mant | -0.025 |
Token | might |
Token ID | 1244 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
awk | +0.037 |
argon | +0.036 |
Cheney | +0.031 |
olicy | +0.030 |
lam | +0.030 |
Neg logit contributions | |
quart | -0.028 |
bucket | -0.027 |
strap | -0.025 |
otaur | -0.025 |
mant | -0.025 |
Token | imply |
Token ID | 20135 |
Feature activation | -8.08e-03 |
Pos logit contributions | |
quart | +0.069 |
bucket | +0.067 |
strap | +0.063 |
mant | +0.061 |
otaur | +0.060 |
Neg logit contributions | |
awk | -0.090 |
argon | -0.088 |
Cheney | -0.078 |
olicy | -0.074 |
lam | -0.074 |
Token | something |
Token ID | 1223 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
awk | +0.021 |
argon | +0.021 |
Cheney | +0.018 |
lam | +0.018 |
olicy | +0.018 |
Neg logit contributions | |
quart | -0.015 |
bucket | -0.014 |
strap | -0.013 |
otaur | -0.013 |
mant | -0.013 |
Token | may |
Token ID | 743 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
quart | +0.085 |
bucket | +0.081 |
strap | +0.076 |
mant | +0.075 |
otaur | +0.074 |
Neg logit contributions | |
awk | -0.114 |
argon | -0.111 |
Cheney | -0.098 |
lam | -0.094 |
olicy | -0.094 |
Token | be |
Token ID | 307 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
quart | +0.131 |
bucket | +0.127 |
strap | +0.120 |
otaur | +0.117 |
mant | +0.117 |
Neg logit contributions | |
awk | -0.149 |
argon | -0.145 |
Cheney | -0.128 |
olicy | -0.122 |
lam | -0.121 |
Token | in |
Token ID | 287 |
Feature activation | +7.11e-03 |
Pos logit contributions | |
quart | +0.058 |
bucket | +0.056 |
strap | +0.052 |
mant | +0.051 |
otaur | +0.050 |
Neg logit contributions | |
awk | -0.079 |
argon | -0.078 |
Cheney | -0.068 |
olicy | -0.066 |
lam | -0.065 |
Token | the |
Token ID | 262 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
quart | +0.014 |
bucket | +0.013 |
strap | +0.012 |
otaur | +0.012 |
mant | +0.012 |
Neg logit contributions | |
awk | -0.018 |
argon | -0.017 |
Cheney | -0.015 |
lam | -0.015 |
olicy | -0.015 |
Token | IGN |
Token ID | 16284 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
quart | +0.127 |
bucket | +0.122 |
otaur | +0.117 |
strap | +0.115 |
mant | +0.114 |
Neg logit contributions | |
awk | -0.131 |
argon | -0.126 |
Cheney | -0.112 |
olicy | -0.107 |
lam | -0.105 |
Token | : |
Token ID | 25 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
quart | +0.391 |
bucket | +0.369 |
mant | +0.334 |
strap | +0.329 |
otaur | +0.326 |
Neg logit contributions | |
awk | -0.817 |
argon | -0.803 |
olicy | -0.727 |
Cheney | -0.719 |
lam | -0.694 |
Token | Got |
Token ID | 11853 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
quart | +0.048 |
bucket | +0.046 |
mant | +0.043 |
strap | +0.043 |
otaur | +0.043 |
Neg logit contributions | |
awk | -0.050 |
argon | -0.048 |
Cheney | -0.041 |
olicy | -0.041 |
lam | -0.040 |
Token | cha |
Token ID | 11693 |
Feature activation | -7.03e-03 |
Pos logit contributions | |
quart | +0.072 |
bucket | +0.069 |
strap | +0.065 |
otaur | +0.065 |
mant | +0.064 |
Neg logit contributions | |
awk | -0.103 |
argon | -0.099 |
Cheney | -0.089 |
lam | -0.085 |
olicy | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | +5.64e-02 |
Pos logit contributions | |
awk | +0.017 |
argon | +0.016 |
Cheney | +0.015 |
lam | +0.014 |
olicy | +0.014 |
Neg logit contributions | |
quart | -0.014 |
bucket | -0.013 |
otaur | -0.013 |
strap | -0.013 |
mant | -0.013 |
Token | Just |
Token ID | 2329 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
quart | +0.120 |
bucket | +0.116 |
strap | +0.108 |
mant | +0.108 |
otaur | +0.108 |
Neg logit contributions | |
awk | -0.129 |
argon | -0.125 |
Cheney | -0.107 |
olicy | -0.106 |
lam | -0.104 |
Token | a |
Token ID | 257 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
quart | +0.195 |
bucket | +0.187 |
strap | +0.176 |
mant | +0.173 |
otaur | +0.173 |
Neg logit contributions | |
awk | -0.263 |
argon | -0.254 |
Cheney | -0.227 |
lam | -0.217 |
olicy | -0.216 |
Token | slight |
Token ID | 3731 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
quart | +0.043 |
bucket | +0.041 |
strap | +0.039 |
mant | +0.038 |
otaur | +0.038 |
Neg logit contributions | |
awk | -0.055 |
argon | -0.053 |
Cheney | -0.047 |
olicy | -0.045 |
lam | -0.045 |
Token | side |
Token ID | 1735 |
Feature activation | -4.15e-02 |
Pos logit contributions | |
awk | +0.342 |
argon | +0.332 |
Cheney | +0.296 |
lam | +0.284 |
olicy | +0.283 |
Neg logit contributions | |
quart | -0.240 |
bucket | -0.231 |
strap | -0.215 |
mant | -0.212 |
otaur | -0.211 |
Token | question |
Token ID | 1808 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
awk | +0.106 |
argon | +0.103 |
Cheney | +0.092 |
lam | +0.088 |
olicy | +0.088 |
Neg logit contributions | |
quart | -0.077 |
bucket | -0.074 |
strap | -0.069 |
otaur | -0.068 |
mant | -0.068 |
Token | , |
Token ID | 11 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
quart | +0.618 |
bucket | +0.595 |
strap | +0.558 |
mant | +0.551 |
otaur | +0.551 |
Neg logit contributions | |
awk | -0.770 |
argon | -0.747 |
Cheney | -0.664 |
lam | -0.633 |
olicy | -0.630 |
Token | umping |
Token ID | 25218 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
quart | +0.065 |
bucket | +0.063 |
otaur | +0.060 |
strap | +0.060 |
mant | +0.059 |
Neg logit contributions | |
awk | -0.058 |
argon | -0.056 |
Cheney | -0.049 |
lam | -0.046 |
olicy | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
quart | +0.288 |
bucket | +0.275 |
strap | +0.255 |
mant | +0.252 |
otaur | +0.251 |
Neg logit contributions | |
awk | -0.411 |
argon | -0.398 |
Cheney | -0.355 |
lam | -0.340 |
olicy | -0.339 |
Token | the |
Token ID | 262 |
Feature activation | -8.25e-03 |
Pos logit contributions | |
awk | +0.049 |
argon | +0.047 |
Cheney | +0.042 |
lam | +0.040 |
olicy | +0.040 |
Neg logit contributions | |
quart | -0.037 |
bucket | -0.035 |
strap | -0.033 |
otaur | -0.033 |
mant | -0.033 |
Token | small |
Token ID | 1402 |
Feature activation | -5.94e-03 |
Pos logit contributions | |
awk | +0.022 |
argon | +0.021 |
Cheney | +0.019 |
lam | +0.018 |
olicy | +0.018 |
Neg logit contributions | |
quart | -0.015 |
bucket | -0.014 |
strap | -0.013 |
otaur | -0.013 |
mant | -0.013 |
Token | man |
Token ID | 582 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
awk | +0.015 |
argon | +0.015 |
Cheney | +0.013 |
lam | +0.012 |
olicy | +0.012 |
Neg logit contributions | |
quart | -0.011 |
bucket | -0.011 |
strap | -0.010 |
otaur | -0.010 |
mant | -0.010 |
Token | seated |
Token ID | 21639 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
quart | +0.292 |
bucket | +0.279 |
strap | +0.263 |
mant | +0.259 |
otaur | +0.258 |
Neg logit contributions | |
awk | -0.363 |
argon | -0.355 |
Cheney | -0.315 |
olicy | -0.301 |
lam | -0.300 |
Token | next |
Token ID | 1306 |
Feature activation | +4.68e-02 |
Pos logit contributions | |
awk | +0.308 |
argon | +0.300 |
Cheney | +0.268 |
lam | +0.258 |
olicy | +0.257 |
Neg logit contributions | |
quart | -0.205 |
bucket | -0.195 |
strap | -0.182 |
otaur | -0.180 |
mant | -0.179 |
Token | to |
Token ID | 284 |
Feature activation | +5.19e-04 |
Pos logit contributions | |
quart | +0.083 |
bucket | +0.080 |
strap | +0.074 |
otaur | +0.074 |
mant | +0.073 |
Neg logit contributions | |
awk | -0.124 |
argon | -0.120 |
Cheney | -0.108 |
lam | -0.103 |
olicy | -0.103 |
Token | him |
Token ID | 683 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
quart | +0.001 |
bucket | +0.001 |
strap | +0.001 |
mant | +0.001 |
otaur | +0.001 |
Neg logit contributions | |
awk | -0.001 |
argon | -0.001 |
Cheney | -0.001 |
lam | -0.001 |
olicy | -0.001 |
Token | drives |
Token ID | 10182 |
Feature activation | -5.04e-02 |
Pos logit contributions | |
awk | +0.074 |
argon | +0.072 |
Cheney | +0.064 |
olicy | +0.062 |
lam | +0.061 |
Neg logit contributions | |
quart | -0.059 |
bucket | -0.057 |
strap | -0.054 |
mant | -0.053 |
otaur | -0.052 |
Token | an |
Token ID | 281 |
Feature activation | -7.88e-02 |
Pos logit contributions | |
awk | +0.126 |
argon | +0.123 |
Cheney | +0.109 |
lam | +0.104 |
olicy | +0.104 |
Neg logit contributions | |
quart | -0.097 |
bucket | -0.093 |
strap | -0.087 |
otaur | -0.086 |
mant | -0.086 |
Token | hearing |
Token ID | 4854 |
Feature activation | -7.39e-02 |
Pos logit contributions | |
awk | +0.536 |
argon | +0.519 |
Cheney | +0.461 |
lam | +0.439 |
olicy | +0.435 |
Neg logit contributions | |
quart | -0.447 |
bucket | -0.429 |
strap | -0.404 |
otaur | -0.403 |
mant | -0.398 |
Token | on |
Token ID | 319 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
awk | +0.185 |
argon | +0.179 |
Cheney | +0.160 |
lam | +0.152 |
olicy | +0.151 |
Neg logit contributions | |
quart | -0.142 |
bucket | -0.136 |
strap | -0.128 |
otaur | -0.127 |
mant | -0.126 |
Token | hold |
Token ID | 1745 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
awk | +0.126 |
argon | +0.122 |
Cheney | +0.108 |
lam | +0.104 |
olicy | +0.102 |
Neg logit contributions | |
quart | -0.100 |
bucket | -0.096 |
otaur | -0.090 |
strap | -0.090 |
mant | -0.088 |
Token | until |
Token ID | 1566 |
Feature activation | -4.45e-02 |
Pos logit contributions | |
awk | +0.599 |
argon | +0.582 |
Cheney | +0.523 |
lam | +0.502 |
olicy | +0.497 |
Neg logit contributions | |
quart | -0.392 |
bucket | -0.374 |
strap | -0.348 |
otaur | -0.347 |
mant | -0.342 |
Token | the |
Token ID | 262 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
awk | +0.113 |
argon | +0.110 |
Cheney | +0.098 |
lam | +0.094 |
olicy | +0.093 |
Neg logit contributions | |
quart | -0.083 |
bucket | -0.080 |
strap | -0.075 |
otaur | -0.074 |
mant | -0.073 |
Token | bigger |
Token ID | 5749 |
Feature activation | -4.42e-02 |
Pos logit contributions | |
awk | +0.052 |
argon | +0.051 |
Cheney | +0.046 |
lam | +0.044 |
olicy | +0.044 |
Neg logit contributions | |
quart | -0.035 |
bucket | -0.033 |
strap | -0.031 |
otaur | -0.031 |
mant | -0.031 |
Token | issue |
Token ID | 2071 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
awk | +0.113 |
argon | +0.111 |
Cheney | +0.098 |
lam | +0.094 |
olicy | +0.093 |
Neg logit contributions | |
quart | -0.083 |
bucket | -0.080 |
strap | -0.074 |
otaur | -0.074 |
mant | -0.073 |
Token | can |
Token ID | 460 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
awk | +0.279 |
argon | +0.271 |
Cheney | +0.241 |
lam | +0.231 |
olicy | +0.229 |
Neg logit contributions | |
quart | -0.213 |
bucket | -0.204 |
strap | -0.191 |
otaur | -0.190 |
mant | -0.188 |
Token | be |
Token ID | 307 |
Feature activation | +6.21e-02 |
Pos logit contributions | |
quart | +0.082 |
bucket | +0.079 |
strap | +0.074 |
otaur | +0.074 |
mant | +0.073 |
Neg logit contributions | |
awk | -0.095 |
argon | -0.092 |
Cheney | -0.082 |
lam | -0.078 |
olicy | -0.077 |
Token | considered |
Token ID | 3177 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
quart | +0.127 |
bucket | +0.121 |
strap | +0.114 |
mant | +0.112 |
otaur | +0.112 |
Neg logit contributions | |
awk | -0.150 |
argon | -0.145 |
Cheney | -0.128 |
lam | -0.121 |
olicy | -0.121 |
Token | first |
Token ID | 717 |
Feature activation | -7.45e-02 |
Pos logit contributions | |
quart | +0.390 |
bucket | +0.373 |
strap | +0.350 |
otaur | +0.346 |
mant | +0.344 |
Neg logit contributions | |
awk | -0.497 |
argon | -0.482 |
Cheney | -0.428 |
lam | -0.409 |
olicy | -0.406 |
Token | the |
Token ID | 262 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
quart | +0.005 |
bucket | +0.005 |
strap | +0.005 |
otaur | +0.005 |
mant | +0.005 |
Neg logit contributions | |
awk | -0.007 |
argon | -0.007 |
Cheney | -0.006 |
lam | -0.006 |
olicy | -0.006 |
Token | reliably |
Token ID | 26995 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
quart | +0.033 |
bucket | +0.031 |
strap | +0.029 |
mant | +0.029 |
otaur | +0.029 |
Neg logit contributions | |
awk | -0.043 |
argon | -0.042 |
Cheney | -0.037 |
olicy | -0.036 |
lam | -0.036 |
Token | offensive |
Token ID | 5859 |
Feature activation | +4.21e-02 |
Pos logit contributions | |
awk | +0.138 |
argon | +0.134 |
Cheney | +0.117 |
olicy | +0.112 |
lam | +0.110 |
Neg logit contributions | |
quart | -0.138 |
bucket | -0.132 |
strap | -0.125 |
mant | -0.124 |
otaur | -0.122 |
Token | Fox |
Token ID | 5426 |
Feature activation | +3.95e-02 |
Pos logit contributions | |
quart | +0.084 |
bucket | +0.081 |
strap | +0.076 |
mant | +0.075 |
otaur | +0.075 |
Neg logit contributions | |
awk | -0.103 |
argon | -0.099 |
Cheney | -0.088 |
lam | -0.084 |
olicy | -0.084 |
Token | News |
Token ID | 3000 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
quart | +0.109 |
bucket | +0.106 |
strap | +0.101 |
otaur | +0.101 |
mant | +0.100 |
Neg logit contributions | |
awk | -0.065 |
argon | -0.062 |
Cheney | -0.052 |
lam | -0.048 |
olicy | -0.048 |
Token | show |
Token ID | 905 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
awk | +0.084 |
argon | +0.081 |
Cheney | +0.072 |
lam | +0.069 |
olicy | +0.068 |
Neg logit contributions | |
quart | -0.071 |
bucket | -0.068 |
strap | -0.064 |
otaur | -0.063 |
mant | -0.063 |
Token | managed |
Token ID | 5257 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
awk | +0.277 |
argon | +0.269 |
Cheney | +0.239 |
olicy | +0.229 |
lam | +0.228 |
Neg logit contributions | |
quart | -0.210 |
bucket | -0.200 |
strap | -0.188 |
otaur | -0.186 |
mant | -0.186 |
Token | to |
Token ID | 284 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
quart | +0.057 |
bucket | +0.054 |
otaur | +0.052 |
strap | +0.051 |
mant | +0.050 |
Neg logit contributions | |
awk | -0.073 |
argon | -0.071 |
Cheney | -0.063 |
lam | -0.061 |
olicy | -0.060 |
Token | out |
Token ID | 503 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
quart | +0.029 |
bucket | +0.028 |
strap | +0.027 |
mant | +0.026 |
otaur | +0.025 |
Neg logit contributions | |
awk | -0.038 |
argon | -0.037 |
Cheney | -0.033 |
olicy | -0.032 |
lam | -0.031 |
Token | do |
Token ID | 4598 |
Feature activation | -9.08e-02 |
Pos logit contributions | |
awk | +0.031 |
argon | +0.029 |
Cheney | +0.025 |
olicy | +0.023 |
lam | +0.023 |
Neg logit contributions | |
quart | -0.046 |
bucket | -0.044 |
strap | -0.042 |
mant | -0.042 |
otaur | -0.041 |
Token | itself |
Token ID | 2346 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
awk | +0.216 |
argon | +0.208 |
Cheney | +0.184 |
lam | +0.176 |
olicy | +0.175 |
Neg logit contributions | |
quart | -0.186 |
bucket | -0.179 |
strap | -0.168 |
otaur | -0.167 |
mant | -0.166 |
Token | . |
Token ID | 13 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
awk | +0.045 |
argon | +0.044 |
Cheney | +0.039 |
lam | +0.037 |
olicy | +0.037 |
Neg logit contributions | |
quart | -0.043 |
bucket | -0.041 |
strap | -0.039 |
otaur | -0.039 |
mant | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | +7.11e-03 |
Pos logit contributions | |
quart | +0.080 |
bucket | +0.077 |
strap | +0.072 |
otaur | +0.072 |
mant | +0.071 |
Neg logit contributions | |
awk | -0.087 |
argon | -0.084 |
Cheney | -0.074 |
lam | -0.070 |
olicy | -0.070 |
Token |
|
Token ID | 198 |
Feature activation | +6.87e-03 |
Pos logit contributions | |
quart | +0.014 |
bucket | +0.013 |
strap | +0.012 |
mant | +0.012 |
otaur | +0.012 |
Neg logit contributions | |
awk | -0.018 |
argon | -0.017 |
Cheney | -0.015 |
olicy | -0.015 |
lam | -0.014 |
Token | Vi |
Token ID | 38432 |
Feature activation | -2.79e-03 |
Pos logit contributions | |
quart | +0.016 |
bucket | +0.015 |
otaur | +0.014 |
strap | +0.014 |
mant | +0.014 |
Neg logit contributions | |
awk | -0.015 |
argon | -0.014 |
Cheney | -0.013 |
olicy | -0.012 |
lam | -0.012 |
Token | aches |
Token ID | 3694 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
awk | +0.005 |
argon | +0.005 |
Cheney | +0.004 |
olicy | +0.004 |
lam | +0.003 |
Neg logit contributions | |
quart | -0.008 |
bucket | -0.007 |
otaur | -0.007 |
strap | -0.007 |
mant | -0.007 |
Token | lav |
Token ID | 18809 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
awk | +0.080 |
argon | +0.079 |
Cheney | +0.071 |
olicy | +0.068 |
Exec | +0.066 |
Neg logit contributions | |
quart | -0.059 |
bucket | -0.056 |
otaur | -0.053 |
strap | -0.052 |
dden | -0.052 |
Token | Pl |
Token ID | 1345 |
Feature activation | -8.34e-03 |
Pos logit contributions | |
awk | +0.467 |
argon | +0.450 |
Cheney | +0.395 |
lam | +0.375 |
olicy | +0.370 |
Neg logit contributions | |
quart | -0.473 |
bucket | -0.456 |
strap | -0.431 |
otaur | -0.431 |
mant | -0.426 |
Token | ak |
Token ID | 461 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
awk | +0.020 |
argon | +0.019 |
Cheney | +0.017 |
olicy | +0.016 |
lam | +0.016 |
Neg logit contributions | |
quart | -0.017 |
bucket | -0.016 |
otaur | -0.015 |
strap | -0.015 |
mant | -0.015 |
Token | as |
Token ID | 292 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
quart | +0.256 |
bucket | +0.248 |
strap | +0.236 |
otaur | +0.236 |
ça | +0.231 |
Neg logit contributions | |
awk | -0.265 |
argon | -0.256 |
Cheney | -0.235 |
olicy | -0.223 |
Exec | -0.214 |
Token | ov |
Token ID | 709 |
Feature activation | -4.87e-02 |
Pos logit contributions | |
quart | +0.270 |
bucket | +0.261 |
otaur | +0.251 |
strap | +0.248 |
ça | +0.243 |
Neg logit contributions | |
awk | -0.243 |
argon | -0.237 |
Cheney | -0.210 |
olicy | -0.200 |
GOP | -0.190 |
Token | is |
Token ID | 318 |
Feature activation | -7.10e-02 |
Pos logit contributions | |
awk | +0.119 |
argon | +0.115 |
Cheney | +0.102 |
lam | +0.098 |
olicy | +0.097 |
Neg logit contributions | |
quart | -0.097 |
bucket | -0.093 |
strap | -0.087 |
otaur | -0.086 |
mant | -0.086 |
Token | . |
Token ID | 764 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
awk | +0.068 |
argon | +0.067 |
Cheney | +0.059 |
lam | +0.056 |
olicy | +0.056 |
Neg logit contributions | |
quart | -0.053 |
bucket | -0.052 |
strap | -0.048 |
otaur | -0.048 |
mant | -0.048 |
Token | Can |
Token ID | 1680 |
Feature activation | -8.85e-02 |
Pos logit contributions | |
awk | +0.053 |
argon | +0.052 |
Cheney | +0.045 |
lam | +0.043 |
olicy | +0.043 |
Neg logit contributions | |
quart | -0.054 |
bucket | -0.053 |
strap | -0.049 |
mant | -0.049 |
otaur | -0.049 |
Token | � |
Token ID | 447 |
Feature activation | -1.77e-03 |
Pos logit contributions | |
awk | +0.224 |
argon | +0.218 |
Cheney | +0.195 |
lam | +0.186 |
olicy | +0.185 |
Neg logit contributions | |
quart | -0.167 |
bucket | -0.161 |
strap | -0.150 |
otaur | -0.149 |
mant | -0.148 |
Token | � |
Token ID | 247 |
Feature activation | +5.62e-02 |
Pos logit contributions | |
awk | +0.004 |
argon | +0.004 |
Cheney | +0.004 |
lam | +0.003 |
olicy | +0.003 |
Neg logit contributions | |
quart | -0.004 |
bucket | -0.004 |
otaur | -0.003 |
strap | -0.003 |
mant | -0.003 |
Token | t |
Token ID | 83 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
quart | +0.117 |
bucket | +0.113 |
strap | +0.107 |
otaur | +0.106 |
mant | +0.105 |
Neg logit contributions | |
awk | -0.130 |
argon | -0.127 |
Cheney | -0.113 |
olicy | -0.107 |
lam | -0.106 |
Token | compare |
Token ID | 8996 |
Feature activation | -5.80e-02 |
Pos logit contributions | |
awk | +0.039 |
argon | +0.038 |
Cheney | +0.034 |
lam | +0.032 |
olicy | +0.032 |
Neg logit contributions | |
quart | -0.031 |
bucket | -0.030 |
strap | -0.028 |
mant | -0.028 |
otaur | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
awk | +0.143 |
argon | +0.140 |
Cheney | +0.123 |
lam | +0.119 |
olicy | +0.117 |
Neg logit contributions | |
quart | -0.115 |
bucket | -0.111 |
strap | -0.102 |
mant | -0.102 |
otaur | -0.101 |
Token | the |
Token ID | 262 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
quart | +0.090 |
bucket | +0.088 |
strap | +0.081 |
mant | +0.080 |
otaur | +0.079 |
Neg logit contributions | |
awk | -0.115 |
argon | -0.113 |
Cheney | -0.100 |
lam | -0.096 |
olicy | -0.095 |
Token | original |
Token ID | 2656 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
quart | +0.061 |
bucket | +0.059 |
strap | +0.054 |
mant | +0.054 |
otaur | +0.053 |
Neg logit contributions | |
awk | -0.080 |
argon | -0.078 |
Cheney | -0.069 |
lam | -0.066 |
olicy | -0.066 |
Token | because |
Token ID | 780 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
quart | +0.031 |
bucket | +0.031 |
strap | +0.028 |
mant | +0.028 |
otaur | +0.028 |
Neg logit contributions | |
awk | -0.038 |
argon | -0.037 |
Cheney | -0.032 |
lam | -0.031 |
olicy | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
awk | +0.052 |
argon | +0.051 |
Cheney | +0.045 |
lam | +0.043 |
olicy | +0.043 |
Neg logit contributions | |
quart | -0.039 |
bucket | -0.037 |
strap | -0.035 |
otaur | -0.034 |
mant | -0.034 |
Token | 7 |
Token ID | 767 |
Feature activation | +4.88e-03 |
Pos logit contributions | |
quart | +0.492 |
bucket | +0.473 |
strap | +0.445 |
otaur | +0.445 |
mant | +0.438 |
Neg logit contributions | |
awk | -0.586 |
argon | -0.567 |
Cheney | -0.504 |
lam | -0.480 |
olicy | -0.475 |
Token | . |
Token ID | 13 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
quart | +0.009 |
bucket | +0.008 |
strap | +0.008 |
mant | +0.008 |
otaur | +0.008 |
Neg logit contributions | |
awk | -0.013 |
argon | -0.012 |
Cheney | -0.011 |
olicy | -0.011 |
lam | -0.011 |
Token | N |
Token ID | 399 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
awk | +0.365 |
argon | +0.353 |
Cheney | +0.310 |
lam | +0.296 |
olicy | +0.293 |
Neg logit contributions | |
quart | -0.321 |
bucket | -0.309 |
strap | -0.290 |
otaur | -0.287 |
mant | -0.286 |
Token | b |
Token ID | 65 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
awk | +0.219 |
argon | +0.210 |
Cheney | +0.183 |
lam | +0.169 |
olicy | +0.168 |
Neg logit contributions | |
quart | -0.288 |
bucket | -0.279 |
otaur | -0.266 |
strap | -0.265 |
mant | -0.261 |
Token | 3 |
Token ID | 18 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
awk | +0.270 |
argon | +0.259 |
Cheney | +0.222 |
lam | +0.208 |
olicy | +0.207 |
Neg logit contributions | |
quart | -0.359 |
bucket | -0.346 |
strap | -0.330 |
otaur | -0.328 |
mant | -0.325 |
Token | { |
Token ID | 1391 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
awk | +0.069 |
argon | +0.067 |
Cheney | +0.059 |
lam | +0.056 |
olicy | +0.055 |
Neg logit contributions | |
quart | -0.071 |
bucket | -0.069 |
otaur | -0.065 |
strap | -0.065 |
mant | -0.064 |
Token | ( |
Token ID | 7 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
awk | +0.716 |
argon | +0.691 |
Cheney | +0.596 |
olicy | +0.569 |
lam | +0.539 |
Neg logit contributions | |
quart | -0.988 |
bucket | -0.958 |
otaur | -0.910 |
strap | -0.904 |
mant | -0.901 |
Token | 244 |
Token ID | 25707 |
Feature activation | -7.11e-02 |
Pos logit contributions | |
awk | +0.193 |
argon | +0.184 |
Cheney | +0.156 |
olicy | +0.144 |
lam | +0.143 |
Neg logit contributions | |
quart | -0.303 |
bucket | -0.295 |
otaur | -0.281 |
strap | -0.280 |
mant | -0.279 |
Token | s |
Token ID | 82 |
Feature activation | -8.84e-02 |
Pos logit contributions | |
awk | +0.186 |
argon | +0.181 |
Cheney | +0.164 |
olicy | +0.158 |
lam | +0.154 |
Neg logit contributions | |
quart | -0.126 |
bucket | -0.121 |
strap | -0.113 |
otaur | -0.111 |
mant | -0.111 |
Token | )} |
Token ID | 38165 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
awk | +0.230 |
argon | +0.225 |
Cheney | +0.204 |
olicy | +0.195 |
lam | +0.190 |
Neg logit contributions | |
quart | -0.157 |
bucket | -0.150 |
otaur | -0.142 |
strap | -0.141 |
mant | -0.140 |
Token | Be |
Token ID | 1355 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
quart | +0.502 |
bucket | +0.483 |
strap | +0.451 |
otaur | +0.448 |
mant | +0.444 |
Neg logit contributions | |
awk | -0.594 |
argon | -0.578 |
Cheney | -0.506 |
lam | -0.482 |
olicy | -0.479 |
Token |
|
Token ID | 198 |
Feature activation | -6.78e-02 |
Pos logit contributions | |
awk | +0.557 |
argon | +0.537 |
Cheney | +0.475 |
lam | +0.452 |
olicy | +0.443 |
Neg logit contributions | |
quart | -0.519 |
bucket | -0.500 |
strap | -0.472 |
otaur | -0.470 |
mant | -0.465 |
Token |
|
Token ID | 198 |
Feature activation | -4.69e-02 |
Pos logit contributions | |
awk | +0.167 |
argon | +0.164 |
Cheney | +0.144 |
olicy | +0.143 |
lam | +0.137 |
Neg logit contributions | |
quart | -0.131 |
bucket | -0.126 |
strap | -0.117 |
mant | -0.116 |
otaur | -0.115 |
Token | + |
Token ID | 10 |
Feature activation | -7.35e-02 |
Pos logit contributions | |
awk | +0.098 |
argon | +0.095 |
Cheney | +0.082 |
lam | +0.078 |
olicy | +0.076 |
Neg logit contributions | |
quart | -0.109 |
bucket | -0.106 |
strap | -0.101 |
otaur | -0.100 |
mant | -0.099 |
Token | Intelligent |
Token ID | 49452 |
Feature activation | +7.30e-03 |
Pos logit contributions | |
awk | +0.169 |
argon | +0.165 |
Cheney | +0.142 |
lam | +0.138 |
olicy | +0.137 |
Neg logit contributions | |
quart | -0.156 |
bucket | -0.150 |
strap | -0.140 |
mant | -0.139 |
otaur | -0.139 |
Token | , |
Token ID | 11 |
Feature activation | -7.84e-02 |
Pos logit contributions | |
quart | +0.015 |
bucket | +0.015 |
otaur | +0.014 |
strap | +0.014 |
mant | +0.014 |
Neg logit contributions | |
awk | -0.017 |
argon | -0.016 |
Cheney | -0.014 |
lam | -0.014 |
olicy | -0.014 |
Token | Techn |
Token ID | 5429 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
awk | +0.182 |
argon | +0.177 |
Cheney | +0.152 |
lam | +0.148 |
olicy | +0.147 |
Neg logit contributions | |
quart | -0.166 |
bucket | -0.160 |
strap | -0.149 |
mant | -0.148 |
otaur | -0.147 |
Token | ophile |
Token ID | 37161 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
awk | +0.905 |
argon | +0.875 |
Cheney | +0.774 |
lam | +0.737 |
olicy | +0.728 |
Neg logit contributions | |
quart | -0.820 |
bucket | -0.789 |
otaur | -0.744 |
strap | -0.743 |
mant | -0.733 |
Token | , |
Token ID | 11 |
Feature activation | -8.27e-02 |
Pos logit contributions | |
quart | +0.089 |
bucket | +0.086 |
otaur | +0.082 |
strap | +0.082 |
mant | +0.080 |
Neg logit contributions | |
awk | -0.095 |
argon | -0.092 |
Cheney | -0.082 |
lam | -0.077 |
olicy | -0.076 |
Token | Diplom |
Token ID | 34905 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
awk | +0.192 |
argon | +0.186 |
Cheney | +0.162 |
lam | +0.156 |
olicy | +0.156 |
Neg logit contributions | |
quart | -0.174 |
bucket | -0.167 |
strap | -0.156 |
mant | -0.155 |
otaur | -0.155 |
Token | atic |
Token ID | 1512 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
quart | +0.349 |
bucket | +0.334 |
strap | +0.310 |
otaur | +0.310 |
mant | +0.306 |
Neg logit contributions | |
awk | -0.450 |
argon | -0.439 |
Cheney | -0.395 |
lam | -0.377 |
olicy | -0.372 |
Token |
|
Token ID | 198 |
Feature activation | +1.21e-03 |
Pos logit contributions | |
awk | +0.072 |
argon | +0.070 |
Cheney | +0.062 |
lam | +0.058 |
olicy | +0.058 |
Neg logit contributions | |
quart | -0.069 |
bucket | -0.066 |
otaur | -0.063 |
strap | -0.063 |
mant | -0.062 |
Token | year |
Token ID | 1941 |
Feature activation | +6.09e-02 |
Pos logit contributions | |
awk | +0.038 |
argon | +0.037 |
Cheney | +0.032 |
olicy | +0.030 |
lam | +0.030 |
Neg logit contributions | |
quart | -0.046 |
bucket | -0.045 |
strap | -0.042 |
otaur | -0.042 |
mant | -0.042 |
Token | , |
Token ID | 11 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
quart | +0.119 |
bucket | +0.114 |
strap | +0.107 |
otaur | +0.107 |
mant | +0.105 |
Neg logit contributions | |
awk | -0.150 |
argon | -0.146 |
Cheney | -0.130 |
lam | -0.124 |
olicy | -0.123 |
Token | $ |
Token ID | 720 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
quart | +0.024 |
bucket | +0.022 |
strap | +0.021 |
otaur | +0.021 |
mant | +0.020 |
Neg logit contributions | |
awk | -0.039 |
argon | -0.038 |
Cheney | -0.034 |
lam | -0.033 |
olicy | -0.032 |
Token | 72 |
Token ID | 4761 |
Feature activation | +5.05e-02 |
Pos logit contributions | |
awk | +0.037 |
argon | +0.036 |
olicy | +0.030 |
Cheney | +0.030 |
lam | +0.027 |
Neg logit contributions | |
quart | -0.060 |
bucket | -0.058 |
otaur | -0.055 |
strap | -0.055 |
ça | -0.055 |
Token | million |
Token ID | 1510 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
quart | +0.117 |
bucket | +0.112 |
otaur | +0.107 |
strap | +0.107 |
mant | +0.105 |
Neg logit contributions | |
awk | -0.105 |
argon | -0.102 |
Cheney | -0.088 |
lam | -0.084 |
olicy | -0.082 |
Token | contract |
Token ID | 2775 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
quart | +0.032 |
bucket | +0.030 |
strap | +0.028 |
otaur | +0.027 |
mant | +0.027 |
Neg logit contributions | |
awk | -0.052 |
argon | -0.051 |
Cheney | -0.046 |
lam | -0.044 |
olicy | -0.044 |
Token | with |
Token ID | 351 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
awk | +0.955 |
argon | +0.923 |
Cheney | +0.823 |
lam | +0.785 |
olicy | +0.773 |
Neg logit contributions | |
quart | -0.811 |
bucket | -0.778 |
otaur | -0.736 |
strap | -0.733 |
mant | -0.723 |
Token | $ |
Token ID | 720 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
awk | +0.130 |
argon | +0.126 |
Cheney | +0.113 |
lam | +0.108 |
olicy | +0.108 |
Neg logit contributions | |
quart | -0.089 |
bucket | -0.085 |
strap | -0.079 |
otaur | -0.079 |
mant | -0.078 |
Token | 37 |
Token ID | 2718 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
awk | +0.036 |
argon | +0.035 |
Cheney | +0.030 |
olicy | +0.029 |
lam | +0.027 |
Neg logit contributions | |
quart | -0.057 |
bucket | -0.055 |
otaur | -0.053 |
strap | -0.053 |
mant | -0.052 |
Token | million |
Token ID | 1510 |
Feature activation | +6.08e-02 |
Pos logit contributions | |
quart | +0.256 |
bucket | +0.247 |
otaur | +0.235 |
strap | +0.234 |
mant | +0.231 |
Neg logit contributions | |
awk | -0.245 |
argon | -0.236 |
Cheney | -0.206 |
lam | -0.196 |
olicy | -0.193 |
Token | guaranteed |
Token ID | 11462 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
quart | +0.117 |
bucket | +0.113 |
strap | +0.105 |
mant | +0.104 |
otaur | +0.103 |
Neg logit contributions | |
awk | -0.154 |
argon | -0.150 |
Cheney | -0.132 |
lam | -0.126 |
olicy | -0.126 |
Token | 30 |
Token ID | 1542 |
Feature activation | +8.43e-02 |
Pos logit contributions | |
quart | +0.457 |
bucket | +0.437 |
otaur | +0.409 |
strap | +0.409 |
mant | +0.404 |
Neg logit contributions | |
awk | -0.619 |
argon | -0.599 |
Cheney | -0.540 |
lam | -0.514 |
olicy | -0.510 |
Token | . |
Token ID | 13 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
quart | +0.150 |
bucket | +0.143 |
strap | +0.134 |
otaur | +0.131 |
mant | +0.131 |
Neg logit contributions | |
awk | -0.221 |
argon | -0.216 |
Cheney | -0.191 |
olicy | -0.191 |
lam | -0.183 |
Token | K |
Token ID | 509 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
awk | +0.293 |
argon | +0.283 |
Cheney | +0.249 |
lam | +0.237 |
olicy | +0.235 |
Neg logit contributions | |
quart | -0.259 |
bucket | -0.249 |
strap | -0.233 |
otaur | -0.232 |
mant | -0.230 |
Token | f |
Token ID | 69 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
awk | +0.025 |
argon | +0.024 |
Cheney | +0.021 |
olicy | +0.019 |
lam | +0.019 |
Neg logit contributions | |
quart | -0.041 |
bucket | -0.040 |
otaur | -0.038 |
strap | -0.038 |
mant | -0.038 |
Token | 2 |
Token ID | 17 |
Feature activation | -8.01e-02 |
Pos logit contributions | |
quart | +0.265 |
bucket | +0.256 |
otaur | +0.245 |
strap | +0.243 |
mant | +0.239 |
Neg logit contributions | |
awk | -0.197 |
argon | -0.188 |
Cheney | -0.163 |
olicy | -0.152 |
lam | -0.148 |
Token | { |
Token ID | 1391 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
awk | +0.170 |
argon | +0.164 |
Cheney | +0.144 |
lam | +0.137 |
olicy | +0.135 |
Neg logit contributions | |
quart | -0.182 |
bucket | -0.176 |
strap | -0.167 |
otaur | -0.167 |
mant | -0.166 |
Token | ( |
Token ID | 7 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
awk | +0.771 |
argon | +0.744 |
Cheney | +0.637 |
olicy | +0.613 |
lam | +0.580 |
Neg logit contributions | |
quart | -1.081 |
bucket | -1.047 |
otaur | -0.995 |
strap | -0.991 |
mant | -0.985 |
Token | 4 |
Token ID | 19 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
awk | +0.185 |
argon | +0.177 |
Cheney | +0.151 |
olicy | +0.141 |
lam | +0.140 |
Neg logit contributions | |
quart | -0.271 |
bucket | -0.263 |
otaur | -0.250 |
strap | -0.250 |
mant | -0.248 |
Token | s |
Token ID | 82 |
Feature activation | -8.81e-02 |
Pos logit contributions | |
awk | +0.308 |
argon | +0.299 |
Cheney | +0.264 |
lam | +0.253 |
hs | +0.249 |
Neg logit contributions | |
quart | -0.272 |
bucket | -0.260 |
otaur | -0.247 |
strap | -0.246 |
mant | -0.244 |
Token | )} |
Token ID | 38165 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
awk | +0.230 |
argon | +0.224 |
Cheney | +0.204 |
olicy | +0.195 |
lam | +0.190 |
Neg logit contributions | |
quart | -0.156 |
bucket | -0.149 |
otaur | -0.141 |
strap | -0.140 |
mant | -0.139 |
Token | g |
Token ID | 308 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
quart | +0.517 |
bucket | +0.496 |
strap | +0.465 |
otaur | +0.460 |
mant | +0.456 |
Neg logit contributions | |
awk | -0.597 |
argon | -0.578 |
Cheney | -0.503 |
lam | -0.481 |
olicy | -0.481 |
Token | a |
Token ID | 257 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
awk | +0.057 |
argon | +0.056 |
Cheney | +0.050 |
lam | +0.048 |
olicy | +0.047 |
Neg logit contributions | |
quart | -0.042 |
bucket | -0.040 |
otaur | -0.037 |
strap | -0.037 |
mant | -0.037 |
Token | bur |
Token ID | 4356 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
awk | +0.097 |
argon | +0.094 |
Cheney | +0.085 |
lam | +0.082 |
olicy | +0.081 |
Neg logit contributions | |
quart | -0.058 |
bucket | -0.056 |
strap | -0.051 |
otaur | -0.051 |
mant | -0.050 |
Token | rito |
Token ID | 39834 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
quart | +0.073 |
bucket | +0.071 |
otaur | +0.066 |
strap | +0.066 |
mant | +0.065 |
Neg logit contributions | |
awk | -0.072 |
argon | -0.070 |
Cheney | -0.061 |
lam | -0.058 |
olicy | -0.057 |
Token | or |
Token ID | 393 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
awk | +0.626 |
argon | +0.604 |
Cheney | +0.541 |
lam | +0.518 |
olicy | +0.510 |
Neg logit contributions | |
quart | -0.492 |
bucket | -0.470 |
otaur | -0.448 |
strap | -0.442 |
mant | -0.437 |
Token | peanut |
Token ID | 26636 |
Feature activation | -6.00e-02 |
Pos logit contributions | |
quart | +0.049 |
bucket | +0.047 |
strap | +0.044 |
mant | +0.043 |
otaur | +0.043 |
Neg logit contributions | |
awk | -0.069 |
argon | -0.067 |
Cheney | -0.059 |
lam | -0.057 |
olicy | -0.057 |
Token | butter |
Token ID | 9215 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
awk | +0.152 |
argon | +0.147 |
Cheney | +0.132 |
lam | +0.126 |
olicy | +0.124 |
Neg logit contributions | |
quart | -0.112 |
bucket | -0.107 |
otaur | -0.101 |
strap | -0.101 |
mant | -0.099 |
Token | sandwich |
Token ID | 20433 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
awk | +1.150 |
argon | +1.107 |
Cheney | +1.005 |
lam | +0.963 |
olicy | +0.949 |
Neg logit contributions | |
quart | -0.743 |
bucket | -0.701 |
otaur | -0.673 |
strap | -0.663 |
mant | -0.651 |
Token | . |
Token ID | 13 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
quart | +0.091 |
bucket | +0.088 |
otaur | +0.083 |
strap | +0.083 |
mant | +0.081 |
Neg logit contributions | |
awk | -0.108 |
argon | -0.104 |
Cheney | -0.093 |
lam | -0.089 |
olicy | -0.087 |
Token | If |
Token ID | 1002 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
quart | +0.041 |
bucket | +0.040 |
otaur | +0.037 |
strap | +0.037 |
mant | +0.037 |
Neg logit contributions | |
awk | -0.037 |
argon | -0.036 |
Cheney | -0.031 |
lam | -0.029 |
olicy | -0.029 |
Token | you |
Token ID | 345 |
Feature activation | -6.11e-02 |
Pos logit contributions | |
awk | +0.030 |
argon | +0.029 |
Cheney | +0.026 |
lam | +0.025 |
olicy | +0.025 |
Neg logit contributions | |
quart | -0.023 |
bucket | -0.022 |
otaur | -0.021 |
strap | -0.021 |
mant | -0.021 |
Token | do |
Token ID | 466 |
Feature activation | -9.01e-03 |
Pos logit contributions | |
awk | +0.152 |
argon | +0.149 |
Cheney | +0.131 |
olicy | +0.125 |
lam | +0.124 |
Neg logit contributions | |
quart | -0.120 |
bucket | -0.116 |
strap | -0.109 |
mant | -0.107 |
otaur | -0.106 |