Token | the |
Token ID | 262 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
cius | +0.208 |
rapes | +0.149 |
lic | +0.146 |
Comes | +0.144 |
:= | +0.141 |
Neg logit contributions | |
hesda | -0.173 |
Arizona | -0.164 |
anyahu | -0.159 |
Catal | -0.151 |
orno | -0.148 |
Token | Transport |
Token ID | 19940 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
cius | +0.366 |
rapes | +0.263 |
lic | +0.258 |
Comes | +0.254 |
:= | +0.250 |
Neg logit contributions | |
hesda | -0.295 |
Arizona | -0.279 |
anyahu | -0.272 |
Catal | -0.257 |
orno | -0.252 |
Token | Department |
Token ID | 2732 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
cius | +0.764 |
rapes | +0.509 |
lic | +0.498 |
Comes | +0.493 |
:= | +0.480 |
Neg logit contributions | |
hesda | -0.858 |
Arizona | -0.818 |
anyahu | -0.800 |
Catal | -0.763 |
offense | -0.752 |
Token | . |
Token ID | 13 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
cius | +0.594 |
rapes | +0.409 |
lic | +0.400 |
Comes | +0.395 |
:= | +0.389 |
Neg logit contributions | |
hesda | -0.568 |
Arizona | -0.541 |
anyahu | -0.527 |
Catal | -0.502 |
offense | -0.497 |
Token | Stre |
Token ID | 9737 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
cius | +0.305 |
rapes | +0.207 |
lic | +0.203 |
Comes | +0.203 |
:= | +0.197 |
Neg logit contributions | |
hesda | -0.322 |
Arizona | -0.304 |
anyahu | -0.300 |
Catal | -0.283 |
orno | -0.280 |
Token | ng |
Token ID | 782 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
cius | +0.926 |
rapes | +0.363 |
lic | +0.353 |
Comes | +0.326 |
:= | +0.316 |
Neg logit contributions | |
hesda | -2.531 |
Arizona | -2.465 |
anyahu | -2.410 |
Catal | -2.342 |
offense | -2.328 |
Token | thening |
Token ID | 20563 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
cius | +2.529 |
rapes | +1.607 |
lic | +1.588 |
Comes | +1.535 |
:= | +1.520 |
Neg logit contributions | |
hesda | -3.186 |
Arizona | -3.042 |
anyahu | -2.983 |
Catal | -2.862 |
offense | -2.846 |
Token | rural |
Token ID | 10016 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
cius | +0.753 |
rapes | +0.524 |
lic | +0.513 |
Comes | +0.506 |
:= | +0.497 |
Neg logit contributions | |
hesda | -0.697 |
Arizona | -0.661 |
anyahu | -0.646 |
Catal | -0.612 |
offense | -0.602 |
Token | transport |
Token ID | 4839 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
cius | +0.287 |
rapes | +0.209 |
lic | +0.205 |
Comes | +0.202 |
:= | +0.199 |
Neg logit contributions | |
hesda | -0.220 |
Arizona | -0.207 |
anyahu | -0.203 |
Catal | -0.190 |
orno | -0.187 |
Token | , |
Token ID | 11 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
cius | +0.060 |
rapes | +0.043 |
lic | +0.042 |
Comes | +0.042 |
:= | +0.041 |
Neg logit contributions | |
hesda | -0.050 |
Arizona | -0.047 |
anyahu | -0.046 |
Catal | -0.043 |
orno | -0.042 |
Token | last |
Token ID | 938 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
cius | +0.263 |
rapes | +0.188 |
lic | +0.184 |
Comes | +0.182 |
:= | +0.178 |
Neg logit contributions | |
hesda | -0.221 |
Arizona | -0.209 |
anyahu | -0.205 |
Catal | -0.193 |
orno | -0.189 |
Token | � |
Token ID | 251 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
cius | +0.200 |
rapes | +0.123 |
lic | +0.119 |
Comes | +0.117 |
:= | +0.114 |
Neg logit contributions | |
hesda | -0.283 |
Arizona | -0.271 |
anyahu | -0.264 |
Catal | -0.255 |
offense | -0.254 |
Token | and |
Token ID | 290 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
hesda | +0.147 |
Arizona | +0.141 |
anyahu | +0.137 |
Catal | +0.131 |
offense | +0.130 |
Neg logit contributions | |
cius | -0.141 |
rapes | -0.095 |
lic | -0.093 |
Comes | -0.092 |
:= | -0.090 |
Token | � |
Token ID | 564 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
cius | +0.166 |
rapes | +0.119 |
lic | +0.115 |
Comes | +0.114 |
:= | +0.113 |
Neg logit contributions | |
hesda | -0.144 |
Arizona | -0.136 |
anyahu | -0.133 |
Catal | -0.125 |
orno | -0.124 |
Token | � |
Token ID | 250 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
cius | +0.010 |
rapes | +0.006 |
lic | +0.006 |
Comes | +0.006 |
:= | +0.006 |
Neg logit contributions | |
hesda | -0.015 |
Arizona | -0.015 |
anyahu | -0.015 |
Catal | -0.014 |
offense | -0.014 |
Token | stre |
Token ID | 22853 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
hesda | +0.118 |
Arizona | +0.112 |
anyahu | +0.109 |
Catal | +0.104 |
offense | +0.103 |
Neg logit contributions | |
cius | -0.126 |
rapes | -0.087 |
lic | -0.085 |
Comes | -0.084 |
:= | -0.082 |
Token | ng |
Token ID | 782 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
cius | +0.599 |
rapes | +0.237 |
lic | +0.234 |
Comes | +0.212 |
:= | +0.204 |
Neg logit contributions | |
hesda | -1.636 |
Arizona | -1.589 |
anyahu | -1.559 |
Catal | -1.510 |
offense | -1.502 |
Token | then |
Token ID | 8524 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
cius | +2.563 |
rapes | +1.662 |
lic | +1.640 |
Comes | +1.570 |
:= | +1.563 |
Neg logit contributions | |
hesda | -3.092 |
Arizona | -2.928 |
anyahu | -2.881 |
Catal | -2.774 |
offense | -2.749 |
Token | faculty |
Token ID | 12829 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
cius | +1.316 |
rapes | +0.922 |
lic | +0.905 |
Comes | +0.887 |
:= | +0.873 |
Neg logit contributions | |
hesda | -1.171 |
Arizona | -1.102 |
anyahu | -1.080 |
Catal | -1.019 |
orno | -1.005 |
Token | tenure |
Token ID | 17081 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
hesda | +0.081 |
Arizona | +0.077 |
anyahu | +0.075 |
Catal | +0.071 |
offense | +0.070 |
Neg logit contributions | |
cius | -0.099 |
rapes | -0.071 |
lic | -0.069 |
Comes | -0.069 |
:= | -0.068 |
Token | systems |
Token ID | 3341 |
Feature activation | +7.68e-02 |
Pos logit contributions | |
hesda | +0.763 |
Arizona | +0.727 |
anyahu | +0.706 |
Catal | +0.673 |
offense | +0.668 |
Neg logit contributions | |
cius | -0.813 |
rapes | -0.560 |
lic | -0.549 |
Comes | -0.542 |
:= | -0.533 |
Token | . |
Token ID | 13 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
cius | +0.064 |
rapes | +0.043 |
lic | +0.042 |
Comes | +0.042 |
:= | +0.041 |
Neg logit contributions | |
hesda | -0.067 |
Arizona | -0.064 |
anyahu | -0.062 |
Catal | -0.059 |
offense | -0.059 |
Token | with |
Token ID | 351 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
cius | +1.092 |
rapes | +0.721 |
lic | +0.706 |
Comes | +0.691 |
:= | +0.679 |
Neg logit contributions | |
hesda | -1.250 |
Arizona | -1.199 |
anyahu | -1.166 |
Catal | -1.120 |
offense | -1.101 |
Token | residue |
Token ID | 35186 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
cius | +0.219 |
rapes | +0.157 |
lic | +0.153 |
Comes | +0.150 |
:= | +0.148 |
Neg logit contributions | |
hesda | -0.187 |
Arizona | -0.178 |
anyahu | -0.173 |
Catal | -0.164 |
orno | -0.160 |
Token | from |
Token ID | 422 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
cius | +0.466 |
rapes | +0.313 |
lic | +0.306 |
Comes | +0.301 |
:= | +0.295 |
Neg logit contributions | |
hesda | -0.507 |
Arizona | -0.487 |
anyahu | -0.476 |
Catal | -0.453 |
offense | -0.446 |
Token | the |
Token ID | 262 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
cius | +0.341 |
rapes | +0.241 |
lic | +0.234 |
Comes | +0.231 |
:= | +0.227 |
Neg logit contributions | |
hesda | -0.309 |
Arizona | -0.294 |
anyahu | -0.287 |
Catal | -0.272 |
offense | -0.267 |
Token | des |
Token ID | 748 |
Feature activation | +9.19e-01 |
Pos logit contributions | |
cius | +0.215 |
rapes | +0.150 |
lic | +0.145 |
Comes | +0.143 |
:= | +0.140 |
Neg logit contributions | |
hesda | -0.211 |
Arizona | -0.201 |
anyahu | -0.196 |
Catal | -0.186 |
orno | -0.183 |
Token | icc |
Token ID | 44240 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
cius | +0.673 |
lic | +0.421 |
rapes | +0.400 |
:= | +0.390 |
esian | +0.390 |
Neg logit contributions | |
hesda | -0.890 |
Arizona | -0.866 |
anyahu | -0.850 |
Catal | -0.823 |
offense | -0.812 |
Token | ant |
Token ID | 415 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
cius | +2.357 |
lic | +1.470 |
rapes | +1.470 |
Comes | +1.410 |
:= | +1.376 |
Neg logit contributions | |
hesda | -3.193 |
Arizona | -3.058 |
anyahu | -2.996 |
Catal | -2.890 |
offense | -2.844 |
Token | . |
Token ID | 13 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
cius | +0.689 |
rapes | +0.468 |
lic | +0.456 |
Comes | +0.448 |
:= | +0.440 |
Neg logit contributions | |
hesda | -0.727 |
Arizona | -0.696 |
anyahu | -0.680 |
Catal | -0.648 |
orno | -0.635 |
Token | You |
Token ID | 921 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
cius | +0.098 |
rapes | +0.066 |
lic | +0.065 |
Comes | +0.065 |
:= | +0.063 |
Neg logit contributions | |
hesda | -0.101 |
Arizona | -0.095 |
anyahu | -0.094 |
offense | -0.088 |
Catal | -0.088 |
Token | do |
Token ID | 466 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
hesda | +0.097 |
Arizona | +0.091 |
anyahu | +0.089 |
Catal | +0.085 |
offense | +0.082 |
Neg logit contributions | |
cius | -0.116 |
rapes | -0.083 |
lic | -0.081 |
Comes | -0.080 |
:= | -0.079 |
Token | not |
Token ID | 407 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
hesda | +0.210 |
Arizona | +0.199 |
anyahu | +0.194 |
Catal | +0.184 |
offense | +0.182 |
Neg logit contributions | |
cius | -0.235 |
rapes | -0.164 |
lic | -0.161 |
Comes | -0.159 |
:= | -0.157 |
Token | to |
Token ID | 284 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
cius | +0.178 |
rapes | +0.122 |
lic | +0.119 |
Comes | +0.117 |
:= | +0.115 |
Neg logit contributions | |
hesda | -0.181 |
Arizona | -0.173 |
anyahu | -0.169 |
Catal | -0.160 |
offense | -0.158 |
Token | use |
Token ID | 779 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
hesda | +0.196 |
Arizona | +0.186 |
anyahu | +0.182 |
Catal | +0.172 |
offense | +0.169 |
Neg logit contributions | |
cius | -0.211 |
rapes | -0.147 |
lic | -0.144 |
Comes | -0.142 |
:= | -0.140 |
Token | the |
Token ID | 262 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
hesda | +0.591 |
Arizona | +0.562 |
anyahu | +0.546 |
Catal | +0.520 |
offense | +0.514 |
Neg logit contributions | |
cius | -0.655 |
rapes | -0.456 |
lic | -0.447 |
Comes | -0.441 |
:= | -0.434 |
Token | old |
Token ID | 1468 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
cius | +0.133 |
rapes | +0.092 |
lic | +0.090 |
Comes | +0.089 |
:= | +0.087 |
Neg logit contributions | |
hesda | -0.126 |
Arizona | -0.120 |
anyahu | -0.117 |
Catal | -0.111 |
offense | -0.109 |
Token | des |
Token ID | 748 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
cius | +0.272 |
rapes | +0.188 |
lic | +0.183 |
Comes | +0.180 |
:= | +0.177 |
Neg logit contributions | |
hesda | -0.268 |
Arizona | -0.256 |
anyahu | -0.250 |
Catal | -0.237 |
orno | -0.232 |
Token | icc |
Token ID | 44240 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
cius | +0.564 |
lic | +0.356 |
rapes | +0.355 |
Comes | +0.339 |
:= | +0.338 |
Neg logit contributions | |
hesda | -0.702 |
Arizona | -0.673 |
anyahu | -0.660 |
Catal | -0.639 |
offense | -0.627 |
Token | ant |
Token ID | 415 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
cius | +2.378 |
rapes | +1.516 |
lic | +1.515 |
Comes | +1.452 |
:= | +1.429 |
Neg logit contributions | |
hesda | -3.024 |
Arizona | -2.902 |
anyahu | -2.839 |
Catal | -2.729 |
offense | -2.689 |
Token | . |
Token ID | 13 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
cius | +0.659 |
rapes | +0.446 |
lic | +0.435 |
Comes | +0.428 |
:= | +0.421 |
Neg logit contributions | |
hesda | -0.692 |
Arizona | -0.662 |
anyahu | -0.646 |
Catal | -0.615 |
offense | -0.605 |
Token | The |
Token ID | 383 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
cius | +0.117 |
rapes | +0.079 |
lic | +0.078 |
Comes | +0.077 |
:= | +0.075 |
Neg logit contributions | |
hesda | -0.127 |
Arizona | -0.119 |
anyahu | -0.118 |
offense | -0.111 |
Catal | -0.111 |
Token | chamber |
Token ID | 11847 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
cius | +0.359 |
rapes | +0.254 |
lic | +0.246 |
Comes | +0.243 |
:= | +0.240 |
Neg logit contributions | |
hesda | -0.322 |
Arizona | -0.307 |
anyahu | -0.298 |
Catal | -0.283 |
orno | -0.276 |
Token | will |
Token ID | 481 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
cius | +1.098 |
rapes | +0.787 |
lic | +0.770 |
Comes | +0.761 |
:= | +0.748 |
Neg logit contributions | |
hesda | -0.887 |
Arizona | -0.845 |
anyahu | -0.822 |
Catal | -0.776 |
orno | -0.755 |
Token | has |
Token ID | 468 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
cius | +0.584 |
rapes | +0.407 |
lic | +0.395 |
Comes | +0.393 |
:= | +0.385 |
Neg logit contributions | |
hesda | -0.559 |
Arizona | -0.534 |
anyahu | -0.519 |
Catal | -0.495 |
orno | -0.488 |
Token | now |
Token ID | 783 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
hesda | +0.239 |
Arizona | +0.226 |
anyahu | +0.220 |
Catal | +0.208 |
offense | +0.204 |
Neg logit contributions | |
cius | -0.297 |
rapes | -0.212 |
lic | -0.209 |
Comes | -0.206 |
:= | -0.203 |
Token | been |
Token ID | 587 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
cius | +0.181 |
rapes | +0.128 |
lic | +0.125 |
Comes | +0.124 |
:= | +0.122 |
Neg logit contributions | |
hesda | -0.159 |
Arizona | -0.150 |
anyahu | -0.147 |
Catal | -0.139 |
offense | -0.137 |
Token | well |
Token ID | 880 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
hesda | +0.245 |
Arizona | +0.233 |
anyahu | +0.227 |
Catal | +0.217 |
offense | +0.214 |
Neg logit contributions | |
cius | -0.241 |
rapes | -0.164 |
lic | -0.161 |
Comes | -0.158 |
:= | -0.156 |
Token | te |
Token ID | 573 |
Feature activation | +7.80e-03 |
Pos logit contributions | |
cius | +0.108 |
rapes | +0.075 |
lic | +0.075 |
Comes | +0.072 |
:= | +0.071 |
Neg logit contributions | |
hesda | -0.101 |
Arizona | -0.096 |
anyahu | -0.093 |
Catal | -0.089 |
orno | -0.087 |
Token | leg |
Token ID | 1455 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
cius | +0.007 |
rapes | +0.005 |
lic | +0.005 |
Comes | +0.005 |
:= | +0.005 |
Neg logit contributions | |
hesda | -0.006 |
Arizona | -0.006 |
anyahu | -0.005 |
Catal | -0.005 |
offense | -0.005 |
Token | rap |
Token ID | 2416 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
cius | +1.749 |
lic | +0.999 |
rapes | +0.970 |
Comes | +0.902 |
:= | +0.868 |
Neg logit contributions | |
hesda | -3.483 |
anyahu | -3.308 |
Arizona | -3.307 |
Catal | -3.173 |
offense | -3.168 |
Token | hed |
Token ID | 704 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
cius | +1.723 |
lic | +1.278 |
rapes | +1.247 |
:= | +1.204 |
Comes | +1.196 |
Neg logit contributions | |
hesda | -1.318 |
Arizona | -1.249 |
anyahu | -1.211 |
Catal | -1.161 |
offense | -1.154 |
Token | and |
Token ID | 290 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
hesda | +1.578 |
Arizona | +1.503 |
anyahu | +1.462 |
Catal | +1.396 |
offense | +1.384 |
Neg logit contributions | |
cius | -1.673 |
rapes | -1.148 |
lic | -1.123 |
Comes | -1.111 |
:= | -1.090 |
Token | will |
Token ID | 481 |
Feature activation | -4.64e-02 |
Pos logit contributions | |
hesda | +0.009 |
Arizona | +0.008 |
anyahu | +0.008 |
Catal | +0.008 |
orno | +0.008 |
Neg logit contributions | |
cius | -0.010 |
rapes | -0.007 |
lic | -0.007 |
Comes | -0.007 |
:= | -0.007 |
Token | take |
Token ID | 1011 |
Feature activation | -8.54e-02 |
Pos logit contributions | |
hesda | +0.035 |
Arizona | +0.033 |
anyahu | +0.032 |
Catal | +0.030 |
offense | +0.030 |
Neg logit contributions | |
cius | -0.044 |
rapes | -0.032 |
lic | -0.031 |
Comes | -0.031 |
:= | -0.030 |
Token | process |
Token ID | 1429 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
cius | +0.144 |
rapes | +0.102 |
lic | +0.100 |
Comes | +0.098 |
:= | +0.098 |
Neg logit contributions | |
hesda | -0.123 |
Arizona | -0.117 |
anyahu | -0.115 |
Catal | -0.107 |
orno | -0.106 |
Token | and |
Token ID | 290 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
hesda | +0.652 |
Arizona | +0.620 |
anyahu | +0.603 |
Catal | +0.574 |
offense | +0.568 |
Neg logit contributions | |
cius | -0.714 |
rapes | -0.496 |
lic | -0.486 |
Comes | -0.480 |
:= | -0.472 |
Token | � |
Token ID | 564 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
cius | +0.425 |
rapes | +0.299 |
lic | +0.293 |
Comes | +0.286 |
:= | +0.286 |
Neg logit contributions | |
hesda | -0.390 |
Arizona | -0.370 |
anyahu | -0.361 |
Catal | -0.340 |
orno | -0.338 |
Token | � |
Token ID | 250 |
Feature activation | -9.80e-02 |
Pos logit contributions | |
cius | +0.030 |
rapes | +0.017 |
lic | +0.017 |
:= | +0.016 |
Comes | +0.016 |
Neg logit contributions | |
hesda | -0.050 |
Arizona | -0.048 |
anyahu | -0.047 |
Catal | -0.045 |
offense | -0.045 |
Token | stre |
Token ID | 22853 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
hesda | +0.081 |
Arizona | +0.076 |
anyahu | +0.075 |
Catal | +0.071 |
offense | +0.070 |
Neg logit contributions | |
cius | -0.086 |
rapes | -0.059 |
lic | -0.059 |
Comes | -0.057 |
:= | -0.057 |
Token | ng |
Token ID | 782 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
cius | +0.489 |
rapes | +0.197 |
lic | +0.192 |
Comes | +0.177 |
:= | +0.170 |
Neg logit contributions | |
hesda | -1.322 |
Arizona | -1.283 |
anyahu | -1.260 |
Catal | -1.219 |
offense | -1.211 |
Token | then |
Token ID | 8524 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
cius | +2.464 |
rapes | +1.638 |
lic | +1.625 |
Comes | +1.550 |
:= | +1.549 |
Neg logit contributions | |
hesda | -2.789 |
Arizona | -2.629 |
anyahu | -2.603 |
Catal | -2.490 |
offense | -2.471 |
Token | � |
Token ID | 447 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
cius | +1.163 |
rapes | +0.830 |
lic | +0.819 |
Comes | +0.800 |
:= | +0.791 |
Neg logit contributions | |
hesda | -0.967 |
Arizona | -0.914 |
anyahu | -0.897 |
Catal | -0.840 |
orno | -0.826 |
Token | � |
Token ID | 251 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
cius | +0.264 |
rapes | +0.158 |
lic | +0.154 |
Comes | +0.151 |
:= | +0.147 |
Neg logit contributions | |
hesda | -0.397 |
Arizona | -0.382 |
anyahu | -0.374 |
Catal | -0.360 |
offense | -0.356 |
Token | its |
Token ID | 663 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
cius | +0.021 |
rapes | +0.015 |
lic | +0.014 |
Comes | +0.014 |
:= | +0.014 |
Neg logit contributions | |
hesda | -0.016 |
Arizona | -0.016 |
anyahu | -0.015 |
Catal | -0.014 |
offense | -0.014 |
Token | own |
Token ID | 898 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
cius | +0.227 |
rapes | +0.166 |
lic | +0.163 |
Comes | +0.161 |
:= | +0.159 |
Neg logit contributions | |
hesda | -0.162 |
Arizona | -0.152 |
anyahu | -0.149 |
Catal | -0.138 |
orno | -0.136 |
Token | 2002 |
Token ID | 6244 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
cius | +0.256 |
rapes | +0.180 |
lic | +0.178 |
Comes | +0.175 |
:= | +0.172 |
Neg logit contributions | |
hesda | -0.252 |
Arizona | -0.235 |
anyahu | -0.234 |
Catal | -0.220 |
orno | -0.218 |
Token | United |
Token ID | 1578 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
cius | +0.697 |
rapes | +0.485 |
lic | +0.478 |
Comes | +0.475 |
:= | +0.464 |
Neg logit contributions | |
hesda | -0.685 |
Arizona | -0.637 |
anyahu | -0.637 |
Catal | -0.594 |
orno | -0.591 |
Token | States |
Token ID | 1829 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
cius | +0.306 |
rapes | +0.210 |
lic | +0.204 |
Comes | +0.201 |
:= | +0.201 |
Neg logit contributions | |
hesda | -0.289 |
Arizona | -0.277 |
anyahu | -0.268 |
Catal | -0.256 |
offense | -0.254 |
Token | 3 |
Token ID | 513 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
hesda | +0.077 |
Arizona | +0.072 |
anyahu | +0.071 |
Catal | +0.066 |
orno | +0.066 |
Neg logit contributions | |
cius | -0.101 |
rapes | -0.074 |
lic | -0.073 |
Comes | -0.072 |
:= | -0.071 |
Token | 472 |
Token ID | 37856 |
Feature activation | +8.21e-02 |
Pos logit contributions | |
cius | +0.288 |
rapes | +0.204 |
lic | +0.200 |
Comes | +0.198 |
:= | +0.194 |
Neg logit contributions | |
hesda | -0.254 |
Arizona | -0.238 |
anyahu | -0.235 |
Catal | -0.222 |
offense | -0.219 |
Token | Posts |
Token ID | 12043 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
cius | +0.059 |
rapes | +0.039 |
Comes | +0.038 |
lic | +0.038 |
:= | +0.037 |
Neg logit contributions | |
hesda | -0.081 |
Arizona | -0.076 |
anyahu | -0.075 |
Catal | -0.071 |
orno | -0.071 |
Token | # |
Token ID | 1303 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
cius | +2.809 |
rapes | +1.986 |
lic | +1.951 |
Comes | +1.938 |
:= | +1.902 |
Neg logit contributions | |
hesda | -2.367 |
Arizona | -2.242 |
anyahu | -2.182 |
Catal | -2.072 |
offense | -2.026 |
Token | 11 |
Token ID | 1157 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
hesda | +0.536 |
Arizona | +0.502 |
anyahu | +0.493 |
Catal | +0.465 |
offense | +0.461 |
Neg logit contributions | |
cius | -0.677 |
rapes | -0.485 |
lic | -0.479 |
Comes | -0.472 |
:= | -0.468 |
Token | On |
Token ID | 1550 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
cius | +0.698 |
rapes | +0.476 |
lic | +0.465 |
Comes | +0.464 |
:= | +0.452 |
Neg logit contributions | |
hesda | -0.721 |
Arizona | -0.689 |
anyahu | -0.674 |
Catal | -0.643 |
orno | -0.629 |
Token | September |
Token ID | 2693 |
Feature activation | -9.09e-02 |
Pos logit contributions | |
cius | +0.856 |
rapes | +0.625 |
lic | +0.613 |
Comes | +0.609 |
:= | +0.604 |
Neg logit contributions | |
hesda | -0.623 |
Arizona | -0.578 |
anyahu | -0.574 |
Catal | -0.532 |
orno | -0.520 |
Token | 20 |
Token ID | 1160 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
hesda | +0.071 |
Arizona | +0.066 |
anyahu | +0.065 |
Catal | +0.060 |
orno | +0.060 |
Neg logit contributions | |
cius | -0.084 |
rapes | -0.061 |
Comes | -0.060 |
lic | -0.060 |
:= | -0.058 |
Token | June |
Token ID | 2795 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
cius | +1.625 |
rapes | +1.221 |
Comes | +1.208 |
lic | +1.197 |
:= | +1.175 |
Neg logit contributions | |
hesda | -1.208 |
anyahu | -1.099 |
Arizona | -1.082 |
orno | -1.008 |
Catal | -0.992 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
cius | +0.346 |
rapes | +0.244 |
lic | +0.241 |
Comes | +0.240 |
:= | +0.235 |
Neg logit contributions | |
hesda | -0.350 |
anyahu | -0.326 |
Arizona | -0.323 |
orno | -0.304 |
Catal | -0.301 |
Token | Canada |
Token ID | 3340 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
cius | +0.288 |
rapes | +0.201 |
lic | +0.198 |
Comes | +0.196 |
:= | +0.191 |
Neg logit contributions | |
hesda | -0.275 |
Arizona | -0.257 |
anyahu | -0.255 |
Catal | -0.239 |
orno | -0.238 |
Token | 16 |
Token ID | 1467 |
Feature activation | +9.76e-02 |
Pos logit contributions | |
cius | +0.170 |
rapes | +0.124 |
Comes | +0.123 |
lic | +0.123 |
:= | +0.120 |
Neg logit contributions | |
hesda | -0.136 |
anyahu | -0.125 |
Arizona | -0.124 |
orno | -0.115 |
Catal | -0.115 |
Token | 10 |
Token ID | 940 |
Feature activation | +5.82e-02 |
Pos logit contributions | |
cius | +0.085 |
rapes | +0.059 |
lic | +0.057 |
Comes | +0.057 |
:= | +0.056 |
Neg logit contributions | |
hesda | -0.082 |
Arizona | -0.077 |
anyahu | -0.076 |
Catal | -0.072 |
offense | -0.071 |
Token | Posts |
Token ID | 12043 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
cius | +0.043 |
rapes | +0.029 |
lic | +0.028 |
Comes | +0.028 |
:= | +0.027 |
Neg logit contributions | |
hesda | -0.056 |
Arizona | -0.052 |
anyahu | -0.052 |
Catal | -0.049 |
orno | -0.049 |
Token | # |
Token ID | 1303 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
cius | +2.851 |
rapes | +2.029 |
lic | +1.992 |
Comes | +1.971 |
:= | +1.942 |
Neg logit contributions | |
hesda | -2.310 |
Arizona | -2.188 |
anyahu | -2.124 |
Catal | -2.016 |
offense | -1.987 |
Token | 14 |
Token ID | 1415 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
hesda | +0.423 |
Arizona | +0.397 |
anyahu | +0.389 |
Catal | +0.367 |
offense | +0.366 |
Neg logit contributions | |
cius | -0.516 |
rapes | -0.367 |
lic | -0.363 |
Comes | -0.356 |
:= | -0.354 |
Token | On |
Token ID | 1550 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
cius | +0.339 |
rapes | +0.228 |
lic | +0.224 |
Comes | +0.223 |
:= | +0.217 |
Neg logit contributions | |
hesda | -0.355 |
Arizona | -0.339 |
anyahu | -0.332 |
Catal | -0.316 |
orno | -0.311 |
Token | September |
Token ID | 2693 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
cius | +0.833 |
rapes | +0.612 |
Comes | +0.601 |
lic | +0.600 |
:= | +0.594 |
Neg logit contributions | |
hesda | -0.646 |
Arizona | -0.602 |
anyahu | -0.592 |
orno | -0.548 |
Catal | -0.544 |
Token | 20 |
Token ID | 1160 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
hesda | +0.037 |
Arizona | +0.034 |
anyahu | +0.033 |
offense | +0.031 |
Catal | +0.030 |
Neg logit contributions | |
cius | -0.072 |
rapes | -0.055 |
lic | -0.054 |
:= | -0.053 |
Comes | -0.053 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
cius | +0.300 |
rapes | +0.210 |
lic | +0.207 |
Comes | +0.205 |
:= | +0.201 |
Neg logit contributions | |
hesda | -0.307 |
Arizona | -0.286 |
anyahu | -0.285 |
Catal | -0.267 |
orno | -0.266 |
Token | United |
Token ID | 1578 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
cius | +0.658 |
rapes | +0.456 |
lic | +0.449 |
Comes | +0.444 |
:= | +0.435 |
Neg logit contributions | |
hesda | -0.629 |
Arizona | -0.592 |
anyahu | -0.585 |
Catal | -0.551 |
offense | -0.546 |
Token | States |
Token ID | 1829 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
cius | +0.454 |
rapes | +0.316 |
lic | +0.306 |
:= | +0.302 |
Comes | +0.302 |
Neg logit contributions | |
hesda | -0.410 |
Arizona | -0.392 |
anyahu | -0.378 |
Catal | -0.361 |
offense | -0.358 |
Token | 21 |
Token ID | 2310 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
cius | +0.157 |
rapes | +0.115 |
lic | +0.114 |
Comes | +0.113 |
:= | +0.111 |
Neg logit contributions | |
hesda | -0.122 |
anyahu | -0.113 |
Arizona | -0.112 |
Catal | -0.104 |
orno | -0.103 |
Token | 50 |
Token ID | 1120 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
cius | +0.691 |
rapes | +0.483 |
Comes | +0.476 |
lic | +0.474 |
:= | +0.464 |
Neg logit contributions | |
hesda | -0.698 |
anyahu | -0.646 |
Arizona | -0.644 |
orno | -0.603 |
Catal | -0.602 |
Token | Posts |
Token ID | 12043 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
cius | +0.023 |
rapes | +0.015 |
Comes | +0.015 |
lic | +0.015 |
:= | +0.015 |
Neg logit contributions | |
hesda | -0.031 |
Arizona | -0.029 |
anyahu | -0.029 |
Catal | -0.027 |
orno | -0.027 |
Token | # |
Token ID | 1303 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
cius | +2.870 |
rapes | +2.048 |
lic | +2.009 |
Comes | +1.987 |
:= | +1.959 |
Neg logit contributions | |
hesda | -2.290 |
Arizona | -2.170 |
anyahu | -2.105 |
Catal | -1.996 |
offense | -1.971 |
Token | 16 |
Token ID | 1433 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
hesda | +0.333 |
Arizona | +0.320 |
anyahu | +0.310 |
Catal | +0.299 |
offense | +0.295 |
Neg logit contributions | |
cius | -0.299 |
rapes | -0.199 |
lic | -0.193 |
Comes | -0.191 |
:= | -0.186 |
Token | Glad |
Token ID | 28442 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
cius | +0.519 |
rapes | +0.350 |
lic | +0.344 |
Comes | +0.342 |
:= | +0.333 |
Neg logit contributions | |
hesda | -0.544 |
Arizona | -0.521 |
anyahu | -0.509 |
Catal | -0.486 |
orno | -0.476 |
Token | to |
Token ID | 284 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
cius | +0.972 |
rapes | +0.659 |
lic | +0.649 |
Comes | +0.641 |
:= | +0.625 |
Neg logit contributions | |
hesda | -0.961 |
Arizona | -0.921 |
anyahu | -0.901 |
Catal | -0.857 |
orno | -0.840 |
Token | hear |
Token ID | 3285 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
cius | +0.673 |
rapes | +0.487 |
lic | +0.476 |
Comes | +0.471 |
:= | +0.464 |
Neg logit contributions | |
hesda | -0.535 |
Arizona | -0.504 |
anyahu | -0.496 |
Catal | -0.469 |
orno | -0.463 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
cius | +0.282 |
rapes | +0.200 |
lic | +0.197 |
Comes | +0.194 |
:= | +0.190 |
Neg logit contributions | |
hesda | -0.263 |
Arizona | -0.246 |
anyahu | -0.244 |
Catal | -0.229 |
orno | -0.227 |
Token | United |
Token ID | 1578 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
cius | +0.553 |
rapes | +0.388 |
lic | +0.383 |
Comes | +0.378 |
:= | +0.371 |
Neg logit contributions | |
hesda | -0.511 |
Arizona | -0.478 |
anyahu | -0.474 |
Catal | -0.445 |
offense | -0.440 |
Token | States |
Token ID | 1829 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
cius | +0.260 |
rapes | +0.181 |
lic | +0.175 |
:= | +0.173 |
Comes | +0.173 |
Neg logit contributions | |
hesda | -0.231 |
Arizona | -0.221 |
anyahu | -0.214 |
Catal | -0.203 |
offense | -0.202 |
Token | 10 |
Token ID | 838 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
cius | +0.029 |
rapes | +0.021 |
lic | +0.021 |
Comes | +0.021 |
:= | +0.020 |
Neg logit contributions | |
hesda | -0.022 |
anyahu | -0.021 |
Arizona | -0.021 |
Catal | -0.019 |
orno | -0.019 |
Token | 53 |
Token ID | 4310 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
cius | +0.422 |
rapes | +0.289 |
lic | +0.283 |
Comes | +0.280 |
:= | +0.274 |
Neg logit contributions | |
hesda | -0.435 |
Arizona | -0.411 |
anyahu | -0.405 |
Catal | -0.384 |
offense | -0.380 |
Token | Posts |
Token ID | 12043 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
cius | +0.547 |
rapes | +0.354 |
Comes | +0.348 |
lic | +0.346 |
:= | +0.338 |
Neg logit contributions | |
hesda | -0.755 |
Arizona | -0.709 |
anyahu | -0.703 |
orno | -0.666 |
Catal | -0.666 |
Token | # |
Token ID | 1303 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
cius | +2.846 |
rapes | +2.033 |
lic | +1.993 |
Comes | +1.969 |
:= | +1.942 |
Neg logit contributions | |
hesda | -2.262 |
Arizona | -2.144 |
anyahu | -2.079 |
Catal | -1.971 |
offense | -1.950 |
Token | 15 |
Token ID | 1314 |
Feature activation | +9.52e-01 |
Pos logit contributions | |
hesda | +0.446 |
Arizona | +0.420 |
anyahu | +0.413 |
Catal | +0.393 |
offense | +0.392 |
Neg logit contributions | |
cius | -0.434 |
rapes | -0.294 |
lic | -0.292 |
Comes | -0.285 |
:= | -0.284 |
Token | honestly |
Token ID | 12698 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
cius | +0.792 |
rapes | +0.534 |
lic | +0.525 |
Comes | +0.523 |
:= | +0.508 |
Neg logit contributions | |
hesda | -0.825 |
Arizona | -0.791 |
anyahu | -0.772 |
Catal | -0.736 |
orno | -0.723 |
Token | if |
Token ID | 611 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
cius | +1.010 |
rapes | +0.695 |
lic | +0.682 |
Comes | +0.675 |
:= | +0.659 |
Neg logit contributions | |
hesda | -0.973 |
Arizona | -0.934 |
anyahu | -0.913 |
Catal | -0.871 |
orno | -0.849 |
Token | we |
Token ID | 356 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
cius | +0.681 |
rapes | +0.466 |
lic | +0.459 |
Comes | +0.453 |
:= | +0.442 |
Neg logit contributions | |
hesda | -0.657 |
Arizona | -0.630 |
anyahu | -0.613 |
Catal | -0.586 |
offense | -0.573 |
Token | TL |
Token ID | 24811 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
cius | +0.644 |
rapes | +0.447 |
lic | +0.439 |
Comes | +0.433 |
:= | +0.425 |
Neg logit contributions | |
hesda | -0.610 |
Arizona | -0.576 |
anyahu | -0.567 |
Catal | -0.536 |
offense | -0.531 |
Token | AD |
Token ID | 2885 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
cius | +0.979 |
rapes | +0.684 |
Comes | +0.661 |
:= | +0.658 |
lic | +0.657 |
Neg logit contributions | |
hesda | -0.979 |
Arizona | -0.920 |
anyahu | -0.913 |
Catal | -0.862 |
offense | -0.842 |
Token | T |
Token ID | 51 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
cius | +1.469 |
rapes | +1.023 |
lic | +1.001 |
Comes | +0.994 |
:= | +0.975 |
Neg logit contributions | |
hesda | -1.376 |
Arizona | -1.294 |
anyahu | -1.272 |
Catal | -1.207 |
offense | -1.185 |
Token | 235 |
Token ID | 28878 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
cius | +0.695 |
rapes | +0.501 |
lic | +0.499 |
Comes | +0.489 |
:= | +0.484 |
Neg logit contributions | |
hesda | -0.564 |
Arizona | -0.530 |
anyahu | -0.527 |
Catal | -0.493 |
offense | -0.486 |
Token | 21 |
Token ID | 2481 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
cius | +0.907 |
rapes | +0.627 |
lic | +0.613 |
Comes | +0.608 |
:= | +0.596 |
Neg logit contributions | |
hesda | -0.877 |
Arizona | -0.832 |
anyahu | -0.816 |
Catal | -0.773 |
offense | -0.763 |
Token | Posts |
Token ID | 12043 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
cius | +0.598 |
rapes | +0.387 |
lic | +0.383 |
Comes | +0.381 |
:= | +0.373 |
Neg logit contributions | |
hesda | -0.812 |
anyahu | -0.759 |
Arizona | -0.759 |
Catal | -0.717 |
orno | -0.716 |
Token | # |
Token ID | 1303 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
cius | +2.819 |
rapes | +2.009 |
lic | +1.972 |
Comes | +1.951 |
:= | +1.923 |
Neg logit contributions | |
hesda | -2.268 |
Arizona | -2.148 |
anyahu | -2.085 |
Catal | -1.978 |
offense | -1.949 |
Token | 18 |
Token ID | 1507 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
hesda | +0.333 |
Arizona | +0.311 |
anyahu | +0.310 |
offense | +0.293 |
Catal | +0.289 |
Neg logit contributions | |
cius | -0.344 |
lic | -0.236 |
rapes | -0.236 |
:= | -0.231 |
Comes | -0.229 |
Token | Good |
Token ID | 4599 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
cius | +0.336 |
rapes | +0.228 |
lic | +0.223 |
Comes | +0.222 |
:= | +0.217 |
Neg logit contributions | |
hesda | -0.345 |
Arizona | -0.331 |
anyahu | -0.323 |
Catal | -0.308 |
orno | -0.302 |
Token | stuff |
Token ID | 3404 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
cius | +0.581 |
rapes | +0.393 |
lic | +0.385 |
Comes | +0.380 |
:= | +0.373 |
Neg logit contributions | |
hesda | -0.591 |
Arizona | -0.568 |
anyahu | -0.550 |
Catal | -0.529 |
orno | -0.518 |
Token | ! |
Token ID | 0 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
cius | +1.075 |
rapes | +0.717 |
lic | +0.701 |
Comes | +0.701 |
:= | +0.688 |
Neg logit contributions | |
hesda | -1.124 |
Arizona | -1.080 |
anyahu | -1.052 |
Catal | -1.010 |
orno | -0.991 |
Token | what |
Token ID | 644 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
hesda | +0.306 |
Arizona | +0.291 |
anyahu | +0.283 |
Catal | +0.269 |
offense | +0.265 |
Neg logit contributions | |
cius | -0.335 |
rapes | -0.233 |
lic | -0.229 |
Comes | -0.226 |
:= | -0.222 |
Token | follows |
Token ID | 5679 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
hesda | +0.153 |
Arizona | +0.145 |
anyahu | +0.142 |
Catal | +0.135 |
offense | +0.132 |
Neg logit contributions | |
cius | -0.151 |
rapes | -0.103 |
Comes | -0.101 |
lic | -0.101 |
:= | -0.097 |
Token | . |
Token ID | 13 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
cius | +0.623 |
rapes | +0.416 |
lic | +0.408 |
Comes | +0.406 |
:= | +0.397 |
Neg logit contributions | |
hesda | -0.691 |
Arizona | -0.661 |
anyahu | -0.646 |
Catal | -0.615 |
orno | -0.607 |
Token | King |
Token ID | 2677 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
hesda | +0.098 |
Arizona | +0.092 |
anyahu | +0.091 |
Catal | +0.086 |
offense | +0.085 |
Neg logit contributions | |
cius | -0.097 |
rapes | -0.066 |
Comes | -0.065 |
lic | -0.065 |
:= | -0.063 |
Token | te |
Token ID | 573 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
cius | +0.931 |
rapes | +0.649 |
lic | +0.634 |
Comes | +0.623 |
:= | +0.607 |
Neg logit contributions | |
hesda | -0.934 |
Arizona | -0.883 |
anyahu | -0.865 |
Catal | -0.824 |
orno | -0.808 |
Token | ases |
Token ID | 1386 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
hesda | +0.287 |
Arizona | +0.278 |
anyahu | +0.273 |
Catal | +0.264 |
offense | +0.262 |
Neg logit contributions | |
cius | -0.133 |
rapes | -0.068 |
lic | -0.066 |
Comes | -0.064 |
:= | -0.060 |
Token | , |
Token ID | 11 |
Feature activation | -9.42e-03 |
Pos logit contributions | |
cius | +2.601 |
rapes | +1.859 |
lic | +1.858 |
Comes | +1.826 |
:= | +1.777 |
Neg logit contributions | |
hesda | -2.349 |
Arizona | -2.251 |
anyahu | -2.197 |
Catal | -2.088 |
orno | -2.035 |
Token | however |
Token ID | 2158 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
hesda | +0.006 |
Arizona | +0.006 |
anyahu | +0.006 |
Catal | +0.005 |
offense | +0.005 |
Neg logit contributions | |
cius | -0.010 |
rapes | -0.007 |
lic | -0.007 |
Comes | -0.007 |
:= | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
cius | +0.759 |
rapes | +0.535 |
lic | +0.524 |
Comes | +0.518 |
:= | +0.510 |
Neg logit contributions | |
hesda | -0.628 |
Arizona | -0.596 |
anyahu | -0.580 |
offense | -0.550 |
Catal | -0.548 |
Token | that |
Token ID | 326 |
Feature activation | +9.63e-02 |
Pos logit contributions | |
cius | +0.013 |
rapes | +0.009 |
lic | +0.009 |
Comes | +0.009 |
:= | +0.009 |
Neg logit contributions | |
hesda | -0.012 |
Arizona | -0.011 |
anyahu | -0.011 |
Catal | -0.011 |
orno | -0.010 |
Token | what |
Token ID | 644 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
cius | +0.086 |
rapes | +0.060 |
lic | +0.059 |
Comes | +0.059 |
:= | +0.057 |
Neg logit contributions | |
hesda | -0.078 |
Arizona | -0.074 |
anyahu | -0.072 |
Catal | -0.069 |
orno | -0.067 |
Token | 2011 |
Token ID | 2813 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
cius | +0.443 |
rapes | +0.311 |
lic | +0.304 |
Comes | +0.303 |
:= | +0.295 |
Neg logit contributions | |
hesda | -0.449 |
Arizona | -0.420 |
anyahu | -0.417 |
Catal | -0.392 |
orno | -0.391 |
Token | United |
Token ID | 1578 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
cius | +0.480 |
rapes | +0.334 |
lic | +0.330 |
Comes | +0.326 |
:= | +0.319 |
Neg logit contributions | |
hesda | -0.456 |
Arizona | -0.427 |
anyahu | -0.423 |
Catal | -0.397 |
orno | -0.394 |
Token | States |
Token ID | 1829 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
cius | +0.264 |
rapes | +0.185 |
lic | +0.179 |
:= | +0.177 |
Comes | +0.177 |
Neg logit contributions | |
hesda | -0.232 |
Arizona | -0.222 |
anyahu | -0.214 |
Catal | -0.204 |
offense | -0.203 |
Token | 6 |
Token ID | 718 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
hesda | +0.150 |
anyahu | +0.139 |
Arizona | +0.139 |
Catal | +0.128 |
orno | +0.127 |
Neg logit contributions | |
cius | -0.196 |
rapes | -0.144 |
lic | -0.142 |
Comes | -0.141 |
:= | -0.138 |
Token | 12 |
Token ID | 1065 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
cius | +0.541 |
rapes | +0.380 |
lic | +0.372 |
Comes | +0.368 |
:= | +0.362 |
Neg logit contributions | |
hesda | -0.493 |
Arizona | -0.463 |
anyahu | -0.456 |
Catal | -0.431 |
offense | -0.426 |
Token | Posts |
Token ID | 12043 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
cius | +0.722 |
rapes | +0.474 |
Comes | +0.463 |
lic | +0.462 |
:= | +0.452 |
Neg logit contributions | |
hesda | -0.938 |
Arizona | -0.876 |
anyahu | -0.874 |
orno | -0.827 |
Catal | -0.826 |
Token | # |
Token ID | 1303 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
cius | +2.751 |
rapes | +1.964 |
lic | +1.927 |
Comes | +1.906 |
:= | +1.879 |
Neg logit contributions | |
hesda | -2.189 |
Arizona | -2.074 |
anyahu | -2.012 |
Catal | -1.908 |
offense | -1.884 |
Token | 17 |
Token ID | 1558 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
hesda | +0.389 |
Arizona | +0.360 |
anyahu | +0.358 |
offense | +0.332 |
Catal | +0.330 |
Neg logit contributions | |
cius | -0.520 |
lic | -0.377 |
rapes | -0.377 |
:= | -0.368 |
Comes | -0.368 |
Token | Good |
Token ID | 4599 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
cius | +0.354 |
rapes | +0.240 |
lic | +0.236 |
Comes | +0.235 |
:= | +0.228 |
Neg logit contributions | |
hesda | -0.364 |
Arizona | -0.348 |
anyahu | -0.340 |
Catal | -0.325 |
orno | -0.318 |
Token | to |
Token ID | 284 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
cius | +0.506 |
rapes | +0.344 |
lic | +0.336 |
Comes | +0.333 |
:= | +0.327 |
Neg logit contributions | |
hesda | -0.506 |
Arizona | -0.485 |
anyahu | -0.470 |
Catal | -0.452 |
orno | -0.442 |
Token | hear |
Token ID | 3285 |
Feature activation | +9.81e-02 |
Pos logit contributions | |
cius | +0.450 |
rapes | +0.325 |
Comes | +0.317 |
lic | +0.317 |
:= | +0.310 |
Neg logit contributions | |
hesda | -0.349 |
Arizona | -0.329 |
anyahu | -0.322 |
Catal | -0.305 |
orno | -0.300 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
cius | +0.371 |
rapes | +0.261 |
lic | +0.258 |
Comes | +0.255 |
:= | +0.249 |
Neg logit contributions | |
hesda | -0.391 |
anyahu | -0.363 |
Arizona | -0.361 |
Catal | -0.339 |
orno | -0.338 |
Token | United |
Token ID | 1578 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
cius | +0.188 |
rapes | +0.131 |
lic | +0.129 |
Comes | +0.128 |
:= | +0.125 |
Neg logit contributions | |
hesda | -0.183 |
Arizona | -0.171 |
anyahu | -0.170 |
Catal | -0.159 |
orno | -0.158 |
Token | States |
Token ID | 1829 |
Feature activation | -9.59e-02 |
Pos logit contributions | |
cius | +0.314 |
rapes | +0.216 |
lic | +0.210 |
:= | +0.207 |
Comes | +0.207 |
Neg logit contributions | |
hesda | -0.292 |
Arizona | -0.280 |
anyahu | -0.270 |
Catal | -0.258 |
offense | -0.256 |
Token | 5 |
Token ID | 642 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
hesda | +0.071 |
anyahu | +0.066 |
Arizona | +0.066 |
Catal | +0.061 |
orno | +0.060 |
Neg logit contributions | |
cius | -0.092 |
rapes | -0.067 |
lic | -0.067 |
Comes | -0.066 |
:= | -0.065 |
Token | 667 |
Token ID | 28933 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
cius | +0.434 |
rapes | +0.303 |
lic | +0.297 |
Comes | +0.293 |
:= | +0.288 |
Neg logit contributions | |
hesda | -0.405 |
Arizona | -0.382 |
anyahu | -0.375 |
Catal | -0.356 |
offense | -0.351 |
Token | Posts |
Token ID | 12043 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
cius | +0.485 |
rapes | +0.314 |
lic | +0.307 |
Comes | +0.306 |
:= | +0.299 |
Neg logit contributions | |
hesda | -0.647 |
Arizona | -0.610 |
anyahu | -0.605 |
Catal | -0.576 |
orno | -0.572 |
Token | # |
Token ID | 1303 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
cius | +2.712 |
rapes | +1.926 |
lic | +1.892 |
Comes | +1.874 |
:= | +1.845 |
Neg logit contributions | |
hesda | -2.216 |
Arizona | -2.099 |
anyahu | -2.039 |
Catal | -1.935 |
offense | -1.906 |
Token | 12 |
Token ID | 1065 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
hesda | +0.737 |
Arizona | +0.688 |
anyahu | +0.685 |
offense | +0.643 |
Catal | +0.643 |
Neg logit contributions | |
cius | -0.769 |
rapes | -0.534 |
lic | -0.528 |
Comes | -0.519 |
:= | -0.516 |
Token | I |
Token ID | 314 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
cius | +0.835 |
rapes | +0.566 |
lic | +0.554 |
Comes | +0.553 |
:= | +0.538 |
Neg logit contributions | |
hesda | -0.875 |
Arizona | -0.835 |
anyahu | -0.820 |
Catal | -0.782 |
orno | -0.765 |
Token | 'm |
Token ID | 1101 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
cius | +0.655 |
rapes | +0.457 |
lic | +0.453 |
Comes | +0.440 |
:= | +0.436 |
Neg logit contributions | |
hesda | -0.581 |
Arizona | -0.544 |
anyahu | -0.533 |
Catal | -0.510 |
orno | -0.498 |
Token | glad |
Token ID | 9675 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
cius | +0.238 |
rapes | +0.170 |
lic | +0.167 |
Comes | +0.164 |
:= | +0.162 |
Neg logit contributions | |
hesda | -0.195 |
Arizona | -0.184 |
anyahu | -0.180 |
Catal | -0.171 |
orno | -0.166 |
Token | upgrades |
Token ID | 16608 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
cius | +0.243 |
rapes | +0.177 |
lic | +0.173 |
Comes | +0.171 |
:= | +0.168 |
Neg logit contributions | |
hesda | -0.185 |
Arizona | -0.175 |
anyahu | -0.170 |
Catal | -0.161 |
orno | -0.157 |
Token | . |
Token ID | 13 |
Feature activation | -8.00e-02 |
Pos logit contributions | |
cius | +0.755 |
rapes | +0.513 |
lic | +0.499 |
Comes | +0.493 |
:= | +0.485 |
Neg logit contributions | |
hesda | -0.795 |
Arizona | -0.759 |
anyahu | -0.744 |
Catal | -0.705 |
orno | -0.697 |
Token | Select |
Token ID | 9683 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
hesda | +0.068 |
Arizona | +0.064 |
anyahu | +0.063 |
Catal | +0.059 |
orno | +0.059 |
Neg logit contributions | |
cius | -0.068 |
rapes | -0.047 |
Comes | -0.046 |
lic | -0.046 |
:= | -0.045 |
Token | ive |
Token ID | 425 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
hesda | +0.711 |
Arizona | +0.671 |
anyahu | +0.657 |
Catal | +0.616 |
offense | +0.606 |
Neg logit contributions | |
cius | -0.934 |
rapes | -0.676 |
lic | -0.665 |
Comes | -0.657 |
:= | -0.646 |
Token | cataly |
Token ID | 36745 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
hesda | +0.220 |
Arizona | +0.208 |
anyahu | +0.203 |
Catal | +0.191 |
offense | +0.187 |
Neg logit contributions | |
cius | -0.299 |
rapes | -0.217 |
lic | -0.213 |
Comes | -0.211 |
:= | -0.208 |
Token | tic |
Token ID | 13370 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
cius | +0.302 |
rapes | +0.196 |
lic | +0.194 |
Comes | +0.188 |
:= | +0.186 |
Neg logit contributions | |
hesda | -0.357 |
Arizona | -0.342 |
anyahu | -0.334 |
Catal | -0.319 |
offense | -0.318 |
Token | reduction |
Token ID | 7741 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
cius | +2.655 |
rapes | +1.989 |
lic | +1.934 |
Comes | +1.868 |
:= | +1.866 |
Neg logit contributions | |
hesda | -2.164 |
Arizona | -2.050 |
anyahu | -2.012 |
orno | -1.874 |
Catal | -1.862 |
Token | systems |
Token ID | 3341 |
Feature activation | +4.57e-02 |
Pos logit contributions | |
cius | +0.605 |
rapes | +0.419 |
lic | +0.405 |
Comes | +0.402 |
:= | +0.397 |
Neg logit contributions | |
hesda | -0.616 |
Arizona | -0.589 |
anyahu | -0.576 |
Catal | -0.545 |
orno | -0.539 |
Token | were |
Token ID | 547 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
cius | +0.041 |
rapes | +0.028 |
lic | +0.028 |
Comes | +0.027 |
:= | +0.027 |
Neg logit contributions | |
hesda | -0.037 |
Arizona | -0.035 |
anyahu | -0.035 |
Catal | -0.033 |
orno | -0.032 |
Token | installed |
Token ID | 6589 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
cius | +0.210 |
rapes | +0.144 |
lic | +0.141 |
Comes | +0.139 |
:= | +0.138 |
Neg logit contributions | |
hesda | -0.215 |
Arizona | -0.203 |
anyahu | -0.200 |
Catal | -0.189 |
orno | -0.187 |
Token | to |
Token ID | 284 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
cius | +1.063 |
rapes | +0.723 |
lic | +0.701 |
Comes | +0.694 |
:= | +0.683 |
Neg logit contributions | |
hesda | -1.155 |
Arizona | -1.104 |
anyahu | -1.089 |
Catal | -1.027 |
orno | -1.020 |
Token | things |
Token ID | 1243 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
hesda | +0.529 |
Arizona | +0.506 |
anyahu | +0.493 |
Catal | +0.470 |
orno | +0.465 |
Neg logit contributions | |
cius | -0.483 |
rapes | -0.325 |
lic | -0.316 |
Comes | -0.311 |
:= | -0.307 |
Token | : |
Token ID | 25 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
cius | +0.198 |
rapes | +0.137 |
lic | +0.134 |
Comes | +0.132 |
:= | +0.130 |
Neg logit contributions | |
hesda | -0.191 |
Arizona | -0.182 |
anyahu | -0.178 |
Catal | -0.169 |
offense | -0.167 |
Token |
|
Token ID | 198 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
hesda | +0.278 |
Arizona | +0.264 |
anyahu | +0.257 |
Catal | +0.245 |
offense | +0.243 |
Neg logit contributions | |
cius | -0.300 |
rapes | -0.207 |
lic | -0.203 |
Comes | -0.200 |
:= | -0.197 |
Token |
|
Token ID | 198 |
Feature activation | -4.16e-03 |
Pos logit contributions | |
hesda | +0.160 |
anyahu | +0.148 |
Arizona | +0.148 |
offense | +0.138 |
orno | +0.138 |
Neg logit contributions | |
cius | -0.149 |
rapes | -0.102 |
lic | -0.102 |
Comes | -0.100 |
:= | -0.100 |
Token | Decre |
Token ID | 43198 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
hesda | +0.003 |
Arizona | +0.003 |
anyahu | +0.003 |
offense | +0.003 |
Catal | +0.003 |
Neg logit contributions | |
cius | -0.004 |
rapes | -0.003 |
lic | -0.003 |
Comes | -0.003 |
:= | -0.003 |
Token | ases |
Token ID | 1386 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
cius | +0.670 |
rapes | +0.339 |
lic | +0.337 |
Comes | +0.312 |
:= | +0.302 |
Neg logit contributions | |
hesda | -1.434 |
Arizona | -1.386 |
anyahu | -1.361 |
Catal | -1.314 |
offense | -1.314 |
Token | blood |
Token ID | 2910 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
cius | +2.596 |
rapes | +1.852 |
lic | +1.800 |
Comes | +1.776 |
:= | +1.775 |
Neg logit contributions | |
hesda | -2.231 |
Arizona | -2.127 |
anyahu | -2.074 |
Catal | -1.939 |
orno | -1.923 |
Token | glucose |
Token ID | 15701 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
cius | +0.651 |
rapes | +0.436 |
lic | +0.427 |
Comes | +0.418 |
:= | +0.414 |
Neg logit contributions | |
hesda | -0.718 |
Arizona | -0.691 |
anyahu | -0.673 |
Catal | -0.641 |
orno | -0.634 |
Token | . |
Token ID | 13 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
cius | +0.407 |
rapes | +0.272 |
lic | +0.264 |
Comes | +0.260 |
:= | +0.260 |
Neg logit contributions | |
hesda | -0.476 |
Arizona | -0.454 |
anyahu | -0.449 |
Catal | -0.425 |
orno | -0.420 |
Token |
|
Token ID | 198 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
cius | +0.323 |
rapes | +0.220 |
lic | +0.216 |
Comes | +0.215 |
:= | +0.209 |
Neg logit contributions | |
hesda | -0.331 |
Arizona | -0.314 |
anyahu | -0.309 |
Catal | -0.291 |
offense | -0.289 |
Token |
|
Token ID | 198 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
cius | +0.295 |
lic | +0.202 |
rapes | +0.201 |
:= | +0.198 |
Comes | +0.198 |
Neg logit contributions | |
hesda | -0.342 |
anyahu | -0.318 |
Arizona | -0.312 |
offense | -0.294 |
orno | -0.293 |
Token | who |
Token ID | 508 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
hesda | +0.361 |
Arizona | +0.343 |
anyahu | +0.334 |
Catal | +0.317 |
offense | +0.311 |
Neg logit contributions | |
cius | -0.419 |
rapes | -0.296 |
lic | -0.289 |
Comes | -0.287 |
:= | -0.282 |
Token | have |
Token ID | 423 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
hesda | +0.140 |
Arizona | +0.132 |
anyahu | +0.129 |
Catal | +0.122 |
offense | +0.120 |
Neg logit contributions | |
cius | -0.163 |
rapes | -0.115 |
lic | -0.113 |
Comes | -0.111 |
:= | -0.110 |
Token | a |
Token ID | 257 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
hesda | +0.102 |
Arizona | +0.097 |
anyahu | +0.094 |
Catal | +0.089 |
offense | +0.088 |
Neg logit contributions | |
cius | -0.117 |
rapes | -0.083 |
lic | -0.081 |
Comes | -0.080 |
:= | -0.079 |
Token | Lock |
Token ID | 13656 |
Feature activation | +9.11e-01 |
Pos logit contributions | |
cius | +0.128 |
rapes | +0.091 |
lic | +0.090 |
Comes | +0.088 |
:= | +0.087 |
Neg logit contributions | |
hesda | -0.108 |
Arizona | -0.103 |
anyahu | -0.100 |
Catal | -0.095 |
offense | -0.093 |
Token | out |
Token ID | 503 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
cius | +0.812 |
rapes | +0.558 |
lic | +0.550 |
Comes | +0.548 |
:= | +0.533 |
Neg logit contributions | |
hesda | -0.745 |
Arizona | -0.706 |
anyahu | -0.691 |
Catal | -0.649 |
offense | -0.645 |
Token | sol |
Token ID | 1540 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
cius | +0.389 |
rapes | +0.268 |
lic | +0.263 |
Comes | +0.259 |
:= | +0.255 |
Neg logit contributions | |
hesda | -0.372 |
Arizona | -0.354 |
anyahu | -0.345 |
Catal | -0.328 |
offense | -0.324 |
Token | en |
Token ID | 268 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
cius | +2.074 |
rapes | +1.280 |
lic | +1.256 |
:= | +1.222 |
Comes | +1.220 |
Neg logit contributions | |
hesda | -2.751 |
Arizona | -2.644 |
anyahu | -2.589 |
Catal | -2.495 |
offense | -2.448 |
Token | oid |
Token ID | 1868 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
cius | +0.702 |
rapes | +0.441 |
lic | +0.433 |
Comes | +0.422 |
:= | +0.415 |
Neg logit contributions | |
hesda | -0.919 |
Arizona | -0.880 |
anyahu | -0.861 |
Catal | -0.826 |
offense | -0.818 |
Token | which |
Token ID | 543 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
cius | +1.046 |
rapes | +0.716 |
lic | +0.703 |
Comes | +0.693 |
:= | +0.682 |
Neg logit contributions | |
hesda | -1.016 |
Arizona | -0.971 |
anyahu | -0.945 |
Catal | -0.901 |
offense | -0.885 |
Token | is |
Token ID | 318 |
Feature activation | -6.91e-02 |
Pos logit contributions | |
hesda | +0.097 |
Arizona | +0.092 |
anyahu | +0.090 |
Catal | +0.086 |
offense | +0.084 |
Neg logit contributions | |
cius | -0.105 |
rapes | -0.074 |
lic | -0.072 |
Comes | -0.071 |
:= | -0.070 |
Token | on |
Token ID | 319 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
hesda | +0.054 |
Arizona | +0.051 |
anyahu | +0.050 |
Catal | +0.047 |
offense | +0.046 |
Neg logit contributions | |
cius | -0.064 |
rapes | -0.045 |
lic | -0.045 |
Comes | -0.044 |
:= | -0.043 |
Token | large |
Token ID | 1588 |
Feature activation | +4.68e-02 |
Pos logit contributions | |
cius | +0.360 |
rapes | +0.254 |
lic | +0.249 |
Comes | +0.247 |
:= | +0.241 |
Neg logit contributions | |
hesda | -0.311 |
Arizona | -0.295 |
anyahu | -0.287 |
Catal | -0.271 |
offense | -0.267 |
Token | pull |
Token ID | 2834 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
cius | +0.042 |
rapes | +0.029 |
lic | +0.029 |
Comes | +0.028 |
:= | +0.028 |
Neg logit contributions | |
hesda | -0.038 |
Arizona | -0.036 |
anyahu | -0.035 |
Catal | -0.033 |
orno | -0.033 |
Token | tab |
Token ID | 7400 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
hesda | +0.214 |
Arizona | +0.204 |
anyahu | +0.198 |
Catal | +0.188 |
offense | +0.186 |
Neg logit contributions | |
cius | -0.240 |
rapes | -0.168 |
lic | -0.165 |
Comes | -0.163 |
:= | -0.160 |
Token | on |
Token ID | 319 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
cius | +0.770 |
rapes | +0.516 |
lic | +0.508 |
Comes | +0.499 |
:= | +0.490 |
Neg logit contributions | |
hesda | -0.810 |
Arizona | -0.777 |
anyahu | -0.760 |
Catal | -0.720 |
offense | -0.711 |
Token | the |
Token ID | 262 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
cius | +0.895 |
rapes | +0.625 |
lic | +0.611 |
Comes | +0.607 |
:= | +0.592 |
Neg logit contributions | |
hesda | -0.820 |
Arizona | -0.779 |
anyahu | -0.761 |
Catal | -0.717 |
orno | -0.708 |
Token | zipper |
Token ID | 48992 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
cius | +0.356 |
rapes | +0.254 |
lic | +0.246 |
Comes | +0.246 |
:= | +0.240 |
Neg logit contributions | |
hesda | -0.313 |
Arizona | -0.296 |
anyahu | -0.290 |
Catal | -0.273 |
orno | -0.268 |
Token | for |
Token ID | 329 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
cius | +2.264 |
rapes | +1.557 |
lic | +1.506 |
Comes | +1.486 |
:= | +1.473 |
Neg logit contributions | |
hesda | -2.442 |
Arizona | -2.318 |
anyahu | -2.302 |
Catal | -2.170 |
orno | -2.103 |
Token | easy |
Token ID | 2562 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
cius | +0.465 |
rapes | +0.342 |
lic | +0.335 |
Comes | +0.333 |
:= | +0.325 |
Neg logit contributions | |
hesda | -0.350 |
Arizona | -0.329 |
anyahu | -0.323 |
Catal | -0.302 |
orno | -0.295 |
Token | use |
Token ID | 779 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
hesda | +0.221 |
Arizona | +0.208 |
anyahu | +0.204 |
Catal | +0.191 |
orno | +0.187 |
Neg logit contributions | |
cius | -0.279 |
rapes | -0.202 |
lic | -0.197 |
Comes | -0.196 |
:= | -0.192 |
Token | with |
Token ID | 351 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
hesda | +0.741 |
Arizona | +0.708 |
anyahu | +0.690 |
Catal | +0.660 |
offense | +0.654 |
Neg logit contributions | |
cius | -0.688 |
rapes | -0.461 |
lic | -0.450 |
Comes | -0.443 |
:= | -0.436 |
Token | longer |
Token ID | 2392 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
cius | +0.158 |
rapes | +0.112 |
lic | +0.110 |
Comes | +0.109 |
:= | +0.107 |
Neg logit contributions | |
hesda | -0.136 |
Arizona | -0.128 |
anyahu | -0.126 |
Catal | -0.117 |
orno | -0.116 |
Token | . |
Token ID | 13 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
hesda | +0.334 |
Arizona | +0.319 |
anyahu | +0.310 |
Catal | +0.297 |
offense | +0.294 |
Neg logit contributions | |
cius | -0.318 |
rapes | -0.215 |
lic | -0.209 |
Comes | -0.206 |
:= | -0.203 |
Token | Rel |
Token ID | 4718 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
hesda | +0.171 |
Arizona | +0.159 |
anyahu | +0.159 |
offense | +0.149 |
Catal | +0.148 |
Neg logit contributions | |
cius | -0.164 |
rapes | -0.113 |
lic | -0.112 |
Comes | -0.111 |
:= | -0.107 |
Token | ieved |
Token ID | 39591 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
hesda | +0.408 |
Arizona | +0.387 |
anyahu | +0.375 |
Catal | +0.356 |
offense | +0.352 |
Neg logit contributions | |
cius | -0.505 |
rapes | -0.359 |
lic | -0.353 |
Comes | -0.348 |
:= | -0.343 |
Token | , |
Token ID | 11 |
Feature activation | -5.37e-02 |
Pos logit contributions | |
cius | +0.361 |
rapes | +0.248 |
lic | +0.243 |
Comes | +0.239 |
:= | +0.235 |
Neg logit contributions | |
hesda | -0.352 |
Arizona | -0.336 |
anyahu | -0.327 |
Catal | -0.311 |
offense | -0.308 |
Token | Par |
Token ID | 10044 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
hesda | +0.037 |
Arizona | +0.035 |
anyahu | +0.034 |
Catal | +0.032 |
offense | +0.031 |
Neg logit contributions | |
cius | -0.054 |
rapes | -0.040 |
lic | -0.039 |
Comes | -0.039 |
:= | -0.038 |
Token | amount |
Token ID | 17287 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
hesda | +0.956 |
Arizona | +0.914 |
anyahu | +0.887 |
Catal | +0.840 |
offense | +0.826 |
Neg logit contributions | |
cius | -1.317 |
rapes | -0.944 |
lic | -0.941 |
Comes | -0.927 |
:= | -0.910 |
Token | jumped |
Token ID | 11687 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
cius | +2.342 |
rapes | +1.650 |
lic | +1.631 |
Comes | +1.593 |
:= | +1.554 |
Neg logit contributions | |
hesda | -2.272 |
Arizona | -2.135 |
anyahu | -2.086 |
Catal | -1.999 |
orno | -1.954 |
Token | at |
Token ID | 379 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
hesda | +0.430 |
Arizona | +0.410 |
anyahu | +0.399 |
Catal | +0.381 |
offense | +0.377 |
Neg logit contributions | |
cius | -0.433 |
rapes | -0.296 |
lic | -0.289 |
Comes | -0.285 |
:= | -0.280 |
Token | the |
Token ID | 262 |
Feature activation | +8.93e-02 |
Pos logit contributions | |
hesda | +0.031 |
Arizona | +0.029 |
anyahu | +0.028 |
Catal | +0.027 |
offense | +0.027 |
Neg logit contributions | |
cius | -0.035 |
rapes | -0.024 |
lic | -0.024 |
Comes | -0.024 |
:= | -0.023 |
Token | chance |
Token ID | 2863 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
cius | +0.096 |
rapes | +0.073 |
lic | +0.072 |
Comes | +0.071 |
:= | +0.070 |
Neg logit contributions | |
hesda | -0.055 |
Arizona | -0.052 |
anyahu | -0.050 |
Catal | -0.047 |
orno | -0.046 |
Token | to |
Token ID | 284 |
Feature activation | +9.60e-02 |
Pos logit contributions | |
cius | +0.708 |
rapes | +0.479 |
lic | +0.467 |
Comes | +0.461 |
:= | +0.453 |
Neg logit contributions | |
hesda | -0.730 |
Arizona | -0.696 |
anyahu | -0.678 |
Catal | -0.648 |
offense | -0.642 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
cius | +0.372 |
rapes | +0.260 |
lic | +0.257 |
Comes | +0.254 |
:= | +0.248 |
Neg logit contributions | |
hesda | -0.355 |
Arizona | -0.334 |
anyahu | -0.331 |
Catal | -0.311 |
orno | -0.308 |
Token | United |
Token ID | 1578 |
Feature activation | +7.81e-02 |
Pos logit contributions | |
cius | +0.191 |
rapes | +0.134 |
lic | +0.132 |
Comes | +0.130 |
:= | +0.128 |
Neg logit contributions | |
hesda | -0.177 |
Arizona | -0.165 |
anyahu | -0.164 |
Catal | -0.154 |
offense | -0.153 |
Token | States |
Token ID | 1829 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
cius | +0.066 |
rapes | +0.045 |
lic | +0.044 |
Comes | +0.043 |
:= | +0.042 |
Neg logit contributions | |
hesda | -0.067 |
Arizona | -0.064 |
anyahu | -0.062 |
Catal | -0.060 |
offense | -0.059 |
Token | 3 |
Token ID | 513 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
hesda | +0.215 |
Arizona | +0.199 |
anyahu | +0.199 |
Catal | +0.184 |
orno | +0.182 |
Neg logit contributions | |
cius | -0.287 |
rapes | -0.210 |
lic | -0.207 |
Comes | -0.207 |
:= | -0.202 |
Token | 240 |
Token ID | 16102 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
cius | +0.016 |
rapes | +0.011 |
lic | +0.011 |
Comes | +0.011 |
:= | +0.010 |
Neg logit contributions | |
hesda | -0.016 |
Arizona | -0.016 |
anyahu | -0.015 |
Catal | -0.015 |
offense | -0.014 |
Token | Posts |
Token ID | 12043 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
hesda | +0.040 |
Arizona | +0.038 |
anyahu | +0.038 |
Catal | +0.036 |
offense | +0.036 |
Neg logit contributions | |
cius | -0.034 |
rapes | -0.023 |
lic | -0.022 |
Comes | -0.022 |
:= | -0.021 |
Token | # |
Token ID | 1303 |
Feature activation | -9.68e-01 |
Pos logit contributions | |
cius | +2.455 |
rapes | +1.721 |
lic | +1.693 |
Comes | +1.684 |
:= | +1.644 |
Neg logit contributions | |
hesda | -2.170 |
Arizona | -2.058 |
anyahu | -2.008 |
Catal | -1.911 |
orno | -1.854 |
Token | 10 |
Token ID | 940 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
hesda | +0.779 |
Arizona | +0.729 |
anyahu | +0.719 |
offense | +0.675 |
Catal | +0.674 |
Neg logit contributions | |
cius | -0.870 |
rapes | -0.611 |
lic | -0.604 |
Comes | -0.595 |
:= | -0.587 |
Token | Happy |
Token ID | 14628 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
cius | +0.322 |
rapes | +0.219 |
lic | +0.214 |
Comes | +0.212 |
:= | +0.207 |
Neg logit contributions | |
hesda | -0.333 |
Arizona | -0.318 |
anyahu | -0.310 |
Catal | -0.296 |
offense | -0.291 |
Token | it |
Token ID | 340 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
cius | +1.014 |
rapes | +0.693 |
lic | +0.678 |
Comes | +0.677 |
:= | +0.663 |
Neg logit contributions | |
hesda | -0.979 |
Arizona | -0.935 |
anyahu | -0.910 |
Catal | -0.869 |
orno | -0.855 |
Token | worked |
Token ID | 3111 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
cius | +0.356 |
rapes | +0.237 |
lic | +0.233 |
Comes | +0.231 |
:= | +0.224 |
Neg logit contributions | |
hesda | -0.395 |
Arizona | -0.377 |
anyahu | -0.370 |
Catal | -0.353 |
offense | -0.350 |
Token | // |
Token ID | 3373 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
hesda | +0.753 |
Arizona | +0.716 |
anyahu | +0.709 |
Catal | +0.672 |
orno | +0.669 |
Neg logit contributions | |
cius | -0.521 |
rapes | -0.325 |
:= | -0.324 |
Comes | -0.324 |
lic | -0.319 |
Token | metres |
Token ID | 18985 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
hesda | +0.792 |
Arizona | +0.757 |
anyahu | +0.740 |
Catal | +0.710 |
offense | +0.704 |
Neg logit contributions | |
cius | -0.644 |
rapes | -0.414 |
lic | -0.404 |
Comes | -0.397 |
:= | -0.389 |
Token | _ |
Token ID | 4808 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
hesda | +0.612 |
Arizona | +0.581 |
anyahu | +0.562 |
Catal | +0.539 |
offense | +0.537 |
Neg logit contributions | |
cius | -0.649 |
rapes | -0.447 |
lic | -0.438 |
Comes | -0.427 |
:= | -0.417 |
Token | P |
Token ID | 47 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
cius | +0.518 |
:= | +0.400 |
lic | +0.388 |
rapes | +0.381 |
Comes | +0.378 |
Neg logit contributions | |
hesda | -0.412 |
anyahu | -0.376 |
Arizona | -0.350 |
orno | -0.341 |
offense | -0.341 |
Token | ulse |
Token ID | 9615 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
hesda | +0.964 |
Arizona | +0.914 |
anyahu | +0.897 |
offense | +0.850 |
Catal | +0.844 |
Neg logit contributions | |
cius | -1.043 |
lic | -0.726 |
:= | -0.703 |
rapes | -0.697 |
esian | -0.676 |
Token | Per |
Token ID | 5990 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
hesda | +0.388 |
anyahu | +0.358 |
Arizona | +0.350 |
orno | +0.333 |
offense | +0.331 |
Neg logit contributions | |
cius | -0.408 |
:= | -0.293 |
lic | -0.290 |
Comes | -0.286 |
rapes | -0.286 |
Token | iod |
Token ID | 2101 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
hesda | +2.477 |
Arizona | +2.351 |
anyahu | +2.282 |
Catal | +2.157 |
offense | +2.144 |
Neg logit contributions | |
cius | -3.004 |
lic | -2.109 |
rapes | -2.096 |
:= | -2.049 |
Comes | -2.047 |
Token | ( |
Token ID | 357 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
cius | +0.190 |
rapes | +0.117 |
lic | +0.115 |
Comes | +0.114 |
:= | +0.114 |
Neg logit contributions | |
hesda | -0.285 |
Arizona | -0.274 |
anyahu | -0.269 |
Catal | -0.256 |
orno | -0.254 |
Token | " |
Token ID | 366 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
cius | +0.607 |
rapes | +0.451 |
lic | +0.446 |
Comes | +0.445 |
:= | +0.444 |
Neg logit contributions | |
hesda | -0.400 |
Arizona | -0.379 |
anyahu | -0.365 |
Catal | -0.339 |
orno | -0.333 |
Token | P |
Token ID | 47 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
hesda | +0.121 |
anyahu | +0.110 |
Arizona | +0.103 |
offense | +0.100 |
orno | +0.100 |
Neg logit contributions | |
cius | -0.156 |
:= | -0.117 |
lic | -0.117 |
rapes | -0.114 |
Comes | -0.112 |
Token | ulse |
Token ID | 9615 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
hesda | +0.974 |
Arizona | +0.925 |
anyahu | +0.899 |
offense | +0.850 |
Catal | +0.847 |
Neg logit contributions | |
cius | -1.057 |
lic | -0.728 |
rapes | -0.704 |
:= | -0.699 |
esian | -0.681 |
Token | . |
Token ID | 13 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
cius | +0.282 |
rapes | +0.188 |
lic | +0.186 |
Comes | +0.182 |
:= | +0.179 |
Neg logit contributions | |
hesda | -0.322 |
Arizona | -0.307 |
anyahu | -0.302 |
Catal | -0.286 |
orno | -0.284 |
Token |
|
Token ID | 198 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
hesda | +0.173 |
Arizona | +0.164 |
anyahu | +0.161 |
Catal | +0.152 |
offense | +0.151 |
Neg logit contributions | |
cius | -0.181 |
rapes | -0.125 |
lic | -0.123 |
Comes | -0.121 |
:= | -0.119 |
Token |
|
Token ID | 198 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
hesda | +0.524 |
anyahu | +0.486 |
Arizona | +0.483 |
orno | +0.453 |
offense | +0.453 |
Neg logit contributions | |
cius | -0.482 |
lic | -0.330 |
rapes | -0.329 |
:= | -0.322 |
Comes | -0.320 |
Token | The |
Token ID | 464 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
hesda | +0.493 |
Arizona | +0.457 |
anyahu | +0.453 |
offense | +0.425 |
orno | +0.422 |
Neg logit contributions | |
cius | -0.591 |
rapes | -0.418 |
lic | -0.418 |
Comes | -0.406 |
:= | -0.404 |
Token | Orbital |
Token ID | 45453 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
hesda | +0.295 |
Arizona | +0.277 |
anyahu | +0.272 |
Catal | +0.255 |
orno | +0.251 |
Neg logit contributions | |
cius | -0.395 |
rapes | -0.287 |
lic | -0.284 |
Comes | -0.279 |
:= | -0.274 |
Token | ATK |
Token ID | 24526 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
cius | +0.022 |
rapes | +0.016 |
lic | +0.016 |
Comes | +0.016 |
:= | +0.016 |
Neg logit contributions | |
hesda | -0.014 |
Arizona | -0.013 |
anyahu | -0.012 |
Catal | -0.012 |
orno | -0.011 |
Token | Cy |
Token ID | 5934 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
hesda | +2.306 |
Arizona | +2.186 |
anyahu | +2.108 |
Catal | +2.010 |
offense | +1.997 |
Neg logit contributions | |
cius | -2.987 |
rapes | -2.141 |
lic | -2.092 |
Comes | -2.070 |
:= | -2.052 |
Token | gn |
Token ID | 4593 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
hesda | +1.624 |
Arizona | +1.514 |
anyahu | +1.461 |
Catal | +1.367 |
offense | +1.348 |
Neg logit contributions | |
cius | -2.952 |
rapes | -2.214 |
lic | -2.207 |
Comes | -2.163 |
:= | -2.143 |
Token | us |
Token ID | 385 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
cius | +1.190 |
lic | +0.843 |
rapes | +0.834 |
Comes | +0.816 |
esian | +0.816 |
Neg logit contributions | |
hesda | -0.963 |
Arizona | -0.912 |
anyahu | -0.891 |
Catal | -0.854 |
offense | -0.830 |
Token | , |
Token ID | 11 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
hesda | +0.807 |
Arizona | +0.760 |
anyahu | +0.738 |
Catal | +0.694 |
offense | +0.679 |
Neg logit contributions | |
cius | -1.160 |
rapes | -0.847 |
lic | -0.834 |
Comes | -0.827 |
:= | -0.813 |
Token | on |
Token ID | 319 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
hesda | +0.451 |
Arizona | +0.426 |
anyahu | +0.416 |
Catal | +0.393 |
offense | +0.386 |
Neg logit contributions | |
cius | -0.537 |
rapes | -0.381 |
lic | -0.375 |
Comes | -0.370 |
:= | -0.363 |
Token | y |
Token ID | 88 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
cius | +0.092 |
rapes | +0.061 |
lic | +0.059 |
Comes | +0.058 |
:= | +0.057 |
Neg logit contributions | |
hesda | -0.103 |
Arizona | -0.098 |
anyahu | -0.096 |
Catal | -0.092 |
offense | -0.091 |
Token | / |
Token ID | 1220 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
hesda | +0.832 |
Arizona | +0.797 |
anyahu | +0.771 |
Catal | +0.741 |
offense | +0.732 |
Neg logit contributions | |
cius | -0.855 |
rapes | -0.588 |
lic | -0.570 |
Comes | -0.566 |
:= | -0.550 |
Token | _ |
Token ID | 4808 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
hesda | +0.365 |
Arizona | +0.347 |
anyahu | +0.336 |
Catal | +0.320 |
offense | +0.319 |
Neg logit contributions | |
cius | -0.422 |
rapes | -0.296 |
lic | -0.289 |
Comes | -0.285 |
:= | -0.280 |
Token | P |
Token ID | 47 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
cius | +0.505 |
rapes | +0.376 |
lic | +0.369 |
Comes | +0.366 |
:= | +0.361 |
Neg logit contributions | |
hesda | -0.307 |
Arizona | -0.289 |
anyahu | -0.277 |
Catal | -0.261 |
offense | -0.257 |
Token | ulse |
Token ID | 9615 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
hesda | +0.925 |
Arizona | +0.873 |
anyahu | +0.855 |
offense | +0.811 |
Catal | +0.805 |
Neg logit contributions | |
cius | -1.003 |
lic | -0.694 |
:= | -0.671 |
rapes | -0.669 |
esian | -0.648 |
Token | Per |
Token ID | 5990 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
hesda | +0.048 |
anyahu | +0.045 |
Arizona | +0.045 |
orno | +0.042 |
offense | +0.042 |
Neg logit contributions | |
cius | -0.050 |
lic | -0.035 |
:= | -0.035 |
rapes | -0.035 |
Comes | -0.034 |
Token | iod |
Token ID | 2101 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
hesda | +2.419 |
Arizona | +2.295 |
anyahu | +2.230 |
Catal | +2.105 |
offense | +2.092 |
Neg logit contributions | |
cius | -2.898 |
lic | -2.029 |
rapes | -2.003 |
:= | -1.967 |
Comes | -1.961 |
Token | * |
Token ID | 1635 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
cius | +0.377 |
rapes | +0.254 |
lic | +0.247 |
Comes | +0.243 |
:= | +0.237 |
Neg logit contributions | |
hesda | -0.399 |
Arizona | -0.381 |
anyahu | -0.371 |
Catal | -0.356 |
offense | -0.353 |
Token | TA |
Token ID | 21664 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
hesda | +1.191 |
Arizona | +1.129 |
anyahu | +1.093 |
Catal | +1.043 |
offense | +1.040 |
Neg logit contributions | |
cius | -1.401 |
rapes | -0.989 |
lic | -0.964 |
Comes | -0.953 |
:= | -0.934 |
Token | U |
Token ID | 52 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
hesda | +0.649 |
anyahu | +0.602 |
Arizona | +0.600 |
orno | +0.554 |
Catal | +0.554 |
Neg logit contributions | |
cius | -0.813 |
rapes | -0.581 |
lic | -0.576 |
:= | -0.571 |
Comes | -0.565 |
Token | ) |
Token ID | 8 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
cius | +0.595 |
rapes | +0.397 |
lic | +0.387 |
Comes | +0.381 |
:= | +0.374 |
Neg logit contributions | |
hesda | -0.650 |
Arizona | -0.622 |
anyahu | -0.605 |
Catal | -0.580 |
offense | -0.574 |
Token | // |
Token ID | 3373 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
hesda | +0.567 |
Arizona | +0.539 |
anyahu | +0.527 |
Catal | +0.501 |
offense | +0.493 |
Neg logit contributions | |
cius | -0.602 |
rapes | -0.416 |
lic | -0.407 |
Comes | -0.403 |
:= | -0.398 |
Token | metres |
Token ID | 18985 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
hesda | +0.869 |
Arizona | +0.827 |
anyahu | +0.806 |
Catal | +0.767 |
offense | +0.759 |
Neg logit contributions | |
cius | -0.907 |
rapes | -0.624 |
lic | -0.611 |
Comes | -0.603 |
:= | -0.594 |
Token | _ |
Token ID | 4808 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
hesda | +0.467 |
Arizona | +0.446 |
anyahu | +0.435 |
Catal | +0.414 |
offense | +0.407 |
Neg logit contributions | |
cius | -0.488 |
rapes | -0.337 |
lic | -0.329 |
Comes | -0.326 |
:= | -0.323 |
Token | P |
Token ID | 47 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
cius | +0.365 |
rapes | +0.272 |
lic | +0.268 |
Comes | +0.266 |
:= | +0.263 |
Neg logit contributions | |
hesda | -0.212 |
Arizona | -0.199 |
anyahu | -0.192 |
Catal | -0.179 |
offense | -0.177 |
Token | ulse |
Token ID | 9615 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
hesda | +0.827 |
Arizona | +0.785 |
anyahu | +0.767 |
offense | +0.729 |
Catal | +0.722 |
Neg logit contributions | |
cius | -0.906 |
lic | -0.633 |
rapes | -0.608 |
:= | -0.608 |
Comes | -0.588 |
Token | Per |
Token ID | 5990 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
hesda | +0.228 |
Arizona | +0.217 |
anyahu | +0.211 |
Catal | +0.201 |
offense | +0.199 |
Neg logit contributions | |
cius | -0.258 |
rapes | -0.181 |
lic | -0.177 |
Comes | -0.175 |
:= | -0.172 |
Token | iod |
Token ID | 2101 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
hesda | +2.329 |
Arizona | +2.211 |
anyahu | +2.147 |
Catal | +2.024 |
offense | +2.018 |
Neg logit contributions | |
cius | -2.811 |
lic | -1.971 |
rapes | -1.954 |
:= | -1.914 |
Comes | -1.909 |
Token | (" |
Token ID | 5855 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
cius | +0.450 |
rapes | +0.299 |
lic | +0.292 |
Comes | +0.288 |
:= | +0.285 |
Neg logit contributions | |
hesda | -0.503 |
Arizona | -0.481 |
anyahu | -0.469 |
Catal | -0.448 |
offense | -0.443 |
Token | P |
Token ID | 47 |
Feature activation | -9.33e-01 |
Pos logit contributions | |
cius | +0.195 |
rapes | +0.142 |
lic | +0.140 |
Comes | +0.138 |
:= | +0.137 |
Neg logit contributions | |
hesda | -0.134 |
Arizona | -0.126 |
anyahu | -0.123 |
Catal | -0.115 |
offense | -0.114 |
Token | ulse |
Token ID | 9615 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
hesda | +0.762 |
Arizona | +0.725 |
anyahu | +0.703 |
offense | +0.667 |
Catal | +0.663 |
Neg logit contributions | |
cius | -0.842 |
lic | -0.583 |
rapes | -0.564 |
:= | -0.559 |
Comes | -0.547 |
Token | period |
Token ID | 2278 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
hesda | +0.271 |
Arizona | +0.257 |
anyahu | +0.250 |
Catal | +0.237 |
offense | +0.236 |
Neg logit contributions | |
cius | -0.316 |
rapes | -0.222 |
lic | -0.218 |
Comes | -0.215 |
:= | -0.211 |
Token | version |
Token ID | 2196 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
hesda | +1.132 |
Arizona | +1.074 |
anyahu | +1.045 |
Catal | +0.998 |
offense | +0.995 |
Neg logit contributions | |
cius | -1.243 |
rapes | -0.860 |
lic | -0.843 |
Comes | -0.832 |
:= | -0.816 |
Token | , |
Token ID | 837 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
cius | +0.101 |
rapes | +0.070 |
lic | +0.069 |
Comes | +0.068 |
:= | +0.067 |
Neg logit contributions | |
hesda | -0.096 |
Arizona | -0.092 |
anyahu | -0.089 |
Catal | -0.085 |
offense | -0.084 |
Token | C |
Token ID | 327 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
hesda | +0.292 |
Arizona | +0.279 |
anyahu | +0.272 |
Catal | +0.261 |
offense | +0.259 |
Neg logit contributions | |
cius | -0.250 |
rapes | -0.164 |
lic | -0.160 |
Comes | -0.157 |
:= | -0.154 |
Token | OUNT |
Token ID | 28270 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
hesda | +0.299 |
Arizona | +0.285 |
anyahu | +0.276 |
Catal | +0.264 |
offense | +0.260 |
Neg logit contributions | |
cius | -0.339 |
rapes | -0.237 |
lic | -0.230 |
Comes | -0.229 |
:= | -0.222 |
Token | ( |
Token ID | 357 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
hesda | +1.454 |
Arizona | +1.392 |
anyahu | +1.337 |
Catal | +1.297 |
offense | +1.290 |
Neg logit contributions | |
cius | -1.519 |
rapes | -1.026 |
lic | -1.014 |
Comes | -0.995 |
esian | -0.970 |
Token | * |
Token ID | 1635 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
cius | +0.034 |
rapes | +0.024 |
lic | +0.024 |
Comes | +0.023 |
:= | +0.023 |
Neg logit contributions | |
hesda | -0.029 |
Arizona | -0.028 |
anyahu | -0.027 |
Catal | -0.026 |
offense | -0.025 |
Token | ) |
Token ID | 1267 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
hesda | +2.369 |
Arizona | +2.231 |
anyahu | +2.170 |
offense | +2.091 |
Catal | +2.089 |
Neg logit contributions | |
cius | -2.656 |
rapes | -1.820 |
lic | -1.791 |
Comes | -1.774 |
esian | -1.729 |
Token | AS |
Token ID | 7054 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
hesda | +0.501 |
Arizona | +0.479 |
anyahu | +0.466 |
Catal | +0.448 |
offense | +0.445 |
Neg logit contributions | |
cius | -0.436 |
rapes | -0.285 |
lic | -0.279 |
Comes | -0.274 |
:= | -0.266 |
Token | count |
Token ID | 954 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
hesda | +1.001 |
Arizona | +0.950 |
anyahu | +0.924 |
Catal | +0.884 |
offense | +0.881 |
Neg logit contributions | |
cius | -1.098 |
rapes | -0.759 |
lic | -0.745 |
Comes | -0.735 |
:= | -0.720 |
Token | FROM |
Token ID | 16034 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
hesda | +0.583 |
Arizona | +0.556 |
anyahu | +0.539 |
Catal | +0.518 |
offense | +0.513 |
Neg logit contributions | |
cius | -0.574 |
rapes | -0.388 |
lic | -0.379 |
Comes | -0.374 |
:= | -0.365 |
Token | ( |
Token ID | 357 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
hesda | +0.797 |
Arizona | +0.760 |
anyahu | +0.740 |
Catal | +0.708 |
offense | +0.704 |
Neg logit contributions | |
cius | -0.761 |
rapes | -0.510 |
lic | -0.499 |
Comes | -0.492 |
:= | -0.483 |
Token | levels |
Token ID | 2974 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
cius | +0.369 |
rapes | +0.257 |
lic | +0.254 |
Comes | +0.250 |
:= | +0.241 |
Neg logit contributions | |
hesda | -0.352 |
Arizona | -0.337 |
anyahu | -0.327 |
Catal | -0.312 |
orno | -0.304 |
Token | of |
Token ID | 286 |
Feature activation | +8.04e-02 |
Pos logit contributions | |
hesda | +0.026 |
Arizona | +0.025 |
anyahu | +0.024 |
Catal | +0.023 |
offense | +0.022 |
Neg logit contributions | |
cius | -0.023 |
rapes | -0.016 |
lic | -0.015 |
Comes | -0.015 |
:= | -0.015 |
Token | speed |
Token ID | 2866 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
cius | +0.077 |
rapes | +0.056 |
lic | +0.055 |
Comes | +0.055 |
:= | +0.053 |
Neg logit contributions | |
hesda | -0.060 |
Arizona | -0.057 |
anyahu | -0.056 |
Catal | -0.052 |
orno | -0.050 |
Token | ) |
Token ID | 8 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
cius | +0.717 |
rapes | +0.480 |
lic | +0.473 |
Comes | +0.461 |
:= | +0.452 |
Neg logit contributions | |
hesda | -0.781 |
Arizona | -0.758 |
anyahu | -0.738 |
Catal | -0.709 |
orno | -0.691 |
Token | and |
Token ID | 290 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
cius | +0.009 |
rapes | +0.006 |
lic | +0.006 |
Comes | +0.006 |
:= | +0.006 |
Neg logit contributions | |
hesda | -0.008 |
Arizona | -0.008 |
anyahu | -0.008 |
Catal | -0.007 |
offense | -0.007 |
Token | Rally |
Token ID | 27752 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
cius | +0.039 |
rapes | +0.027 |
Comes | +0.026 |
lic | +0.026 |
:= | +0.026 |
Neg logit contributions | |
hesda | -0.037 |
Arizona | -0.035 |
anyahu | -0.034 |
Catal | -0.033 |
offense | -0.032 |
Token | ( |
Token ID | 357 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
hesda | +2.631 |
Arizona | +2.526 |
anyahu | +2.443 |
offense | +2.370 |
Catal | +2.359 |
Neg logit contributions | |
cius | -2.342 |
rapes | -1.546 |
lic | -1.487 |
Comes | -1.458 |
:= | -1.451 |
Token | for |
Token ID | 1640 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
cius | +0.378 |
rapes | +0.281 |
lic | +0.279 |
Comes | +0.274 |
:= | +0.270 |
Neg logit contributions | |
hesda | -0.233 |
Arizona | -0.218 |
anyahu | -0.212 |
Catal | -0.197 |
offense | -0.196 |
Token | maximum |
Token ID | 5415 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
hesda | +0.377 |
Arizona | +0.357 |
anyahu | +0.348 |
Catal | +0.328 |
orno | +0.320 |
Neg logit contributions | |
cius | -0.479 |
rapes | -0.346 |
lic | -0.339 |
Comes | -0.337 |
:= | -0.328 |
Token | strength |
Token ID | 4202 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
hesda | +0.462 |
Arizona | +0.437 |
anyahu | +0.424 |
Catal | +0.398 |
orno | +0.386 |
Neg logit contributions | |
cius | -0.705 |
rapes | -0.524 |
lic | -0.513 |
Comes | -0.511 |
:= | -0.501 |
Token | ). |
Token ID | 737 |
Feature activation | +8.95e-01 |
Pos logit contributions | |
hesda | +0.199 |
Arizona | +0.191 |
anyahu | +0.187 |
Catal | +0.179 |
orno | +0.176 |
Neg logit contributions | |
cius | -0.175 |
rapes | -0.117 |
lic | -0.114 |
Comes | -0.112 |
:= | -0.110 |
Token | scandal |
Token ID | 10731 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
cius | +0.105 |
rapes | +0.075 |
lic | +0.074 |
Comes | +0.073 |
:= | +0.071 |
Neg logit contributions | |
hesda | -0.086 |
Arizona | -0.081 |
anyahu | -0.079 |
Catal | -0.074 |
offense | -0.073 |
Token | - |
Token ID | 12 |
Feature activation | +8.41e-02 |
Pos logit contributions | |
hesda | +0.251 |
Arizona | +0.238 |
anyahu | +0.230 |
Catal | +0.219 |
offense | +0.216 |
Neg logit contributions | |
cius | -0.316 |
rapes | -0.226 |
lic | -0.222 |
Comes | -0.219 |
:= | -0.216 |
Token | hit |
Token ID | 17945 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
cius | +0.072 |
rapes | +0.049 |
lic | +0.048 |
Comes | +0.047 |
:= | +0.047 |
Neg logit contributions | |
hesda | -0.071 |
Arizona | -0.068 |
anyahu | -0.066 |
Catal | -0.063 |
offense | -0.063 |
Token | former |
Token ID | 1966 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
hesda | +0.724 |
Arizona | +0.688 |
anyahu | +0.668 |
Catal | +0.635 |
offense | +0.627 |
Neg logit contributions | |
cius | -0.834 |
rapes | -0.587 |
lic | -0.575 |
Comes | -0.567 |
:= | -0.558 |
Token | International |
Token ID | 4037 |
Feature activation | +8.37e-01 |
Pos logit contributions | |
hesda | +0.239 |
Arizona | +0.227 |
anyahu | +0.221 |
Catal | +0.209 |
offense | +0.206 |
Neg logit contributions | |
cius | -0.258 |
rapes | -0.181 |
lic | -0.176 |
Comes | -0.175 |
:= | -0.171 |
Token | Monetary |
Token ID | 34112 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
cius | +0.675 |
rapes | +0.452 |
lic | +0.441 |
Comes | +0.436 |
:= | +0.427 |
Neg logit contributions | |
hesda | -0.749 |
Arizona | -0.715 |
anyahu | -0.697 |
Catal | -0.664 |
offense | -0.658 |
Token | Fund |
Token ID | 7557 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
hesda | +2.367 |
Arizona | +2.252 |
anyahu | +2.190 |
Catal | +2.086 |
offense | +2.063 |
Neg logit contributions | |
cius | -2.572 |
rapes | -1.786 |
lic | -1.748 |
Comes | -1.727 |
:= | -1.699 |
Token | chief |
Token ID | 4039 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
cius | +0.109 |
rapes | +0.076 |
lic | +0.075 |
Comes | +0.074 |
:= | +0.072 |
Neg logit contributions | |
hesda | -0.100 |
Arizona | -0.095 |
anyahu | -0.092 |
Catal | -0.088 |
offense | -0.086 |
Token | Domin |
Token ID | 11817 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
hesda | +0.220 |
Arizona | +0.209 |
anyahu | +0.202 |
Catal | +0.192 |
offense | +0.188 |
Neg logit contributions | |
cius | -0.262 |
rapes | -0.186 |
lic | -0.183 |
Comes | -0.181 |
:= | -0.177 |
Token | ique |
Token ID | 2350 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
hesda | +0.100 |
Arizona | +0.094 |
anyahu | +0.091 |
Catal | +0.085 |
offense | +0.084 |
Neg logit contributions | |
cius | -0.163 |
rapes | -0.121 |
lic | -0.119 |
Comes | -0.118 |
:= | -0.117 |
Token | Strauss |
Token ID | 42971 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
cius | +0.022 |
rapes | +0.015 |
lic | +0.014 |
Comes | +0.014 |
:= | +0.014 |
Neg logit contributions | |
hesda | -0.025 |
Arizona | -0.024 |
anyahu | -0.024 |
Catal | -0.023 |
offense | -0.022 |
Token | j |
Token ID | 474 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
hesda | +0.308 |
Arizona | +0.291 |
anyahu | +0.287 |
Catal | +0.267 |
orno | +0.262 |
Neg logit contributions | |
cius | -0.385 |
rapes | -0.280 |
lic | -0.271 |
Comes | -0.268 |
:= | -0.264 |
Token | umble |
Token ID | 10344 |
Feature activation | -7.95e-02 |
Pos logit contributions | |
cius | +0.039 |
rapes | +0.025 |
lic | +0.024 |
Comes | +0.024 |
:= | +0.023 |
Neg logit contributions | |
hesda | -0.050 |
Arizona | -0.048 |
anyahu | -0.047 |
Catal | -0.045 |
offense | -0.045 |
Token | of |
Token ID | 286 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
hesda | +0.076 |
Arizona | +0.072 |
anyahu | +0.071 |
Catal | +0.068 |
offense | +0.067 |
Neg logit contributions | |
cius | -0.059 |
rapes | -0.038 |
lic | -0.038 |
Comes | -0.037 |
:= | -0.036 |
Token | floating |
Token ID | 12462 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
hesda | +0.160 |
Arizona | +0.151 |
anyahu | +0.149 |
Catal | +0.139 |
offense | +0.136 |
Neg logit contributions | |
cius | -0.196 |
rapes | -0.142 |
lic | -0.138 |
Comes | -0.136 |
:= | -0.134 |
Token | ice |
Token ID | 4771 |
Feature activation | -6.33e-02 |
Pos logit contributions | |
hesda | +0.575 |
Arizona | +0.543 |
anyahu | +0.532 |
Catal | +0.498 |
offense | +0.487 |
Neg logit contributions | |
cius | -0.724 |
rapes | -0.527 |
lic | -0.514 |
Comes | -0.505 |
:= | -0.498 |
Token | downstream |
Token ID | 33218 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
hesda | +0.052 |
Arizona | +0.049 |
anyahu | +0.048 |
Catal | +0.045 |
offense | +0.044 |
Neg logit contributions | |
cius | -0.056 |
rapes | -0.040 |
lic | -0.039 |
Comes | -0.038 |
:= | -0.037 |
Token | from |
Token ID | 422 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
hesda | +2.407 |
Arizona | +2.293 |
anyahu | +2.235 |
Catal | +2.128 |
offense | +2.104 |
Neg logit contributions | |
cius | -2.468 |
rapes | -1.698 |
lic | -1.659 |
Comes | -1.637 |
:= | -1.610 |
Token | the |
Token ID | 262 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
hesda | +0.238 |
Arizona | +0.226 |
anyahu | +0.220 |
Catal | +0.209 |
offense | +0.207 |
Neg logit contributions | |
cius | -0.262 |
rapes | -0.183 |
lic | -0.179 |
Comes | -0.177 |
:= | -0.174 |
Token | glacier |
Token ID | 44539 |
Feature activation | +7.91e-01 |
Pos logit contributions | |
hesda | +0.412 |
Arizona | +0.388 |
anyahu | +0.382 |
Catal | +0.358 |
orno | +0.351 |
Neg logit contributions | |
cius | -0.494 |
rapes | -0.355 |
lic | -0.345 |
Comes | -0.342 |
:= | -0.335 |
Token | . |
Token ID | 13 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
cius | +0.687 |
rapes | +0.487 |
lic | +0.472 |
Comes | +0.468 |
:= | +0.458 |
Neg logit contributions | |
hesda | -0.651 |
Arizona | -0.619 |
anyahu | -0.612 |
Catal | -0.574 |
orno | -0.561 |
Token | Turn |
Token ID | 6756 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
hesda | +0.582 |
Arizona | +0.545 |
anyahu | +0.541 |
offense | +0.508 |
Catal | +0.507 |
Neg logit contributions | |
cius | -0.537 |
rapes | -0.362 |
lic | -0.356 |
Comes | -0.356 |
:= | -0.346 |
Token | military |
Token ID | 2422 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
hesda | +0.140 |
Arizona | +0.132 |
anyahu | +0.126 |
Catal | +0.121 |
offense | +0.118 |
Neg logit contributions | |
cius | -0.186 |
rapes | -0.135 |
lic | -0.134 |
Comes | -0.131 |
:= | -0.129 |
Token | occupation |
Token ID | 13755 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
hesda | +0.176 |
Arizona | +0.164 |
anyahu | +0.158 |
Catal | +0.152 |
orno | +0.147 |
Neg logit contributions | |
cius | -0.231 |
rapes | -0.170 |
lic | -0.166 |
Comes | -0.163 |
:= | -0.160 |
Token | . |
Token ID | 13 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
hesda | +0.227 |
Arizona | +0.217 |
anyahu | +0.211 |
Catal | +0.202 |
offense | +0.200 |
Neg logit contributions | |
cius | -0.213 |
rapes | -0.143 |
lic | -0.140 |
Comes | -0.138 |
:= | -0.135 |
Token |
|
Token ID | 198 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
hesda | +0.118 |
Arizona | +0.111 |
anyahu | +0.109 |
Catal | +0.103 |
offense | +0.103 |
Neg logit contributions | |
cius | -0.119 |
rapes | -0.082 |
lic | -0.080 |
Comes | -0.080 |
:= | -0.078 |
Token |
|
Token ID | 198 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
hesda | +0.235 |
anyahu | +0.217 |
Arizona | +0.215 |
offense | +0.202 |
orno | +0.202 |
Neg logit contributions | |
cius | -0.210 |
lic | -0.144 |
rapes | -0.143 |
:= | -0.140 |
Comes | -0.139 |
Token | Per |
Token ID | 5990 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
hesda | +0.268 |
Arizona | +0.242 |
anyahu | +0.241 |
offense | +0.230 |
orno | +0.226 |
Neg logit contributions | |
cius | -0.308 |
lic | -0.222 |
rapes | -0.220 |
Comes | -0.214 |
:= | -0.213 |
Token | ceptions |
Token ID | 11755 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
hesda | +2.081 |
Arizona | +1.968 |
anyahu | +1.916 |
Catal | +1.807 |
offense | +1.792 |
Neg logit contributions | |
cius | -2.775 |
rapes | -2.004 |
lic | -1.952 |
Comes | -1.940 |
:= | -1.914 |
Token | are |
Token ID | 389 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
cius | +0.659 |
rapes | +0.437 |
lic | +0.428 |
Comes | +0.422 |
:= | +0.414 |
Neg logit contributions | |
hesda | -0.738 |
Arizona | -0.703 |
anyahu | -0.686 |
Catal | -0.654 |
orno | -0.646 |
Token | indeed |
Token ID | 5600 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
cius | +0.359 |
rapes | +0.256 |
lic | +0.250 |
Comes | +0.245 |
:= | +0.243 |
Neg logit contributions | |
hesda | -0.302 |
Arizona | -0.285 |
anyahu | -0.278 |
Catal | -0.261 |
orno | -0.256 |
Token | changing |
Token ID | 5609 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
cius | +0.122 |
rapes | +0.087 |
lic | +0.085 |
Comes | +0.083 |
:= | +0.082 |
Neg logit contributions | |
hesda | -0.103 |
Arizona | -0.098 |
anyahu | -0.096 |
Catal | -0.090 |
orno | -0.088 |
Token | , |
Token ID | 11 |
Feature activation | +8.51e-03 |
Pos logit contributions | |
cius | +0.233 |
rapes | +0.157 |
lic | +0.155 |
Comes | +0.152 |
:= | +0.150 |
Neg logit contributions | |
hesda | -0.243 |
Arizona | -0.232 |
anyahu | -0.227 |
Catal | -0.216 |
offense | -0.213 |
Token | 0 |
Token ID | 15 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
hesda | +0.147 |
Arizona | +0.140 |
anyahu | +0.137 |
Catal | +0.131 |
offense | +0.130 |
Neg logit contributions | |
cius | -0.137 |
rapes | -0.091 |
lic | -0.090 |
Comes | -0.088 |
:= | -0.087 |
Token | , |
Token ID | 11 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
cius | +0.820 |
rapes | +0.579 |
lic | +0.565 |
Comes | +0.561 |
esian | +0.545 |
Neg logit contributions | |
hesda | -0.689 |
Arizona | -0.656 |
anyahu | -0.635 |
Catal | -0.604 |
offense | -0.600 |
Token | _ |
Token ID | 4808 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
hesda | +0.197 |
Arizona | +0.187 |
anyahu | +0.182 |
Catal | +0.173 |
offense | +0.171 |
Neg logit contributions | |
cius | -0.224 |
rapes | -0.157 |
lic | -0.154 |
Comes | -0.152 |
:= | -0.150 |
Token | P |
Token ID | 47 |
Feature activation | -8.93e-01 |
Pos logit contributions | |
cius | +0.352 |
rapes | +0.266 |
lic | +0.260 |
Comes | +0.258 |
:= | +0.254 |
Neg logit contributions | |
hesda | -0.195 |
Arizona | -0.184 |
anyahu | -0.175 |
Catal | -0.165 |
offense | -0.162 |
Token | ulse |
Token ID | 9615 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
hesda | +0.743 |
Arizona | +0.702 |
anyahu | +0.687 |
offense | +0.652 |
Catal | +0.650 |
Neg logit contributions | |
cius | -0.794 |
lic | -0.550 |
:= | -0.529 |
rapes | -0.525 |
esian | -0.510 |
Token | Per |
Token ID | 5990 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
cius | +0.183 |
lic | +0.126 |
:= | +0.124 |
Comes | +0.120 |
rapes | +0.120 |
Neg logit contributions | |
hesda | -0.211 |
anyahu | -0.196 |
Arizona | -0.194 |
orno | -0.186 |
offense | -0.184 |
Token | iod |
Token ID | 2101 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
hesda | +2.255 |
Arizona | +2.133 |
anyahu | +2.071 |
Catal | +1.957 |
offense | +1.950 |
Neg logit contributions | |
cius | -2.643 |
lic | -1.851 |
rapes | -1.806 |
:= | -1.789 |
Comes | -1.775 |
Token | ] |
Token ID | 60 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
cius | +0.590 |
rapes | +0.411 |
lic | +0.404 |
Comes | +0.399 |
:= | +0.394 |
Neg logit contributions | |
hesda | -0.535 |
Arizona | -0.508 |
anyahu | -0.494 |
Catal | -0.470 |
offense | -0.464 |
Token | to |
Token ID | 284 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
cius | +0.014 |
rapes | +0.009 |
lic | +0.009 |
:= | +0.009 |
Comes | +0.009 |
Neg logit contributions | |
hesda | -0.013 |
Arizona | -0.013 |
anyahu | -0.012 |
Catal | -0.012 |
offense | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
cius | +0.199 |
rapes | +0.141 |
lic | +0.138 |
Comes | +0.136 |
:= | +0.136 |
Neg logit contributions | |
hesda | -0.176 |
Arizona | -0.166 |
anyahu | -0.163 |
Catal | -0.154 |
orno | -0.151 |
Token | rem |
Token ID | 816 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
cius | +0.198 |
rapes | +0.139 |
lic | +0.137 |
:= | +0.134 |
Comes | +0.134 |
Neg logit contributions | |
hesda | -0.175 |
Arizona | -0.165 |
anyahu | -0.162 |
Catal | -0.153 |
offense | -0.150 |
Token | years |
Token ID | 812 |
Feature activation | -8.67e-02 |
Pos logit contributions | |
cius | +0.505 |
rapes | +0.356 |
lic | +0.345 |
Comes | +0.341 |
:= | +0.335 |
Neg logit contributions | |
hesda | -0.464 |
Arizona | -0.437 |
anyahu | -0.427 |
Catal | -0.408 |
orno | -0.403 |
Token | in |
Token ID | 287 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
hesda | +0.075 |
Arizona | +0.070 |
anyahu | +0.069 |
Catal | +0.066 |
orno | +0.064 |
Neg logit contributions | |
cius | -0.073 |
rapes | -0.050 |
Comes | -0.049 |
lic | -0.049 |
:= | -0.047 |
Token | prison |
Token ID | 3770 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
cius | +0.023 |
rapes | +0.016 |
Comes | +0.015 |
lic | +0.015 |
:= | +0.015 |
Neg logit contributions | |
hesda | -0.022 |
Arizona | -0.020 |
anyahu | -0.020 |
Catal | -0.019 |
orno | -0.019 |
Token | MORE |
Token ID | 12011 |
Feature activation | -9.10e-01 |
Pos logit contributions | |
cius | +0.397 |
rapes | +0.270 |
Comes | +0.264 |
:= | +0.253 |
lic | +0.251 |
Neg logit contributions | |
hesda | -0.475 |
Arizona | -0.443 |
anyahu | -0.441 |
Catal | -0.422 |
orno | -0.418 |
Token | and |
Token ID | 290 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
hesda | +0.776 |
Arizona | +0.738 |
anyahu | +0.723 |
Catal | +0.688 |
orno | +0.676 |
Neg logit contributions | |
cius | -0.770 |
rapes | -0.530 |
lic | -0.516 |
Comes | -0.510 |
:= | -0.500 |
Token | tick |
Token ID | 4378 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
hesda | +0.817 |
Arizona | +0.774 |
anyahu | +0.755 |
Catal | +0.718 |
offense | +0.707 |
Neg logit contributions | |
cius | -0.905 |
rapes | -0.634 |
lic | -0.619 |
Comes | -0.611 |
:= | -0.601 |
Token | ed |
Token ID | 276 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
hesda | +2.167 |
Arizona | +2.059 |
anyahu | +1.987 |
Catal | +1.894 |
offense | +1.882 |
Neg logit contributions | |
cius | -2.633 |
rapes | -1.859 |
lic | -1.816 |
Comes | -1.807 |
:= | -1.779 |
Token | through |
Token ID | 832 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
hesda | +0.287 |
Arizona | +0.269 |
anyahu | +0.261 |
Catal | +0.245 |
offense | +0.240 |
Neg logit contributions | |
cius | -0.444 |
rapes | -0.329 |
lic | -0.324 |
Comes | -0.319 |
:= | -0.316 |
Token | her |
Token ID | 607 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
hesda | +0.129 |
Arizona | +0.122 |
anyahu | +0.120 |
Catal | +0.113 |
orno | +0.111 |
Neg logit contributions | |
cius | -0.159 |
rapes | -0.115 |
lic | -0.112 |
Comes | -0.110 |
:= | -0.108 |
Token | usual |
Token ID | 6678 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
hesda | +0.449 |
Arizona | +0.420 |
anyahu | +0.414 |
Catal | +0.389 |
orno | +0.383 |
Neg logit contributions | |
cius | -0.548 |
rapes | -0.398 |
lic | -0.389 |
Comes | -0.379 |
:= | -0.374 |
Token | policy |
Token ID | 2450 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
cius | +0.565 |
rapes | +0.406 |
lic | +0.395 |
Comes | +0.385 |
:= | +0.379 |
Neg logit contributions | |
hesda | -0.498 |
Arizona | -0.466 |
anyahu | -0.462 |
Catal | -0.436 |
orno | -0.430 |
Token | not |
Token ID | 407 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
hesda | +0.084 |
Arizona | +0.079 |
anyahu | +0.078 |
Catal | +0.073 |
offense | +0.072 |
Neg logit contributions | |
cius | -0.098 |
rapes | -0.069 |
lic | -0.068 |
Comes | -0.068 |
:= | -0.066 |
Token | quite |
Token ID | 2407 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
hesda | +0.395 |
Arizona | +0.373 |
anyahu | +0.364 |
Catal | +0.345 |
offense | +0.339 |
Neg logit contributions | |
cius | -0.456 |
rapes | -0.324 |
lic | -0.317 |
Comes | -0.313 |
:= | -0.308 |
Token | sure |
Token ID | 1654 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
cius | +0.248 |
rapes | +0.177 |
lic | +0.173 |
Comes | +0.172 |
:= | +0.168 |
Neg logit contributions | |
hesda | -0.217 |
Arizona | -0.204 |
anyahu | -0.200 |
Catal | -0.189 |
offense | -0.185 |
Token | what |
Token ID | 644 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
hesda | +0.881 |
Arizona | +0.839 |
anyahu | +0.818 |
Catal | +0.780 |
offense | +0.771 |
Neg logit contributions | |
cius | -0.897 |
rapes | -0.615 |
lic | -0.601 |
Comes | -0.593 |
:= | -0.583 |
Token | F |
Token ID | 376 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
cius | +0.185 |
rapes | +0.126 |
Comes | +0.122 |
lic | +0.122 |
:= | +0.118 |
Neg logit contributions | |
hesda | -0.196 |
Arizona | -0.187 |
anyahu | -0.184 |
Catal | -0.175 |
orno | -0.171 |
Token | UB |
Token ID | 10526 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
hesda | +0.040 |
Arizona | +0.038 |
anyahu | +0.037 |
Catal | +0.035 |
offense | +0.035 |
Neg logit contributions | |
cius | -0.044 |
rapes | -0.031 |
lic | -0.031 |
Comes | -0.030 |
:= | -0.029 |
Token | AR |
Token ID | 1503 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
hesda | +1.950 |
Arizona | +1.836 |
anyahu | +1.779 |
Catal | +1.675 |
offense | +1.652 |
Neg logit contributions | |
cius | -2.847 |
rapes | -2.087 |
lic | -2.051 |
Comes | -2.030 |
:= | -2.000 |
Token | means |
Token ID | 1724 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
hesda | +0.170 |
Arizona | +0.161 |
anyahu | +0.158 |
Catal | +0.149 |
offense | +0.147 |
Neg logit contributions | |
cius | -0.187 |
rapes | -0.131 |
lic | -0.128 |
Comes | -0.127 |
:= | -0.124 |
Token | . |
Token ID | 13 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
hesda | +0.112 |
Arizona | +0.107 |
anyahu | +0.104 |
Catal | +0.099 |
offense | +0.097 |
Neg logit contributions | |
cius | -0.119 |
rapes | -0.082 |
lic | -0.081 |
Comes | -0.080 |
:= | -0.078 |
Token | She |
Token ID | 1375 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
hesda | +0.024 |
Arizona | +0.022 |
anyahu | +0.022 |
Catal | +0.021 |
offense | +0.021 |
Neg logit contributions | |
cius | -0.022 |
rapes | -0.015 |
Comes | -0.015 |
lic | -0.015 |
:= | -0.014 |
Token | was |
Token ID | 373 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
hesda | +0.231 |
Arizona | +0.219 |
anyahu | +0.214 |
Catal | +0.204 |
offense | +0.201 |
Neg logit contributions | |
cius | -0.221 |
rapes | -0.150 |
lic | -0.146 |
Comes | -0.145 |
:= | -0.142 |
Token | , |
Token ID | 11 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
hesda | +0.490 |
Arizona | +0.464 |
anyahu | +0.455 |
Catal | +0.428 |
orno | +0.423 |
Neg logit contributions | |
cius | -0.498 |
rapes | -0.342 |
lic | -0.336 |
Comes | -0.333 |
:= | -0.325 |
Token | beginning |
Token ID | 3726 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
cius | +0.015 |
rapes | +0.010 |
lic | +0.010 |
Comes | +0.010 |
:= | +0.010 |
Neg logit contributions | |
hesda | -0.014 |
Arizona | -0.014 |
anyahu | -0.014 |
orno | -0.013 |
Catal | -0.013 |
Token | with |
Token ID | 351 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
hesda | +0.219 |
Arizona | +0.208 |
anyahu | +0.205 |
Catal | +0.193 |
orno | +0.191 |
Neg logit contributions | |
cius | -0.206 |
rapes | -0.140 |
lic | -0.136 |
Comes | -0.135 |
:= | -0.133 |
Token | the |
Token ID | 262 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
hesda | +0.286 |
Arizona | +0.269 |
anyahu | +0.267 |
Catal | +0.246 |
orno | +0.244 |
Neg logit contributions | |
cius | -0.327 |
rapes | -0.231 |
lic | -0.229 |
Comes | -0.228 |
:= | -0.221 |
Token | upcoming |
Token ID | 7865 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
hesda | +0.103 |
Arizona | +0.096 |
anyahu | +0.096 |
Catal | +0.087 |
orno | +0.087 |
Neg logit contributions | |
cius | -0.131 |
rapes | -0.095 |
lic | -0.094 |
Comes | -0.093 |
:= | -0.091 |
Token | Rally |
Token ID | 27752 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
hesda | +0.136 |
Arizona | +0.127 |
anyahu | +0.126 |
Catal | +0.116 |
orno | +0.114 |
Neg logit contributions | |
cius | -0.164 |
rapes | -0.118 |
lic | -0.116 |
Comes | -0.115 |
:= | -0.112 |
Token | e |
Token ID | 68 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
hesda | +2.236 |
Arizona | +2.131 |
anyahu | +2.060 |
Catal | +1.972 |
offense | +1.951 |
Neg logit contributions | |
cius | -2.510 |
rapes | -1.755 |
lic | -1.713 |
Comes | -1.690 |
:= | -1.670 |
Token | Monte |
Token ID | 22489 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
hesda | +0.153 |
Arizona | +0.144 |
anyahu | +0.141 |
Catal | +0.132 |
offense | +0.131 |
Neg logit contributions | |
cius | -0.169 |
rapes | -0.118 |
lic | -0.117 |
Comes | -0.114 |
:= | -0.112 |
Token | - |
Token ID | 12 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
hesda | +1.051 |
Arizona | +1.007 |
anyahu | +0.991 |
Catal | +0.937 |
offense | +0.932 |
Neg logit contributions | |
cius | -0.857 |
rapes | -0.549 |
lic | -0.539 |
Comes | -0.528 |
:= | -0.513 |
Token | Car |
Token ID | 9914 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
cius | +0.502 |
lic | +0.355 |
rapes | +0.353 |
Comes | +0.348 |
:= | +0.341 |
Neg logit contributions | |
hesda | -0.403 |
Arizona | -0.374 |
anyahu | -0.370 |
offense | -0.346 |
orno | -0.343 |
Token | lo |
Token ID | 5439 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
cius | +0.924 |
rapes | +0.582 |
lic | +0.571 |
Comes | +0.557 |
:= | +0.545 |
Neg logit contributions | |
hesda | -1.204 |
Arizona | -1.156 |
anyahu | -1.131 |
Catal | -1.082 |
offense | -1.074 |
Token | the |
Token ID | 262 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
hesda | +0.506 |
Arizona | +0.477 |
anyahu | +0.463 |
Catal | +0.436 |
offense | +0.430 |
Neg logit contributions | |
cius | -0.708 |
rapes | -0.516 |
lic | -0.507 |
Comes | -0.502 |
:= | -0.495 |
Token | first |
Token ID | 717 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
hesda | +0.459 |
Arizona | +0.434 |
anyahu | +0.428 |
Catal | +0.400 |
orno | +0.395 |
Neg logit contributions | |
cius | -0.519 |
rapes | -0.369 |
lic | -0.361 |
Comes | -0.357 |
:= | -0.352 |
Token | uncontrolled |
Token ID | 47913 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
hesda | +0.505 |
Arizona | +0.475 |
anyahu | +0.464 |
Catal | +0.435 |
offense | +0.422 |
Neg logit contributions | |
cius | -0.734 |
rapes | -0.540 |
lic | -0.532 |
Comes | -0.526 |
:= | -0.517 |
Token | re |
Token ID | 302 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
hesda | +0.666 |
Arizona | +0.626 |
anyahu | +0.609 |
Catal | +0.572 |
offense | +0.559 |
Neg logit contributions | |
cius | -0.949 |
rapes | -0.696 |
lic | -0.686 |
Comes | -0.678 |
:= | -0.667 |
Token | - |
Token ID | 12 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
hesda | +0.466 |
Arizona | +0.444 |
anyahu | +0.418 |
Catal | +0.396 |
offense | +0.395 |
Neg logit contributions | |
cius | -0.800 |
rapes | -0.601 |
Comes | -0.580 |
lic | -0.573 |
:= | -0.570 |
Token | entry |
Token ID | 13000 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
hesda | +0.529 |
Arizona | +0.498 |
anyahu | +0.482 |
Catal | +0.454 |
offense | +0.448 |
Neg logit contributions | |
cius | -0.796 |
rapes | -0.585 |
lic | -0.576 |
Comes | -0.569 |
:= | -0.562 |
Token | of |
Token ID | 286 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
hesda | +2.418 |
Arizona | +2.309 |
anyahu | +2.241 |
Catal | +2.149 |
offense | +2.142 |
Neg logit contributions | |
cius | -2.310 |
rapes | -1.550 |
lic | -1.513 |
Comes | -1.489 |
:= | -1.466 |
Token | an |
Token ID | 281 |
Feature activation | -8.35e-01 |
Pos logit contributions | |
hesda | +0.244 |
Arizona | +0.229 |
anyahu | +0.224 |
Catal | +0.210 |
offense | +0.204 |
Neg logit contributions | |
cius | -0.324 |
rapes | -0.236 |
lic | -0.231 |
Comes | -0.229 |
:= | -0.225 |
Token | Es |
Token ID | 8678 |
Feature activation | -9.34e-01 |
Pos logit contributions | |
hesda | +0.604 |
Arizona | +0.570 |
anyahu | +0.554 |
Catal | +0.524 |
offense | +0.513 |
Neg logit contributions | |
cius | -0.817 |
rapes | -0.592 |
lic | -0.580 |
Comes | -0.575 |
:= | -0.567 |
Token | a |
Token ID | 64 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
hesda | +0.881 |
Arizona | +0.837 |
anyahu | +0.822 |
Catal | +0.793 |
offense | +0.788 |
Neg logit contributions | |
cius | -0.703 |
lic | -0.456 |
rapes | -0.443 |
:= | -0.430 |
esian | -0.429 |
Token | satellite |
Token ID | 11210 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
cius | +0.413 |
rapes | +0.301 |
lic | +0.299 |
Comes | +0.295 |
:= | +0.290 |
Neg logit contributions | |
hesda | -0.286 |
Arizona | -0.269 |
anyahu | -0.262 |
Catal | -0.245 |
offense | -0.239 |
Token | based |
Token ID | 1912 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
cius | +0.299 |
rapes | +0.181 |
lic | +0.176 |
Comes | +0.173 |
:= | +0.168 |
Neg logit contributions | |
hesda | -0.458 |
Arizona | -0.441 |
anyahu | -0.428 |
Catal | -0.413 |
offense | -0.410 |
Token | on |
Token ID | 319 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
cius | +0.433 |
rapes | +0.297 |
lic | +0.288 |
Comes | +0.286 |
:= | +0.280 |
Neg logit contributions | |
hesda | -0.418 |
Arizona | -0.397 |
anyahu | -0.389 |
Catal | -0.370 |
offense | -0.366 |
Token | Ha |
Token ID | 9398 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
cius | +0.029 |
rapes | +0.021 |
lic | +0.021 |
Comes | +0.020 |
:= | +0.020 |
Neg logit contributions | |
hesda | -0.023 |
Arizona | -0.022 |
anyahu | -0.021 |
Catal | -0.020 |
offense | -0.020 |
Token | aretz |
Token ID | 48338 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
cius | +0.829 |
rapes | +0.666 |
lic | +0.664 |
:= | +0.659 |
Comes | +0.658 |
Neg logit contributions | |
hesda | -0.227 |
Arizona | -0.187 |
anyahu | -0.175 |
Catal | -0.155 |
offense | -0.155 |
Token | , |
Token ID | 11 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
hesda | +1.229 |
Arizona | +1.173 |
anyahu | +1.145 |
Catal | +1.093 |
offense | +1.083 |
Neg logit contributions | |
cius | -1.185 |
rapes | -0.799 |
lic | -0.780 |
Comes | -0.769 |
:= | -0.756 |
Token | JP |
Token ID | 21331 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
cius | +0.029 |
rapes | +0.020 |
lic | +0.020 |
Comes | +0.020 |
:= | +0.019 |
Neg logit contributions | |
hesda | -0.026 |
Arizona | -0.024 |
anyahu | -0.023 |
Catal | -0.022 |
orno | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | +3.89e-02 |
Pos logit contributions | |
hesda | +2.206 |
Arizona | +2.096 |
anyahu | +2.039 |
Catal | +1.941 |
offense | +1.918 |
Neg logit contributions | |
cius | -2.510 |
rapes | -1.757 |
lic | -1.719 |
Comes | -1.687 |
:= | -1.664 |
Token | T |
Token ID | 309 |
Feature activation | -9.80e-02 |
Pos logit contributions | |
cius | +0.036 |
rapes | +0.025 |
lic | +0.025 |
Comes | +0.025 |
:= | +0.024 |
Neg logit contributions | |
hesda | -0.031 |
Arizona | -0.029 |
anyahu | -0.028 |
Catal | -0.027 |
orno | -0.026 |
Token | Z |
Token ID | 57 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
hesda | +0.076 |
Arizona | +0.071 |
anyahu | +0.069 |
Catal | +0.066 |
offense | +0.065 |
Neg logit contributions | |
cius | -0.091 |
rapes | -0.064 |
lic | -0.064 |
Comes | -0.063 |
:= | -0.062 |
Token | , |
Token ID | 11 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
cius | +0.009 |
rapes | +0.007 |
lic | +0.006 |
Comes | +0.006 |
:= | +0.006 |
Neg logit contributions | |
hesda | -0.009 |
Arizona | -0.009 |
anyahu | -0.008 |
Catal | -0.008 |
offense | -0.008 |
Token | Reuters |
Token ID | 8428 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
cius | +0.306 |
rapes | +0.216 |
lic | +0.211 |
Comes | +0.208 |
:= | +0.205 |
Neg logit contributions | |
hesda | -0.282 |
Arizona | -0.267 |
anyahu | -0.258 |
Catal | -0.246 |
orno | -0.243 |
Token | ( |
Token ID | 357 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
hesda | +0.731 |
Arizona | +0.699 |
anyahu | +0.678 |
offense | +0.654 |
Catal | +0.654 |
Neg logit contributions | |
cius | -0.630 |
rapes | -0.411 |
lic | -0.399 |
Comes | -0.393 |
:= | -0.387 |
Token | 18 |
Token ID | 1507 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
cius | +0.497 |
lic | +0.342 |
rapes | +0.341 |
Comes | +0.331 |
:= | +0.330 |
Neg logit contributions | |
hesda | -0.503 |
anyahu | -0.465 |
Arizona | -0.465 |
offense | -0.439 |
orno | -0.436 |
Token | ) |
Token ID | 8 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
hesda | +0.259 |
Arizona | +0.248 |
anyahu | +0.241 |
offense | +0.231 |
Catal | +0.230 |
Neg logit contributions | |
cius | -0.280 |
rapes | -0.192 |
lic | -0.189 |
Comes | -0.186 |
:= | -0.184 |
Token |
|
Token ID | 198 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
cius | +0.142 |
rapes | +0.096 |
Comes | +0.096 |
lic | +0.096 |
:= | +0.094 |
Neg logit contributions | |
hesda | -0.154 |
Arizona | -0.144 |
anyahu | -0.144 |
offense | -0.134 |
Catal | -0.134 |
Token |
|
Token ID | 198 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
hesda | +0.257 |
anyahu | +0.238 |
Arizona | +0.237 |
offense | +0.222 |
orno | +0.221 |
Neg logit contributions | |
cius | -0.232 |
lic | -0.159 |
rapes | -0.158 |
:= | -0.155 |
Comes | -0.155 |
Token | Per |
Token ID | 5990 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
hesda | +0.158 |
anyahu | +0.143 |
Arizona | +0.143 |
offense | +0.133 |
orno | +0.131 |
Neg logit contributions | |
cius | -0.211 |
lic | -0.153 |
rapes | -0.152 |
Comes | -0.149 |
:= | -0.148 |
Token | form |
Token ID | 687 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
hesda | +2.272 |
Arizona | +2.161 |
anyahu | +2.098 |
Catal | +2.003 |
offense | +1.989 |
Neg logit contributions | |
cius | -2.383 |
rapes | -1.651 |
Comes | -1.594 |
lic | -1.591 |
:= | -1.562 |
Token | all |
Token ID | 477 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
cius | +1.203 |
rapes | +0.865 |
lic | +0.850 |
Comes | +0.849 |
:= | +0.823 |
Neg logit contributions | |
hesda | -0.945 |
Arizona | -0.893 |
anyahu | -0.867 |
Catal | -0.815 |
orno | -0.804 |
Token | 8 |
Token ID | 807 |
Feature activation | +9.41e-02 |
Pos logit contributions | |
cius | +0.015 |
rapes | +0.010 |
lic | +0.010 |
Comes | +0.010 |
:= | +0.010 |
Neg logit contributions | |
hesda | -0.011 |
Arizona | -0.011 |
anyahu | -0.010 |
Catal | -0.010 |
orno | -0.010 |
Token | gestures |
Token ID | 24621 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
cius | +0.086 |
rapes | +0.061 |
lic | +0.060 |
Comes | +0.059 |
:= | +0.058 |
Neg logit contributions | |
hesda | -0.074 |
Arizona | -0.070 |
anyahu | -0.068 |
Catal | -0.064 |
orno | -0.064 |
Token | of |
Token ID | 286 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
hesda | +0.017 |
Arizona | +0.016 |
anyahu | +0.015 |
Catal | +0.015 |
orno | +0.014 |
Neg logit contributions | |
cius | -0.016 |
rapes | -0.011 |
lic | -0.011 |
Comes | -0.011 |
:= | -0.010 |
Token | step |
Token ID | 2239 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
hesda | +0.079 |
Arizona | +0.076 |
anyahu | +0.074 |
Catal | +0.070 |
offense | +0.069 |
Neg logit contributions | |
cius | -0.081 |
rapes | -0.056 |
lic | -0.055 |
Comes | -0.054 |
:= | -0.054 |
Token | by |
Token ID | 416 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
hesda | +0.409 |
Arizona | +0.390 |
anyahu | +0.379 |
Catal | +0.361 |
offense | +0.356 |
Neg logit contributions | |
cius | -0.428 |
rapes | -0.296 |
lic | -0.290 |
Comes | -0.286 |
:= | -0.283 |
Token | step |
Token ID | 2239 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
hesda | +0.342 |
Arizona | +0.326 |
anyahu | +0.317 |
Catal | +0.302 |
offense | +0.299 |
Neg logit contributions | |
cius | -0.362 |
rapes | -0.250 |
lic | -0.245 |
Comes | -0.242 |
:= | -0.238 |
Token | , |
Token ID | 11 |
Feature activation | -5.48e-02 |
Pos logit contributions | |
hesda | +0.296 |
Arizona | +0.282 |
anyahu | +0.274 |
Catal | +0.261 |
offense | +0.258 |
Neg logit contributions | |
cius | -0.304 |
rapes | -0.208 |
lic | -0.204 |
Comes | -0.201 |
:= | -0.199 |
Token | first |
Token ID | 717 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
hesda | +0.046 |
Arizona | +0.044 |
anyahu | +0.043 |
Catal | +0.041 |
offense | +0.040 |
Neg logit contributions | |
cius | -0.047 |
rapes | -0.033 |
lic | -0.032 |
Comes | -0.031 |
:= | -0.031 |
Token | ly |
Token ID | 306 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
hesda | +0.589 |
Arizona | +0.561 |
anyahu | +0.547 |
Catal | +0.519 |
offense | +0.512 |
Neg logit contributions | |
cius | -0.626 |
rapes | -0.434 |
lic | -0.426 |
Comes | -0.419 |
:= | -0.415 |
Token | mapping |
Token ID | 16855 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
hesda | +2.312 |
Arizona | +2.203 |
anyahu | +2.142 |
Catal | +2.049 |
offense | +2.042 |
Neg logit contributions | |
cius | -2.335 |
rapes | -1.589 |
lic | -1.548 |
Comes | -1.531 |
:= | -1.495 |
Token | it |
Token ID | 340 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
hesda | +0.315 |
Arizona | +0.300 |
anyahu | +0.291 |
Catal | +0.277 |
offense | +0.274 |
Neg logit contributions | |
cius | -0.365 |
rapes | -0.256 |
lic | -0.251 |
Comes | -0.248 |
:= | -0.244 |
Token | onto |
Token ID | 4291 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
cius | +0.093 |
rapes | +0.062 |
lic | +0.060 |
Comes | +0.059 |
:= | +0.059 |
Neg logit contributions | |
hesda | -0.103 |
Arizona | -0.099 |
anyahu | -0.096 |
Catal | -0.092 |
offense | -0.091 |
Token | the |
Token ID | 262 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
hesda | +0.276 |
Arizona | +0.261 |
anyahu | +0.253 |
Catal | +0.240 |
offense | +0.240 |
Neg logit contributions | |
cius | -0.337 |
rapes | -0.239 |
lic | -0.235 |
Comes | -0.231 |
:= | -0.227 |
Token | range |
Token ID | 2837 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
hesda | +0.170 |
Arizona | +0.162 |
anyahu | +0.158 |
Catal | +0.150 |
offense | +0.148 |
Neg logit contributions | |
cius | -0.179 |
rapes | -0.124 |
lic | -0.121 |
Comes | -0.120 |
:= | -0.118 |
Token | dates |
Token ID | 9667 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
hesda | +0.296 |
Arizona | +0.280 |
anyahu | +0.276 |
Catal | +0.255 |
orno | +0.253 |
Neg logit contributions | |
cius | -0.374 |
rapes | -0.271 |
lic | -0.268 |
Comes | -0.263 |
:= | -0.257 |
Token | on |
Token ID | 319 |
Feature activation | -8.60e-02 |
Pos logit contributions | |
hesda | +0.299 |
Arizona | +0.284 |
anyahu | +0.281 |
Catal | +0.265 |
orno | +0.261 |
Neg logit contributions | |
cius | -0.300 |
rapes | -0.207 |
lic | -0.203 |
Comes | -0.200 |
:= | -0.195 |
Token | the |
Token ID | 262 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
hesda | +0.071 |
Arizona | +0.067 |
anyahu | +0.066 |
Catal | +0.062 |
orno | +0.062 |
Neg logit contributions | |
cius | -0.075 |
rapes | -0.052 |
lic | -0.052 |
Comes | -0.051 |
:= | -0.050 |
Token | FIA |
Token ID | 49432 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
hesda | +0.155 |
Arizona | +0.146 |
anyahu | +0.144 |
Catal | +0.134 |
orno | +0.133 |
Neg logit contributions | |
cius | -0.183 |
rapes | -0.130 |
lic | -0.129 |
Comes | -0.127 |
:= | -0.124 |
Token | World |
Token ID | 2159 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
hesda | +1.659 |
Arizona | +1.584 |
anyahu | +1.544 |
Catal | +1.474 |
offense | +1.460 |
Neg logit contributions | |
cius | -1.580 |
rapes | -1.064 |
lic | -1.040 |
Comes | -1.026 |
:= | -1.007 |
Token | Rally |
Token ID | 27752 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
hesda | +0.232 |
Arizona | +0.216 |
anyahu | +0.210 |
Catal | +0.193 |
offense | +0.191 |
Neg logit contributions | |
cius | -0.408 |
rapes | -0.305 |
lic | -0.303 |
Comes | -0.299 |
:= | -0.295 |
Token | Championship |
Token ID | 10749 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
hesda | +2.016 |
Arizona | +1.916 |
anyahu | +1.844 |
Catal | +1.769 |
offense | +1.751 |
Neg logit contributions | |
cius | -2.604 |
rapes | -1.865 |
lic | -1.821 |
Comes | -1.802 |
:= | -1.784 |
Token | , |
Token ID | 11 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
hesda | +0.490 |
Arizona | +0.464 |
anyahu | +0.455 |
Catal | +0.428 |
orno | +0.423 |
Neg logit contributions | |
cius | -0.498 |
rapes | -0.342 |
lic | -0.336 |
Comes | -0.333 |
:= | -0.325 |
Token | beginning |
Token ID | 3726 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
cius | +0.015 |
rapes | +0.010 |
lic | +0.010 |
Comes | +0.010 |
:= | +0.010 |
Neg logit contributions | |
hesda | -0.014 |
Arizona | -0.014 |
anyahu | -0.014 |
orno | -0.013 |
Catal | -0.013 |
Token | with |
Token ID | 351 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
hesda | +0.219 |
Arizona | +0.208 |
anyahu | +0.205 |
Catal | +0.193 |
orno | +0.191 |
Neg logit contributions | |
cius | -0.206 |
rapes | -0.140 |
lic | -0.136 |
Comes | -0.135 |
:= | -0.133 |
Token | the |
Token ID | 262 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
hesda | +0.286 |
Arizona | +0.269 |
anyahu | +0.267 |
Catal | +0.246 |
orno | +0.244 |
Neg logit contributions | |
cius | -0.327 |
rapes | -0.231 |
lic | -0.229 |
Comes | -0.228 |
:= | -0.221 |
Token | about |
Token ID | 546 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
hesda | +0.248 |
Arizona | +0.236 |
anyahu | +0.230 |
Catal | +0.219 |
offense | +0.216 |
Neg logit contributions | |
cius | -0.254 |
rapes | -0.175 |
lic | -0.171 |
Comes | -0.168 |
:= | -0.165 |
Token | the |
Token ID | 262 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
hesda | +0.532 |
Arizona | +0.505 |
anyahu | +0.491 |
Catal | +0.467 |
offense | +0.460 |
Neg logit contributions | |
cius | -0.610 |
rapes | -0.429 |
lic | -0.420 |
Comes | -0.414 |
:= | -0.408 |
Token | Trump |
Token ID | 1301 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
hesda | +0.204 |
Arizona | +0.193 |
anyahu | +0.188 |
Catal | +0.178 |
orno | +0.175 |
Neg logit contributions | |
cius | -0.241 |
rapes | -0.172 |
lic | -0.168 |
Comes | -0.165 |
:= | -0.162 |
Token | Free |
Token ID | 3232 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
hesda | +0.201 |
Arizona | +0.189 |
anyahu | +0.183 |
Catal | +0.173 |
offense | +0.169 |
Neg logit contributions | |
cius | -0.293 |
rapes | -0.215 |
lic | -0.211 |
Comes | -0.209 |
:= | -0.205 |
Token | Speech |
Token ID | 24709 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
cius | +0.278 |
rapes | +0.202 |
lic | +0.199 |
Comes | +0.197 |
:= | +0.194 |
Neg logit contributions | |
hesda | -0.199 |
Arizona | -0.187 |
anyahu | -0.182 |
Catal | -0.171 |
offense | -0.169 |
Token | Rally |
Token ID | 27752 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
hesda | +0.609 |
Arizona | +0.581 |
anyahu | +0.568 |
Catal | +0.542 |
orno | +0.533 |
Neg logit contributions | |
cius | -0.572 |
rapes | -0.386 |
lic | -0.378 |
Comes | -0.373 |
:= | -0.364 |
Token | as |
Token ID | 355 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
hesda | +2.216 |
Arizona | +2.112 |
anyahu | +2.051 |
Catal | +1.958 |
offense | +1.940 |
Neg logit contributions | |
cius | -2.350 |
rapes | -1.621 |
lic | -1.588 |
Comes | -1.565 |
:= | -1.543 |
Token | most |
Token ID | 749 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
cius | +0.217 |
rapes | +0.150 |
lic | +0.146 |
Comes | +0.144 |
:= | +0.141 |
Neg logit contributions | |
hesda | -0.207 |
Arizona | -0.197 |
anyahu | -0.193 |
Catal | -0.183 |
offense | -0.180 |
Token | other |
Token ID | 584 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
hesda | +0.422 |
Arizona | +0.403 |
anyahu | +0.393 |
Catal | +0.376 |
offense | +0.372 |
Neg logit contributions | |
cius | -0.396 |
rapes | -0.266 |
lic | -0.259 |
Comes | -0.256 |
:= | -0.251 |
Token | sane |
Token ID | 33241 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
cius | +0.495 |
rapes | +0.343 |
lic | +0.333 |
Comes | +0.329 |
:= | +0.322 |
Neg logit contributions | |
hesda | -0.484 |
Arizona | -0.458 |
anyahu | -0.450 |
Catal | -0.428 |
offense | -0.419 |
Token | , |
Token ID | 11 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
cius | +0.522 |
rapes | +0.348 |
lic | +0.337 |
Comes | +0.331 |
:= | +0.323 |
Neg logit contributions | |
hesda | -0.595 |
Arizona | -0.564 |
anyahu | -0.555 |
Catal | -0.531 |
orno | -0.520 |
Token |
|
Token ID | 198 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
hesda | +0.173 |
Arizona | +0.164 |
anyahu | +0.161 |
Catal | +0.152 |
offense | +0.151 |
Neg logit contributions | |
cius | -0.181 |
rapes | -0.125 |
lic | -0.123 |
Comes | -0.121 |
:= | -0.119 |
Token |
|
Token ID | 198 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
hesda | +0.524 |
anyahu | +0.486 |
Arizona | +0.483 |
orno | +0.453 |
offense | +0.453 |
Neg logit contributions | |
cius | -0.482 |
lic | -0.330 |
rapes | -0.329 |
:= | -0.322 |
Comes | -0.320 |
Token | The |
Token ID | 464 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
hesda | +0.493 |
Arizona | +0.457 |
anyahu | +0.453 |
offense | +0.425 |
orno | +0.422 |
Neg logit contributions | |
cius | -0.591 |
rapes | -0.418 |
lic | -0.418 |
Comes | -0.406 |
:= | -0.404 |
Token | Orbital |
Token ID | 45453 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
hesda | +0.295 |
Arizona | +0.277 |
anyahu | +0.272 |
Catal | +0.255 |
orno | +0.251 |
Neg logit contributions | |
cius | -0.395 |
rapes | -0.287 |
lic | -0.284 |
Comes | -0.279 |
:= | -0.274 |
Token | ATK |
Token ID | 24526 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
cius | +0.022 |
rapes | +0.016 |
lic | +0.016 |
Comes | +0.016 |
:= | +0.016 |
Neg logit contributions | |
hesda | -0.014 |
Arizona | -0.013 |
anyahu | -0.012 |
Catal | -0.012 |
orno | -0.011 |
Token | Cy |
Token ID | 5934 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
hesda | +2.306 |
Arizona | +2.186 |
anyahu | +2.108 |
Catal | +2.010 |
offense | +1.997 |
Neg logit contributions | |
cius | -2.987 |
rapes | -2.141 |
lic | -2.092 |
Comes | -2.070 |
:= | -2.052 |
Token | gn |
Token ID | 4593 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
hesda | +1.624 |
Arizona | +1.514 |
anyahu | +1.461 |
Catal | +1.367 |
offense | +1.348 |
Neg logit contributions | |
cius | -2.952 |
rapes | -2.214 |
lic | -2.207 |
Comes | -2.163 |
:= | -2.143 |
Token | us |
Token ID | 385 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
cius | +1.190 |
lic | +0.843 |
rapes | +0.834 |
Comes | +0.816 |
esian | +0.816 |
Neg logit contributions | |
hesda | -0.963 |
Arizona | -0.912 |
anyahu | -0.891 |
Catal | -0.854 |
offense | -0.830 |
Token | , |
Token ID | 11 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
hesda | +0.807 |
Arizona | +0.760 |
anyahu | +0.738 |
Catal | +0.694 |
offense | +0.679 |
Neg logit contributions | |
cius | -1.160 |
rapes | -0.847 |
lic | -0.834 |
Comes | -0.827 |
:= | -0.813 |
Token | on |
Token ID | 319 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
hesda | +0.451 |
Arizona | +0.426 |
anyahu | +0.416 |
Catal | +0.393 |
offense | +0.386 |
Neg logit contributions | |
cius | -0.537 |
rapes | -0.381 |
lic | -0.375 |
Comes | -0.370 |
:= | -0.363 |
Token | a |
Token ID | 257 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
hesda | +0.379 |
Arizona | +0.355 |
anyahu | +0.351 |
Catal | +0.328 |
orno | +0.325 |
Neg logit contributions | |
cius | -0.443 |
rapes | -0.313 |
lic | -0.311 |
Comes | -0.305 |
:= | -0.296 |
Token | LO |
Token ID | 17579 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
cius | +0.284 |
rapes | +0.192 |
lic | +0.187 |
Comes | +0.186 |
:= | +0.183 |
Neg logit contributions | |
hesda | -0.303 |
Arizona | -0.287 |
anyahu | -0.281 |
Catal | -0.267 |
offense | -0.264 |
Token | OM |
Token ID | 2662 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
hesda | +0.423 |
Arizona | +0.399 |
anyahu | +0.393 |
Catal | +0.372 |
orno | +0.370 |
Neg logit contributions | |
cius | -0.378 |
rapes | -0.253 |
lic | -0.248 |
Comes | -0.244 |
:= | -0.241 |
Token |
|
Token ID | 198 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
cius | +0.655 |
rapes | +0.437 |
Comes | +0.428 |
lic | +0.428 |
:= | +0.418 |
Neg logit contributions | |
hesda | -0.760 |
Arizona | -0.715 |
anyahu | -0.708 |
Catal | -0.670 |
orno | -0.666 |
Token |
|
Token ID | 198 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
cius | +0.369 |
lic | +0.253 |
rapes | +0.251 |
:= | +0.247 |
Comes | +0.245 |
Neg logit contributions | |
hesda | -0.416 |
anyahu | -0.384 |
Arizona | -0.381 |
offense | -0.358 |
orno | -0.358 |
Token | Ra |
Token ID | 21762 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
cius | +0.458 |
lic | +0.329 |
rapes | +0.325 |
Comes | +0.317 |
:= | +0.316 |
Neg logit contributions | |
hesda | -0.377 |
anyahu | -0.341 |
Arizona | -0.337 |
offense | -0.322 |
orno | -0.318 |
Token | ising |
Token ID | 1710 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
cius | +0.489 |
lic | +0.317 |
rapes | +0.315 |
Comes | +0.304 |
:= | +0.301 |
Neg logit contributions | |
hesda | -0.583 |
Arizona | -0.556 |
anyahu | -0.544 |
Catal | -0.525 |
offense | -0.516 |
Token | the |
Token ID | 262 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
cius | +1.712 |
rapes | +1.190 |
lic | +1.158 |
Comes | +1.140 |
:= | +1.121 |
Neg logit contributions | |
hesda | -1.607 |
Arizona | -1.514 |
anyahu | -1.486 |
Catal | -1.409 |
orno | -1.387 |
Token | debt |
Token ID | 5057 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
hesda | +0.009 |
Arizona | +0.008 |
anyahu | +0.008 |
Catal | +0.008 |
orno | +0.008 |
Neg logit contributions | |
cius | -0.010 |
rapes | -0.007 |
lic | -0.007 |
Comes | -0.007 |
:= | -0.007 |
Token | ceiling |
Token ID | 13387 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
cius | +0.074 |
rapes | +0.041 |
lic | +0.039 |
Comes | +0.039 |
:= | +0.037 |
Neg logit contributions | |
hesda | -0.140 |
Arizona | -0.134 |
anyahu | -0.132 |
Catal | -0.128 |
orno | -0.126 |
Token | is |
Token ID | 318 |
Feature activation | -8.02e-02 |
Pos logit contributions | |
hesda | +0.425 |
Arizona | +0.400 |
anyahu | +0.391 |
Catal | +0.371 |
orno | +0.366 |
Neg logit contributions | |
cius | -0.497 |
rapes | -0.360 |
Comes | -0.349 |
lic | -0.348 |
:= | -0.342 |
Token | one |
Token ID | 530 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
hesda | +0.059 |
Arizona | +0.055 |
anyahu | +0.054 |
Catal | +0.051 |
orno | +0.050 |
Neg logit contributions | |
cius | -0.078 |
rapes | -0.056 |
lic | -0.056 |
Comes | -0.055 |
:= | -0.054 |
Token | Foundation |
Token ID | 5693 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
hesda | +0.268 |
Arizona | +0.253 |
anyahu | +0.247 |
Catal | +0.234 |
orno | +0.233 |
Neg logit contributions | |
cius | -0.264 |
rapes | -0.180 |
lic | -0.179 |
Comes | -0.177 |
:= | -0.174 |
Token | ( |
Token ID | 357 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
hesda | +0.320 |
Arizona | +0.305 |
anyahu | +0.297 |
Catal | +0.284 |
offense | +0.281 |
Neg logit contributions | |
cius | -0.332 |
rapes | -0.228 |
lic | -0.223 |
Comes | -0.219 |
:= | -0.217 |
Token | NS |
Token ID | 8035 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
cius | +0.146 |
rapes | +0.096 |
lic | +0.095 |
Comes | +0.092 |
:= | +0.092 |
Neg logit contributions | |
hesda | -0.165 |
Arizona | -0.156 |
anyahu | -0.153 |
Catal | -0.146 |
offense | -0.146 |
Token | F |
Token ID | 37 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
cius | +0.477 |
rapes | +0.331 |
:= | +0.330 |
lic | +0.329 |
Comes | +0.324 |
Neg logit contributions | |
hesda | -0.468 |
anyahu | -0.434 |
Arizona | -0.428 |
orno | -0.404 |
Catal | -0.396 |
Token | ), |
Token ID | 828 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
cius | +0.791 |
rapes | +0.535 |
lic | +0.522 |
Comes | +0.513 |
:= | +0.508 |
Neg logit contributions | |
hesda | -0.815 |
Arizona | -0.779 |
anyahu | -0.760 |
Catal | -0.727 |
offense | -0.720 |
Token | nearly |
Token ID | 3016 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
cius | +0.140 |
rapes | +0.100 |
lic | +0.097 |
Comes | +0.096 |
:= | +0.095 |
Neg logit contributions | |
hesda | -0.116 |
Arizona | -0.110 |
anyahu | -0.107 |
Catal | -0.101 |
offense | -0.099 |
Token | 70 |
Token ID | 4317 |
Feature activation | +9.84e-01 |
Pos logit contributions | |
cius | +1.660 |
rapes | +1.219 |
lic | +1.181 |
Comes | +1.167 |
:= | +1.145 |
Neg logit contributions | |
hesda | -1.344 |
Arizona | -1.253 |
anyahu | -1.234 |
Catal | -1.146 |
orno | -1.127 |
Token | % |
Token ID | 4 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
cius | +0.922 |
rapes | +0.659 |
lic | +0.643 |
Comes | +0.630 |
:= | +0.626 |
Neg logit contributions | |
hesda | -0.758 |
Arizona | -0.716 |
anyahu | -0.695 |
Catal | -0.656 |
offense | -0.647 |
Token | of |
Token ID | 286 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
hesda | +0.192 |
Arizona | +0.189 |
anyahu | +0.183 |
offense | +0.176 |
Catal | +0.175 |
Neg logit contributions | |
cius | -0.177 |
rapes | -0.117 |
Comes | -0.117 |
lic | -0.116 |
esian | -0.111 |
Token | South |
Token ID | 2520 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
cius | +0.324 |
rapes | +0.225 |
lic | +0.220 |
Comes | +0.217 |
:= | +0.214 |
Neg logit contributions | |
hesda | -0.300 |
Arizona | -0.286 |
anyahu | -0.278 |
Catal | -0.264 |
offense | -0.261 |
Token | Koreans |
Token ID | 25999 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
cius | +0.196 |
rapes | +0.133 |
lic | +0.130 |
Comes | +0.128 |
:= | +0.126 |
Neg logit contributions | |
hesda | -0.189 |
Arizona | -0.180 |
anyahu | -0.174 |
Catal | -0.169 |
offense | -0.168 |
Token | the |
Token ID | 262 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
cius | +0.402 |
rapes | +0.280 |
lic | +0.276 |
Comes | +0.270 |
:= | +0.266 |
Neg logit contributions | |
hesda | -0.375 |
Arizona | -0.355 |
anyahu | -0.349 |
Catal | -0.329 |
orno | -0.326 |
Token | reality |
Token ID | 3950 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
cius | +0.142 |
rapes | +0.102 |
lic | +0.099 |
Comes | +0.097 |
:= | +0.096 |
Neg logit contributions | |
hesda | -0.124 |
Arizona | -0.116 |
anyahu | -0.115 |
Catal | -0.108 |
orno | -0.107 |
Token | is |
Token ID | 318 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
cius | +0.547 |
rapes | +0.383 |
lic | +0.375 |
Comes | +0.371 |
:= | +0.364 |
Neg logit contributions | |
hesda | -0.495 |
Arizona | -0.470 |
anyahu | -0.457 |
Catal | -0.436 |
offense | -0.429 |
Token | that |
Token ID | 326 |
Feature activation | +6.27e-02 |
Pos logit contributions | |
cius | +0.195 |
rapes | +0.138 |
lic | +0.135 |
Comes | +0.133 |
:= | +0.131 |
Neg logit contributions | |
hesda | -0.170 |
Arizona | -0.161 |
anyahu | -0.158 |
Catal | -0.149 |
offense | -0.146 |
Token | body |
Token ID | 1767 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
cius | +0.058 |
rapes | +0.041 |
lic | +0.040 |
Comes | +0.039 |
:= | +0.039 |
Neg logit contributions | |
hesda | -0.049 |
Arizona | -0.046 |
anyahu | -0.046 |
Catal | -0.043 |
orno | -0.042 |
Token | art |
Token ID | 1242 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
cius | +1.052 |
rapes | +0.770 |
lic | +0.758 |
Comes | +0.728 |
:= | +0.728 |
Neg logit contributions | |
hesda | -0.816 |
Arizona | -0.771 |
anyahu | -0.754 |
Catal | -0.714 |
NPR | -0.685 |
Token | is |
Token ID | 318 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
cius | +1.633 |
rapes | +1.143 |
lic | +1.127 |
Comes | +1.097 |
:= | +1.089 |
Neg logit contributions | |
hesda | -1.575 |
Arizona | -1.491 |
anyahu | -1.479 |
Catal | -1.393 |
orno | -1.351 |
Token | much |
Token ID | 881 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
cius | +0.102 |
rapes | +0.074 |
lic | +0.072 |
Comes | +0.070 |
:= | +0.070 |
Neg logit contributions | |
hesda | -0.084 |
Arizona | -0.079 |
anyahu | -0.078 |
Catal | -0.073 |
orno | -0.071 |
Token | more |
Token ID | 517 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
cius | +0.520 |
rapes | +0.384 |
lic | +0.380 |
Comes | +0.370 |
:= | +0.366 |
Neg logit contributions | |
hesda | -0.357 |
Arizona | -0.336 |
anyahu | -0.326 |
Catal | -0.305 |
offense | -0.296 |
Token | complex |
Token ID | 3716 |
Feature activation | -5.66e-02 |
Pos logit contributions | |
cius | +0.568 |
rapes | +0.411 |
lic | +0.405 |
Comes | +0.396 |
:= | +0.394 |
Neg logit contributions | |
hesda | -0.436 |
Arizona | -0.412 |
anyahu | -0.402 |
Catal | -0.378 |
offense | -0.367 |
Token | than |
Token ID | 621 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
hesda | +0.044 |
Arizona | +0.042 |
anyahu | +0.041 |
Catal | +0.039 |
offense | +0.038 |
Neg logit contributions | |
cius | -0.052 |
rapes | -0.037 |
lic | -0.036 |
Comes | -0.035 |
:= | -0.035 |
Token | manager |
Token ID | 4706 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
cius | +0.012 |
rapes | +0.008 |
lic | +0.008 |
Comes | +0.008 |
:= | +0.008 |
Neg logit contributions | |
hesda | -0.011 |
Arizona | -0.011 |
anyahu | -0.011 |
Catal | -0.010 |
orno | -0.010 |
Token | — |
Token ID | 851 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
cius | +0.177 |
rapes | +0.124 |
lic | +0.121 |
Comes | +0.120 |
:= | +0.118 |
Neg logit contributions | |
hesda | -0.164 |
Arizona | -0.155 |
anyahu | -0.151 |
Catal | -0.143 |
offense | -0.141 |
Token | and |
Token ID | 290 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
hesda | +0.409 |
Arizona | +0.387 |
anyahu | +0.378 |
Catal | +0.356 |
offense | +0.353 |
Neg logit contributions | |
cius | -0.468 |
rapes | -0.330 |
lic | -0.324 |
Comes | -0.320 |
:= | -0.314 |
Token | girlfriend |
Token ID | 11077 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
cius | +0.245 |
rapes | +0.174 |
lic | +0.172 |
Comes | +0.169 |
:= | +0.167 |
Neg logit contributions | |
hesda | -0.206 |
Arizona | -0.194 |
anyahu | -0.191 |
Catal | -0.178 |
orno | -0.177 |
Token | — |
Token ID | 851 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
hesda | +0.304 |
Arizona | +0.290 |
anyahu | +0.283 |
Catal | +0.270 |
offense | +0.267 |
Neg logit contributions | |
cius | -0.300 |
rapes | -0.204 |
lic | -0.200 |
Comes | -0.197 |
:= | -0.194 |
Token | sent |
Token ID | 1908 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
hesda | +0.314 |
Arizona | +0.296 |
anyahu | +0.289 |
Catal | +0.273 |
offense | +0.270 |
Neg logit contributions | |
cius | -0.357 |
rapes | -0.252 |
lic | -0.248 |
Comes | -0.245 |
:= | -0.240 |
Token | out |
Token ID | 503 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
cius | +1.609 |
rapes | +1.156 |
lic | +1.137 |
Comes | +1.126 |
:= | +1.105 |
Neg logit contributions | |
hesda | -1.346 |
Arizona | -1.256 |
anyahu | -1.236 |
Catal | -1.148 |
orno | -1.142 |
Token | an |
Token ID | 281 |
Feature activation | -4.83e-02 |
Pos logit contributions | |
hesda | +0.008 |
Arizona | +0.007 |
anyahu | +0.007 |
Catal | +0.007 |
offense | +0.006 |
Neg logit contributions | |
cius | -0.010 |
rapes | -0.008 |
lic | -0.008 |
Comes | -0.007 |
:= | -0.007 |
Token | e |
Token ID | 304 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
hesda | +0.042 |
Arizona | +0.040 |
anyahu | +0.039 |
Catal | +0.038 |
orno | +0.037 |
Neg logit contributions | |
cius | -0.040 |
rapes | -0.027 |
lic | -0.026 |
Comes | -0.026 |
:= | -0.026 |
Token | - |
Token ID | 12 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
cius | +0.814 |
lic | +0.588 |
rapes | +0.587 |
Comes | +0.573 |
:= | +0.569 |
Neg logit contributions | |
hesda | -0.586 |
Arizona | -0.549 |
anyahu | -0.533 |
Catal | -0.496 |
offense | -0.494 |
Token | mail |
Token ID | 4529 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
cius | +0.103 |
lic | +0.071 |
rapes | +0.071 |
Comes | +0.069 |
:= | +0.068 |
Neg logit contributions | |
hesda | -0.099 |
Arizona | -0.093 |
anyahu | -0.091 |
offense | -0.086 |
Catal | -0.086 |
Token | seem |
Token ID | 1283 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
hesda | +0.221 |
Arizona | +0.208 |
anyahu | +0.203 |
Catal | +0.193 |
orno | +0.189 |
Neg logit contributions | |
cius | -0.265 |
rapes | -0.189 |
lic | -0.185 |
Comes | -0.181 |
:= | -0.180 |
Token | to |
Token ID | 284 |
Feature activation | -7.40e-02 |
Pos logit contributions | |
cius | +0.224 |
rapes | +0.152 |
lic | +0.148 |
Comes | +0.145 |
:= | +0.142 |
Neg logit contributions | |
hesda | -0.239 |
Arizona | -0.228 |
anyahu | -0.223 |
Catal | -0.213 |
offense | -0.209 |
Token | think |
Token ID | 892 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
hesda | +0.058 |
Arizona | +0.055 |
anyahu | +0.053 |
Catal | +0.051 |
orno | +0.049 |
Neg logit contributions | |
cius | -0.069 |
rapes | -0.049 |
lic | -0.048 |
Comes | -0.047 |
:= | -0.046 |
Token | that |
Token ID | 326 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
cius | +0.482 |
rapes | +0.343 |
lic | +0.332 |
Comes | +0.328 |
:= | +0.321 |
Neg logit contributions | |
hesda | -0.433 |
Arizona | -0.410 |
anyahu | -0.399 |
Catal | -0.380 |
orno | -0.371 |
Token | the |
Token ID | 262 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
hesda | +0.262 |
Arizona | +0.247 |
anyahu | +0.241 |
Catal | +0.228 |
offense | +0.223 |
Neg logit contributions | |
cius | -0.316 |
rapes | -0.228 |
lic | -0.222 |
Comes | -0.219 |
:= | -0.215 |
Token | oil |
Token ID | 3056 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
cius | +0.023 |
rapes | +0.017 |
lic | +0.016 |
Comes | +0.016 |
:= | +0.016 |
Neg logit contributions | |
hesda | -0.019 |
Arizona | -0.018 |
anyahu | -0.017 |
Catal | -0.016 |
orno | -0.016 |
Token | industry |
Token ID | 2831 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
cius | +1.845 |
rapes | +1.336 |
lic | +1.283 |
Comes | +1.264 |
esian | +1.213 |
Neg logit contributions | |
hesda | -1.829 |
Arizona | -1.727 |
anyahu | -1.687 |
Catal | -1.609 |
orno | -1.599 |
Token | knows |
Token ID | 4206 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
cius | +0.230 |
rapes | +0.164 |
lic | +0.158 |
Comes | +0.156 |
:= | +0.154 |
Neg logit contributions | |
hesda | -0.209 |
Arizona | -0.199 |
anyahu | -0.193 |
Catal | -0.184 |
orno | -0.180 |
Token | best |
Token ID | 1266 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
cius | +0.581 |
rapes | +0.415 |
lic | +0.402 |
Comes | +0.394 |
:= | +0.389 |
Neg logit contributions | |
hesda | -0.533 |
Arizona | -0.500 |
anyahu | -0.489 |
Catal | -0.461 |
orno | -0.452 |
Token | and |
Token ID | 290 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
hesda | +0.511 |
Arizona | +0.487 |
anyahu | +0.474 |
Catal | +0.453 |
offense | +0.448 |
Neg logit contributions | |
cius | -0.515 |
rapes | -0.352 |
lic | -0.344 |
Comes | -0.339 |
:= | -0.334 |
Token | can |
Token ID | 460 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
hesda | +0.316 |
Arizona | +0.301 |
anyahu | +0.293 |
Catal | +0.279 |
offense | +0.273 |
Neg logit contributions | |
cius | -0.350 |
rapes | -0.248 |
lic | -0.240 |
Comes | -0.237 |
:= | -0.233 |
Token | S |
Token ID | 50 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
hesda | +0.799 |
anyahu | +0.736 |
Arizona | +0.713 |
orno | +0.701 |
offense | +0.696 |
Neg logit contributions | |
cius | -0.687 |
lic | -0.469 |
:= | -0.463 |
rapes | -0.461 |
Comes | -0.457 |
Token | . |
Token ID | 13 |
Feature activation | +7.42e-02 |
Pos logit contributions | |
hesda | +0.487 |
Arizona | +0.460 |
anyahu | +0.454 |
Catal | +0.432 |
offense | +0.428 |
Neg logit contributions | |
cius | -0.419 |
rapes | -0.275 |
lic | -0.271 |
Comes | -0.267 |
:= | -0.265 |
Token | Senate |
Token ID | 3845 |
Feature activation | -8.63e-02 |
Pos logit contributions | |
cius | +0.070 |
rapes | +0.050 |
lic | +0.049 |
Comes | +0.049 |
:= | +0.048 |
Neg logit contributions | |
hesda | -0.057 |
Arizona | -0.053 |
anyahu | -0.052 |
Catal | -0.049 |
offense | -0.048 |
Token | at |
Token ID | 379 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
hesda | +0.075 |
Arizona | +0.070 |
anyahu | +0.070 |
Catal | +0.066 |
orno | +0.065 |
Neg logit contributions | |
cius | -0.072 |
rapes | -0.049 |
lic | -0.048 |
Comes | -0.048 |
:= | -0.047 |
Token | Earth |
Token ID | 3668 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
hesda | +0.213 |
Arizona | +0.199 |
anyahu | +0.197 |
Catal | +0.183 |
orno | +0.182 |
Neg logit contributions | |
cius | -0.246 |
rapes | -0.172 |
lic | -0.171 |
Comes | -0.169 |
:= | -0.164 |
Token | Friendly |
Token ID | 38683 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
hesda | +0.870 |
Arizona | +0.825 |
anyahu | +0.805 |
Catal | +0.768 |
offense | +0.761 |
Neg logit contributions | |
cius | -0.915 |
rapes | -0.626 |
lic | -0.617 |
Comes | -0.609 |
:= | -0.597 |
Token | Products |
Token ID | 18675 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
cius | +0.573 |
rapes | +0.397 |
lic | +0.394 |
Comes | +0.391 |
:= | +0.379 |
Neg logit contributions | |
hesda | -0.530 |
Arizona | -0.496 |
anyahu | -0.489 |
Catal | -0.461 |
offense | -0.459 |
Token | packaging |
Token ID | 16846 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
hesda | +0.588 |
Arizona | +0.555 |
anyahu | +0.545 |
Catal | +0.513 |
orno | +0.511 |
Neg logit contributions | |
cius | -0.622 |
rapes | -0.430 |
lic | -0.426 |
Comes | -0.423 |
:= | -0.413 |
Token | plant |
Token ID | 4618 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
hesda | +0.347 |
Arizona | +0.328 |
anyahu | +0.321 |
Catal | +0.302 |
orno | +0.301 |
Neg logit contributions | |
cius | -0.389 |
rapes | -0.276 |
lic | -0.271 |
Comes | -0.269 |
:= | -0.263 |
Token | on |
Token ID | 319 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
hesda | +1.672 |
Arizona | +1.589 |
anyahu | +1.552 |
Catal | +1.469 |
offense | +1.449 |
Neg logit contributions | |
cius | -1.842 |
rapes | -1.289 |
lic | -1.263 |
Comes | -1.251 |
:= | -1.226 |
Token | November |
Token ID | 3389 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
cius | +0.209 |
rapes | +0.154 |
lic | +0.153 |
Comes | +0.152 |
:= | +0.147 |
Neg logit contributions | |
hesda | -0.149 |
Arizona | -0.137 |
anyahu | -0.136 |
orno | -0.126 |
Catal | -0.125 |
Token | very |
Token ID | 845 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
hesda | +0.187 |
Arizona | +0.178 |
anyahu | +0.173 |
Catal | +0.163 |
offense | +0.159 |
Neg logit contributions | |
cius | -0.235 |
rapes | -0.169 |
lic | -0.166 |
Comes | -0.164 |
:= | -0.162 |
Token | inefficient |
Token ID | 30904 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
hesda | +0.401 |
Arizona | +0.380 |
anyahu | +0.368 |
Catal | +0.348 |
offense | +0.341 |
Neg logit contributions | |
cius | -0.515 |
rapes | -0.371 |
lic | -0.364 |
Comes | -0.359 |
:= | -0.355 |
Token | solution |
Token ID | 4610 |
Feature activation | +5.68e-02 |
Pos logit contributions | |
cius | +0.158 |
rapes | +0.112 |
lic | +0.111 |
Comes | +0.109 |
:= | +0.109 |
Neg logit contributions | |
hesda | -0.134 |
Arizona | -0.127 |
anyahu | -0.124 |
Catal | -0.116 |
orno | -0.114 |
Token | . |
Token ID | 13 |
Feature activation | -6.04e-02 |
Pos logit contributions | |
cius | +0.048 |
rapes | +0.033 |
lic | +0.032 |
Comes | +0.031 |
:= | +0.031 |
Neg logit contributions | |
hesda | -0.049 |
Arizona | -0.047 |
anyahu | -0.045 |
Catal | -0.043 |
offense | -0.043 |
Token | If |
Token ID | 1002 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
hesda | +0.055 |
Arizona | +0.052 |
anyahu | +0.052 |
Catal | +0.049 |
offense | +0.048 |
Neg logit contributions | |
cius | -0.048 |
rapes | -0.031 |
lic | -0.031 |
Comes | -0.031 |
:= | -0.030 |
Token | we |
Token ID | 356 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
cius | +0.441 |
rapes | +0.305 |
lic | +0.300 |
Comes | +0.297 |
:= | +0.292 |
Neg logit contributions | |
hesda | -0.412 |
Arizona | -0.392 |
anyahu | -0.381 |
Catal | -0.361 |
offense | -0.357 |
Token | implement |
Token ID | 3494 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
cius | +0.164 |
rapes | +0.117 |
lic | +0.114 |
Comes | +0.113 |
:= | +0.112 |
Neg logit contributions | |
hesda | -0.140 |
Arizona | -0.132 |
anyahu | -0.129 |
Catal | -0.122 |
offense | -0.119 |
Token | a |
Token ID | 257 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
cius | +0.102 |
rapes | +0.073 |
lic | +0.072 |
Comes | +0.071 |
:= | +0.071 |
Neg logit contributions | |
hesda | -0.082 |
Arizona | -0.077 |
anyahu | -0.075 |
Catal | -0.070 |
offense | -0.069 |
Token | copy |
Token ID | 4866 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
hesda | +0.041 |
Arizona | +0.039 |
anyahu | +0.038 |
Catal | +0.036 |
offense | +0.036 |
Neg logit contributions | |
cius | -0.041 |
rapes | -0.028 |
lic | -0.028 |
Comes | -0.028 |
:= | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +5.40e-02 |
Pos logit contributions | |
hesda | +0.130 |
Arizona | +0.124 |
anyahu | +0.121 |
Catal | +0.115 |
offense | +0.114 |
Neg logit contributions | |
cius | -0.127 |
rapes | -0.086 |
lic | -0.085 |
Comes | -0.083 |
:= | -0.082 |
Token | apply |
Token ID | 4174 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
cius | +0.047 |
rapes | +0.033 |
lic | +0.032 |
Comes | +0.032 |
:= | +0.032 |
Neg logit contributions | |
hesda | -0.044 |
Arizona | -0.042 |
anyahu | -0.041 |
Catal | -0.039 |
offense | -0.038 |
Token | monitor |
Token ID | 5671 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
cius | +0.002 |
rapes | +0.001 |
lic | +0.001 |
Comes | +0.001 |
:= | +0.001 |
Neg logit contributions | |
hesda | -0.002 |
Arizona | -0.002 |
anyahu | -0.002 |
Catal | -0.002 |
offense | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +7.18e-02 |
Pos logit contributions | |
cius | +0.152 |
rapes | +0.104 |
lic | +0.102 |
Comes | +0.101 |
:= | +0.099 |
Neg logit contributions | |
hesda | -0.149 |
Arizona | -0.143 |
anyahu | -0.139 |
Catal | -0.132 |
offense | -0.130 |
Token | note |
Token ID | 3465 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
cius | +0.066 |
rapes | +0.047 |
lic | +0.046 |
Comes | +0.046 |
:= | +0.045 |
Neg logit contributions | |
hesda | -0.056 |
Arizona | -0.053 |
anyahu | -0.052 |
Catal | -0.049 |
orno | -0.048 |
Token | the |
Token ID | 262 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
cius | +0.466 |
rapes | +0.325 |
lic | +0.317 |
Comes | +0.313 |
:= | +0.310 |
Neg logit contributions | |
hesda | -0.433 |
Arizona | -0.413 |
anyahu | -0.402 |
Catal | -0.382 |
orno | -0.375 |
Token | increase |
Token ID | 2620 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
cius | +0.158 |
rapes | +0.112 |
lic | +0.109 |
Comes | +0.108 |
:= | +0.107 |
Neg logit contributions | |
hesda | -0.135 |
Arizona | -0.129 |
anyahu | -0.125 |
Catal | -0.119 |
orno | -0.117 |
Token | in |
Token ID | 287 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
cius | +0.346 |
rapes | +0.228 |
lic | +0.223 |
Comes | +0.219 |
:= | +0.216 |
Neg logit contributions | |
hesda | -0.396 |
Arizona | -0.379 |
anyahu | -0.369 |
Catal | -0.354 |
offense | -0.350 |
Token | R |
Token ID | 371 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
cius | +0.115 |
rapes | +0.082 |
lic | +0.081 |
Comes | +0.080 |
:= | +0.079 |
Neg logit contributions | |
hesda | -0.093 |
Arizona | -0.088 |
anyahu | -0.085 |
Catal | -0.081 |
offense | -0.080 |
Token | FI |
Token ID | 11674 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
hesda | +0.142 |
Arizona | +0.132 |
anyahu | +0.129 |
offense | +0.121 |
Catal | +0.120 |
Neg logit contributions | |
cius | -0.202 |
lic | -0.149 |
:= | -0.146 |
rapes | -0.145 |
Comes | -0.141 |
Token | . |
Token ID | 13 |
Feature activation | +5.67e-02 |
Pos logit contributions | |
cius | +0.240 |
rapes | +0.162 |
lic | +0.158 |
Comes | +0.156 |
:= | +0.154 |
Neg logit contributions | |
hesda | -0.258 |
Arizona | -0.246 |
anyahu | -0.241 |
Catal | -0.230 |
orno | -0.225 |
Token | Run |
Token ID | 5660 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
cius | +0.044 |
rapes | +0.029 |
Comes | +0.028 |
lic | +0.028 |
:= | +0.027 |
Neg logit contributions | |
hesda | -0.053 |
Arizona | -0.050 |
anyahu | -0.049 |
Catal | -0.047 |
offense | -0.046 |
Token | both |
Token ID | 1111 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
hesda | +0.506 |
Arizona | +0.481 |
anyahu | +0.468 |
Catal | +0.444 |
offense | +0.437 |
Neg logit contributions | |
cius | -0.574 |
rapes | -0.404 |
lic | -0.397 |
Comes | -0.392 |
:= | -0.385 |
Token | getting |
Token ID | 1972 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
hesda | +0.132 |
Arizona | +0.125 |
anyahu | +0.122 |
Catal | +0.116 |
orno | +0.113 |
Neg logit contributions | |
cius | -0.162 |
rapes | -0.115 |
lic | -0.112 |
Comes | -0.111 |
:= | -0.109 |
Token | a |
Token ID | 257 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
hesda | +0.180 |
Arizona | +0.171 |
anyahu | +0.168 |
Catal | +0.160 |
orno | +0.155 |
Neg logit contributions | |
cius | -0.195 |
rapes | -0.138 |
lic | -0.135 |
Comes | -0.132 |
:= | -0.130 |
Token | job |
Token ID | 1693 |
Feature activation | +9.98e-01 |
Pos logit contributions | |
hesda | +0.359 |
Arizona | +0.341 |
anyahu | +0.331 |
Catal | +0.317 |
orno | +0.307 |
Neg logit contributions | |
cius | -0.451 |
rapes | -0.323 |
lic | -0.321 |
Comes | -0.312 |
:= | -0.309 |
Token | at |
Token ID | 379 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
cius | +0.838 |
rapes | +0.567 |
lic | +0.556 |
Comes | +0.542 |
:= | +0.540 |
Neg logit contributions | |
hesda | -0.854 |
Arizona | -0.823 |
anyahu | -0.803 |
Catal | -0.769 |
orno | -0.757 |
Token | the |
Token ID | 262 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
hesda | +0.015 |
Arizona | +0.014 |
anyahu | +0.014 |
Catal | +0.013 |
orno | +0.012 |
Neg logit contributions | |
cius | -0.027 |
rapes | -0.020 |
lic | -0.020 |
Comes | -0.020 |
:= | -0.020 |
Token | White |
Token ID | 2635 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
hesda | +0.009 |
Arizona | +0.008 |
anyahu | +0.008 |
Catal | +0.008 |
orno | +0.008 |
Neg logit contributions | |
cius | -0.010 |
rapes | -0.007 |
lic | -0.007 |
Comes | -0.007 |
:= | -0.006 |
Token | House |
Token ID | 2097 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
cius | +0.423 |
rapes | +0.290 |
Comes | +0.288 |
lic | +0.287 |
:= | +0.282 |
Neg logit contributions | |
hesda | -0.441 |
Arizona | -0.410 |
anyahu | -0.408 |
orno | -0.385 |
Catal | -0.384 |
Token | have |
Token ID | 423 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
hesda | +0.036 |
Arizona | +0.034 |
anyahu | +0.033 |
Catal | +0.031 |
orno | +0.031 |
Neg logit contributions | |
cius | -0.043 |
rapes | -0.030 |
lic | -0.030 |
Comes | -0.029 |
:= | -0.029 |
Token | mostly |
Token ID | 4632 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
hesda | +0.237 |
Arizona | +0.225 |
anyahu | +0.219 |
Catal | +0.208 |
orno | +0.203 |
Neg logit contributions | |
cius | -0.277 |
rapes | -0.198 |
lic | -0.193 |
Comes | -0.191 |
:= | -0.188 |
Token | focused |
Token ID | 5670 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
cius | +0.926 |
rapes | +0.665 |
lic | +0.650 |
Comes | +0.643 |
:= | +0.629 |
Neg logit contributions | |
hesda | -0.787 |
Arizona | -0.747 |
anyahu | -0.730 |
Catal | -0.692 |
orno | -0.677 |
Token | on |
Token ID | 319 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
hesda | +0.124 |
Arizona | +0.118 |
anyahu | +0.115 |
Catal | +0.110 |
offense | +0.109 |
Neg logit contributions | |
cius | -0.122 |
rapes | -0.083 |
lic | -0.081 |
Comes | -0.080 |
:= | -0.079 |
Token | attempting |
Token ID | 9361 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
cius | +0.260 |
rapes | +0.182 |
lic | +0.178 |
Comes | +0.176 |
:= | +0.172 |
Neg logit contributions | |
hesda | -0.239 |
Arizona | -0.225 |
anyahu | -0.223 |
Catal | -0.210 |
orno | -0.205 |
Token | to |
Token ID | 284 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
cius | +0.308 |
rapes | +0.209 |
lic | +0.205 |
Comes | +0.201 |
:= | +0.198 |
Neg logit contributions | |
hesda | -0.308 |
Arizona | -0.296 |
anyahu | -0.287 |
offense | -0.276 |
Catal | -0.274 |
Token | amend |
Token ID | 13582 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
hesda | +0.424 |
Arizona | +0.401 |
anyahu | +0.391 |
Catal | +0.372 |
offense | +0.364 |
Neg logit contributions | |
cius | -0.475 |
rapes | -0.333 |
lic | -0.326 |
Comes | -0.322 |
:= | -0.318 |
Token | the |
Token ID | 262 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
hesda | +0.258 |
Arizona | +0.245 |
anyahu | +0.238 |
Catal | +0.226 |
offense | +0.223 |
Neg logit contributions | |
cius | -0.303 |
rapes | -0.214 |
lic | -0.209 |
Comes | -0.207 |
:= | -0.204 |
Token | Greek |
Token ID | 8312 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
hesda | +0.044 |
Arizona | +0.042 |
anyahu | +0.041 |
Catal | +0.039 |
orno | +0.038 |
Neg logit contributions | |
cius | -0.054 |
rapes | -0.038 |
lic | -0.038 |
Comes | -0.037 |
:= | -0.037 |
Token | Council |
Token ID | 4281 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
cius | +0.193 |
rapes | +0.134 |
lic | +0.132 |
Comes | +0.130 |
:= | +0.128 |
Neg logit contributions | |
hesda | -0.175 |
Arizona | -0.166 |
anyahu | -0.162 |
Catal | -0.154 |
offense | -0.151 |
Token | constitution |
Token ID | 11784 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
cius | +0.680 |
rapes | +0.455 |
lic | +0.449 |
Comes | +0.438 |
:= | +0.429 |
Neg logit contributions | |
hesda | -0.745 |
Arizona | -0.707 |
anyahu | -0.693 |
Catal | -0.658 |
offense | -0.649 |
Token | concerning |
Token ID | 9305 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
hesda | +1.071 |
Arizona | +1.022 |
anyahu | +0.996 |
Catal | +0.951 |
offense | +0.941 |
Neg logit contributions | |
cius | -1.014 |
rapes | -0.682 |
lic | -0.667 |
Comes | -0.657 |
:= | -0.645 |
Token | organizations |
Token ID | 5745 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
cius | +0.398 |
rapes | +0.283 |
lic | +0.276 |
Comes | +0.272 |
:= | +0.267 |
Neg logit contributions | |
hesda | -0.339 |
Arizona | -0.319 |
anyahu | -0.313 |
Catal | -0.295 |
orno | -0.289 |
Token | that |
Token ID | 326 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
cius | +0.177 |
rapes | +0.121 |
lic | +0.119 |
Comes | +0.117 |
:= | +0.115 |
Neg logit contributions | |
hesda | -0.174 |
Arizona | -0.165 |
anyahu | -0.162 |
Catal | -0.153 |
orno | -0.151 |
Token | are |
Token ID | 389 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
hesda | +0.124 |
Arizona | +0.117 |
anyahu | +0.114 |
Catal | +0.108 |
orno | +0.106 |
Neg logit contributions | |
cius | -0.145 |
rapes | -0.103 |
lic | -0.100 |
Comes | -0.099 |
:= | -0.098 |
Token | up |
Token ID | 510 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
hesda | +0.528 |
Arizona | +0.496 |
anyahu | +0.490 |
Catal | +0.461 |
orno | +0.449 |
Neg logit contributions | |
cius | -0.621 |
rapes | -0.450 |
lic | -0.440 |
Comes | -0.431 |
:= | -0.424 |
Token | a |
Token ID | 257 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
hesda | +0.656 |
Arizona | +0.619 |
anyahu | +0.605 |
Catal | +0.570 |
orno | +0.556 |
Neg logit contributions | |
cius | -0.819 |
rapes | -0.591 |
lic | -0.578 |
Comes | -0.570 |
:= | -0.559 |
Token | smokes |
Token ID | 44589 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
hesda | +0.245 |
Arizona | +0.228 |
anyahu | +0.225 |
Catal | +0.210 |
orno | +0.204 |
Neg logit contributions | |
cius | -0.295 |
rapes | -0.213 |
lic | -0.212 |
Comes | -0.205 |
:= | -0.201 |
Token | creen |
Token ID | 32060 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
hesda | +0.783 |
Arizona | +0.717 |
anyahu | +0.692 |
Catal | +0.651 |
offense | +0.621 |
Neg logit contributions | |
cius | -1.546 |
lic | -1.175 |
rapes | -1.174 |
Comes | -1.148 |
:= | -1.129 |
Token | and |
Token ID | 290 |
Feature activation | +7.42e-02 |
Pos logit contributions | |
hesda | +0.464 |
Arizona | +0.442 |
anyahu | +0.431 |
Catal | +0.413 |
orno | +0.404 |
Neg logit contributions | |
cius | -0.446 |
rapes | -0.305 |
lic | -0.299 |
Comes | -0.293 |
:= | -0.288 |
Token | prevent |
Token ID | 2948 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
cius | +0.068 |
rapes | +0.049 |
lic | +0.047 |
Comes | +0.047 |
:= | +0.046 |
Neg logit contributions | |
hesda | -0.059 |
Arizona | -0.055 |
anyahu | -0.054 |
Catal | -0.051 |
orno | -0.050 |
Token | the |
Token ID | 262 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
hesda | +0.934 |
Arizona | +0.881 |
anyahu | +0.863 |
Catal | +0.817 |
orno | +0.800 |
Neg logit contributions | |
cius | -1.088 |
rapes | -0.777 |
lic | -0.759 |
Comes | -0.748 |
:= | -0.735 |
Token | group |
Token ID | 1448 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
hesda | +0.238 |
Arizona | +0.223 |
anyahu | +0.220 |
Catal | +0.207 |
orno | +0.204 |
Neg logit contributions | |
cius | -0.298 |
rapes | -0.216 |
lic | -0.212 |
Comes | -0.207 |
:= | -0.204 |
Token | from |
Token ID | 422 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
cius | +0.009 |
rapes | +0.006 |
lic | +0.006 |
Comes | +0.006 |
:= | +0.006 |
Neg logit contributions | |
hesda | -0.011 |
Arizona | -0.010 |
anyahu | -0.010 |
Catal | -0.010 |
offense | -0.010 |
Token | complaining |
Token ID | 18705 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
hesda | +0.453 |
Arizona | +0.426 |
anyahu | +0.422 |
Catal | +0.398 |
orno | +0.391 |
Neg logit contributions | |
cius | -0.509 |
rapes | -0.362 |
lic | -0.353 |
Comes | -0.348 |
:= | -0.342 |
Token | to |
Token ID | 284 |
Feature activation | +7.89e-02 |
Pos logit contributions | |
hesda | +1.002 |
Arizona | +0.955 |
anyahu | +0.930 |
Catal | +0.887 |
offense | +0.878 |
Neg logit contributions | |
cius | -1.012 |
rapes | -0.692 |
lic | -0.676 |
Comes | -0.667 |
:= | -0.656 |
Token | the |
Token ID | 262 |
Feature activation | +7.18e-02 |
Pos logit contributions | |
hesda | +0.089 |
Arizona | +0.084 |
anyahu | +0.082 |
Catal | +0.078 |
offense | +0.078 |
Neg logit contributions | |
cius | -0.088 |
rapes | -0.060 |
lic | -0.059 |
Comes | -0.058 |
:= | -0.057 |
Token | man |
Token ID | 582 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
cius | +0.065 |
rapes | +0.046 |
lic | +0.045 |
Comes | +0.044 |
:= | +0.044 |
Neg logit contributions | |
hesda | -0.057 |
Arizona | -0.054 |
anyahu | -0.053 |
Catal | -0.050 |
orno | -0.049 |
Token | facilitated |
Token ID | 35923 |
Feature activation | +6.80e-02 |
Pos logit contributions | |
hesda | +0.014 |
Arizona | +0.013 |
anyahu | +0.013 |
Catal | +0.013 |
offense | +0.012 |
Neg logit contributions | |
cius | -0.014 |
rapes | -0.010 |
lic | -0.009 |
Comes | -0.009 |
:= | -0.009 |
Token | payments |
Token ID | 7524 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
cius | +0.063 |
rapes | +0.045 |
lic | +0.044 |
Comes | +0.043 |
:= | +0.042 |
Neg logit contributions | |
hesda | -0.053 |
Arizona | -0.050 |
anyahu | -0.049 |
Catal | -0.046 |
orno | -0.046 |
Token | of |
Token ID | 286 |
Feature activation | +7.19e-02 |
Pos logit contributions | |
cius | +0.180 |
rapes | +0.119 |
lic | +0.116 |
Comes | +0.114 |
:= | +0.112 |
Neg logit contributions | |
hesda | -0.204 |
Arizona | -0.195 |
anyahu | -0.191 |
Catal | -0.182 |
offense | -0.180 |
Token | $ |
Token ID | 720 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
cius | +0.067 |
rapes | +0.047 |
lic | +0.047 |
Comes | +0.045 |
:= | +0.045 |
Neg logit contributions | |
hesda | -0.056 |
Arizona | -0.053 |
anyahu | -0.052 |
Catal | -0.049 |
orno | -0.048 |
Token | 17 |
Token ID | 1558 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
hesda | +0.108 |
Arizona | +0.100 |
anyahu | +0.100 |
offense | +0.093 |
orno | +0.092 |
Neg logit contributions | |
cius | -0.124 |
rapes | -0.088 |
lic | -0.087 |
Comes | -0.085 |
:= | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
hesda | +0.309 |
Arizona | +0.291 |
anyahu | +0.280 |
Catal | +0.265 |
offense | +0.261 |
Neg logit contributions | |
cius | -0.494 |
rapes | -0.365 |
lic | -0.358 |
Comes | -0.355 |
:= | -0.350 |
Token | 2 |
Token ID | 17 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
hesda | +0.571 |
Arizona | +0.533 |
anyahu | +0.524 |
offense | +0.492 |
Catal | +0.492 |
Neg logit contributions | |
cius | -0.668 |
rapes | -0.475 |
lic | -0.470 |
Comes | -0.463 |
:= | -0.457 |
Token | million |
Token ID | 1510 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
hesda | +0.510 |
Arizona | +0.479 |
anyahu | +0.457 |
Catal | +0.430 |
offense | +0.425 |
Neg logit contributions | |
cius | -0.927 |
rapes | -0.697 |
lic | -0.685 |
Comes | -0.681 |
:= | -0.671 |
Token | in |
Token ID | 287 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
cius | +0.654 |
rapes | +0.432 |
lic | +0.421 |
Comes | +0.412 |
:= | +0.406 |
Neg logit contributions | |
hesda | -0.752 |
Arizona | -0.717 |
anyahu | -0.703 |
Catal | -0.670 |
offense | -0.663 |
Token | almost |
Token ID | 2048 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
hesda | +0.016 |
Arizona | +0.016 |
anyahu | +0.015 |
Catal | +0.014 |
orno | +0.014 |
Neg logit contributions | |
cius | -0.019 |
rapes | -0.013 |
lic | -0.013 |
Comes | -0.013 |
:= | -0.013 |
Token | certainly |
Token ID | 3729 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
cius | +1.284 |
rapes | +0.935 |
lic | +0.924 |
:= | +0.902 |
Comes | +0.899 |
Neg logit contributions | |
hesda | -0.980 |
Arizona | -0.924 |
anyahu | -0.894 |
Catal | -0.848 |
orno | -0.826 |
Token | be |
Token ID | 307 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
cius | +0.804 |
rapes | +0.564 |
lic | +0.553 |
Comes | +0.547 |
:= | +0.541 |
Neg logit contributions | |
hesda | -0.721 |
Arizona | -0.685 |
anyahu | -0.668 |
Catal | -0.634 |
orno | -0.623 |
Token | part |
Token ID | 636 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
cius | +0.124 |
rapes | +0.088 |
lic | +0.086 |
Comes | +0.085 |
:= | +0.083 |
Neg logit contributions | |
hesda | -0.108 |
Arizona | -0.102 |
anyahu | -0.099 |
Catal | -0.094 |
orno | -0.092 |
Token | of |
Token ID | 286 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
cius | +0.419 |
rapes | +0.259 |
lic | +0.252 |
Comes | +0.245 |
:= | +0.241 |
Neg logit contributions | |
hesda | -0.597 |
Arizona | -0.573 |
anyahu | -0.559 |
Catal | -0.538 |
orno | -0.530 |
Token | national |
Token ID | 2260 |
Feature activation | -8.97e-01 |
Pos logit contributions | |
hesda | +0.012 |
Arizona | +0.012 |
anyahu | +0.011 |
Catal | +0.011 |
offense | +0.011 |
Neg logit contributions | |
cius | -0.015 |
rapes | -0.010 |
lic | -0.010 |
Comes | -0.010 |
:= | -0.010 |
Token | policy |
Token ID | 2450 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
hesda | +0.703 |
Arizona | +0.664 |
anyahu | +0.642 |
Catal | +0.608 |
orno | +0.596 |
Neg logit contributions | |
cius | -0.830 |
rapes | -0.596 |
lic | -0.583 |
Comes | -0.571 |
:= | -0.565 |
Token | in |
Token ID | 287 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
cius | +0.356 |
rapes | +0.243 |
lic | +0.236 |
Comes | +0.233 |
:= | +0.231 |
Neg logit contributions | |
hesda | -0.374 |
Arizona | -0.358 |
anyahu | -0.348 |
Catal | -0.332 |
orno | -0.325 |
Token | dozens |
Token ID | 9264 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
hesda | +0.377 |
Arizona | +0.356 |
anyahu | +0.349 |
Catal | +0.329 |
orno | +0.323 |
Neg logit contributions | |
cius | -0.449 |
rapes | -0.320 |
lic | -0.313 |
Comes | -0.309 |
:= | -0.304 |
Token | if |
Token ID | 611 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
cius | +0.785 |
rapes | +0.507 |
lic | +0.494 |
Comes | +0.488 |
:= | +0.479 |
Neg logit contributions | |
hesda | -0.940 |
Arizona | -0.901 |
anyahu | -0.880 |
Catal | -0.842 |
offense | -0.840 |
Token | not |
Token ID | 407 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
hesda | +0.016 |
Arizona | +0.015 |
anyahu | +0.014 |
Catal | +0.014 |
orno | +0.014 |
Neg logit contributions | |
cius | -0.015 |
rapes | -0.010 |
lic | -0.010 |
Comes | -0.010 |
:= | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
cius | +0.073 |
rapes | +0.050 |
lic | +0.049 |
Comes | +0.049 |
:= | +0.047 |
Neg logit contributions | |
hesda | -0.077 |
Arizona | -0.073 |
anyahu | -0.072 |
Catal | -0.069 |
orno | -0.067 |
Token | probably |
Token ID | 2192 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
hesda | +0.626 |
Arizona | +0.589 |
anyahu | +0.578 |
Catal | +0.544 |
orno | +0.533 |
Neg logit contributions | |
cius | -0.778 |
rapes | -0.559 |
lic | -0.551 |
Comes | -0.544 |
:= | -0.534 |
Token | my |
Token ID | 616 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
cius | +0.382 |
rapes | +0.272 |
lic | +0.267 |
Comes | +0.264 |
:= | +0.259 |
Neg logit contributions | |
hesda | -0.328 |
Arizona | -0.308 |
anyahu | -0.304 |
Catal | -0.286 |
orno | -0.280 |
Token | favorite |
Token ID | 4004 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
hesda | +0.018 |
Arizona | +0.017 |
anyahu | +0.017 |
Catal | +0.016 |
orno | +0.015 |
Neg logit contributions | |
cius | -0.026 |
rapes | -0.019 |
lic | -0.018 |
Comes | -0.018 |
:= | -0.018 |
Token | of |
Token ID | 286 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
hesda | +0.556 |
Arizona | +0.526 |
anyahu | +0.514 |
Catal | +0.489 |
offense | +0.480 |
Neg logit contributions | |
cius | -0.612 |
rapes | -0.426 |
lic | -0.418 |
Comes | -0.414 |
:= | -0.406 |
Token | the |
Token ID | 262 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
hesda | +0.234 |
Arizona | +0.223 |
anyahu | +0.218 |
Catal | +0.207 |
offense | +0.204 |
Neg logit contributions | |
cius | -0.237 |
rapes | -0.162 |
lic | -0.159 |
Comes | -0.157 |
:= | -0.154 |
Token | afternoon |
Token ID | 6672 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
hesda | +0.339 |
Arizona | +0.318 |
anyahu | +0.312 |
Catal | +0.295 |
orno | +0.288 |
Neg logit contributions | |
cius | -0.415 |
rapes | -0.298 |
lic | -0.291 |
Comes | -0.290 |
:= | -0.283 |
Token | . |
Token ID | 13 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
hesda | +0.377 |
Arizona | +0.360 |
anyahu | +0.352 |
Catal | +0.336 |
offense | +0.331 |
Neg logit contributions | |
cius | -0.359 |
rapes | -0.243 |
lic | -0.237 |
Comes | -0.233 |
:= | -0.228 |
Token | Named |
Token ID | 34441 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
hesda | +0.262 |
Arizona | +0.246 |
anyahu | +0.244 |
Catal | +0.230 |
offense | +0.228 |
Neg logit contributions | |
cius | -0.246 |
rapes | -0.166 |
lic | -0.164 |
Comes | -0.163 |
:= | -0.159 |
Token | after |
Token ID | 706 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
hesda | +0.270 |
Arizona | +0.257 |
anyahu | +0.250 |
Catal | +0.237 |
offense | +0.234 |
Neg logit contributions | |
cius | -0.299 |
rapes | -0.209 |
lic | -0.205 |
Comes | -0.202 |
:= | -0.199 |
Token | a |
Token ID | 257 |
Feature activation | +3.64e-02 |
Pos logit contributions | |
hesda | +0.125 |
Arizona | +0.119 |
anyahu | +0.116 |
Catal | +0.110 |
offense | +0.108 |
Neg logit contributions | |
cius | -0.147 |
rapes | -0.103 |
lic | -0.102 |
Comes | -0.100 |
:= | -0.099 |
Token | � |
Token ID | 447 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
hesda | +0.210 |
Arizona | +0.199 |
anyahu | +0.195 |
Catal | +0.185 |
offense | +0.182 |
Neg logit contributions | |
cius | -0.214 |
rapes | -0.149 |
lic | -0.144 |
Comes | -0.141 |
:= | -0.139 |
Token | � |
Token ID | 251 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
hesda | +0.170 |
Arizona | +0.163 |
anyahu | +0.161 |
Catal | +0.154 |
offense | +0.152 |
Neg logit contributions | |
cius | -0.109 |
rapes | -0.065 |
lic | -0.063 |
Comes | -0.061 |
:= | -0.060 |
Token | National |
Token ID | 2351 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
hesda | +0.259 |
Arizona | +0.245 |
anyahu | +0.240 |
Catal | +0.227 |
offense | +0.225 |
Neg logit contributions | |
cius | -0.282 |
rapes | -0.197 |
lic | -0.193 |
Comes | -0.189 |
:= | -0.186 |
Token | Review |
Token ID | 6602 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
hesda | +0.267 |
Arizona | +0.254 |
anyahu | +0.249 |
Catal | +0.239 |
offense | +0.236 |
Neg logit contributions | |
cius | -0.199 |
rapes | -0.126 |
lic | -0.123 |
Comes | -0.122 |
:= | -0.119 |
Token | national |
Token ID | 2260 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
hesda | +1.214 |
Arizona | +1.146 |
anyahu | +1.119 |
Catal | +1.062 |
offense | +1.049 |
Neg logit contributions | |
cius | -1.273 |
rapes | -0.883 |
lic | -0.864 |
Comes | -0.856 |
:= | -0.841 |
Token | affairs |
Token ID | 9674 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
hesda | +0.331 |
Arizona | +0.311 |
anyahu | +0.303 |
Catal | +0.287 |
orno | +0.283 |
Neg logit contributions | |
cius | -0.369 |
rapes | -0.260 |
lic | -0.255 |
Comes | -0.251 |
:= | -0.248 |
Token | correspondent |
Token ID | 21076 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
hesda | +0.268 |
Arizona | +0.252 |
anyahu | +0.248 |
Catal | +0.234 |
orno | +0.231 |
Neg logit contributions | |
cius | -0.269 |
rapes | -0.184 |
lic | -0.181 |
Comes | -0.178 |
:= | -0.176 |
Token | John |
Token ID | 1757 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
hesda | +0.127 |
Arizona | +0.119 |
anyahu | +0.117 |
Catal | +0.109 |
offense | +0.108 |
Neg logit contributions | |
cius | -0.150 |
rapes | -0.107 |
lic | -0.105 |
Comes | -0.104 |
:= | -0.102 |
Token | Fund |
Token ID | 7557 |
Feature activation | -7.50e-01 |
Pos logit contributions | |
hesda | +0.139 |
Arizona | +0.132 |
anyahu | +0.129 |
Catal | +0.120 |
offense | +0.120 |
Neg logit contributions | |
cius | -0.158 |
rapes | -0.111 |
lic | -0.110 |
Comes | -0.109 |
:= | -0.106 |
Token | wrote |
Token ID | 2630 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
hesda | +0.606 |
Arizona | +0.580 |
anyahu | +0.560 |
Catal | +0.537 |
offense | +0.531 |
Neg logit contributions | |
cius | -0.665 |
rapes | -0.466 |
lic | -0.457 |
Comes | -0.448 |
:= | -0.443 |
Token | in |
Token ID | 287 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
hesda | +0.586 |
Arizona | +0.556 |
anyahu | +0.542 |
Catal | +0.516 |
offense | +0.510 |
Neg logit contributions | |
cius | -0.601 |
rapes | -0.414 |
lic | -0.404 |
Comes | -0.399 |
:= | -0.394 |
Token | towards |
Token ID | 3371 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
hesda | +0.511 |
Arizona | +0.485 |
anyahu | +0.474 |
Catal | +0.449 |
offense | +0.440 |
Neg logit contributions | |
cius | -0.600 |
rapes | -0.425 |
lic | -0.417 |
Comes | -0.410 |
:= | -0.406 |
Token | Earth |
Token ID | 3668 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
hesda | +0.891 |
Arizona | +0.847 |
anyahu | +0.823 |
Catal | +0.782 |
offense | +0.774 |
Neg logit contributions | |
cius | -1.019 |
rapes | -0.715 |
lic | -0.700 |
Comes | -0.691 |
:= | -0.681 |
Token | . |
Token ID | 13 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
hesda | +1.175 |
Arizona | +1.121 |
anyahu | +1.091 |
Catal | +1.043 |
offense | +1.033 |
Neg logit contributions | |
cius | -1.144 |
rapes | -0.775 |
lic | -0.756 |
Comes | -0.746 |
:= | -0.733 |
Token | Some |
Token ID | 2773 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
hesda | +0.382 |
Arizona | +0.358 |
anyahu | +0.357 |
Catal | +0.334 |
orno | +0.333 |
Neg logit contributions | |
cius | -0.344 |
rapes | -0.232 |
lic | -0.228 |
Comes | -0.227 |
:= | -0.222 |
Token | seventeen |
Token ID | 38741 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
hesda | +0.662 |
Arizona | +0.625 |
anyahu | +0.612 |
Catal | +0.580 |
orno | +0.567 |
Neg logit contributions | |
cius | -0.763 |
rapes | -0.541 |
lic | -0.530 |
Comes | -0.520 |
:= | -0.512 |
Token | minutes |
Token ID | 2431 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
hesda | +0.419 |
Arizona | +0.398 |
anyahu | +0.387 |
Catal | +0.367 |
offense | +0.363 |
Neg logit contributions | |
cius | -0.481 |
rapes | -0.338 |
lic | -0.331 |
Comes | -0.327 |
:= | -0.322 |
Token | before |
Token ID | 878 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
hesda | +1.303 |
Arizona | +1.238 |
anyahu | +1.204 |
Catal | +1.142 |
offense | +1.125 |
Neg logit contributions | |
cius | -1.547 |
rapes | -1.097 |
lic | -1.076 |
Comes | -1.061 |
:= | -1.045 |
Token | impact |
Token ID | 2928 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
hesda | +0.275 |
Arizona | +0.258 |
anyahu | +0.251 |
Catal | +0.233 |
orno | +0.226 |
Neg logit contributions | |
cius | -0.491 |
rapes | -0.371 |
lic | -0.367 |
Comes | -0.362 |
:= | -0.357 |
Token | , |
Token ID | 11 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
hesda | +1.622 |
Arizona | +1.542 |
anyahu | +1.487 |
Catal | +1.419 |
offense | +1.413 |
Neg logit contributions | |
cius | -1.908 |
rapes | -1.340 |
lic | -1.312 |
Comes | -1.296 |
:= | -1.276 |
Token | the |
Token ID | 262 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
hesda | +0.289 |
Arizona | +0.274 |
anyahu | +0.268 |
Catal | +0.254 |
offense | +0.250 |
Neg logit contributions | |
cius | -0.325 |
rapes | -0.228 |
lic | -0.223 |
Comes | -0.220 |
:= | -0.217 |
Token | F |
Token ID | 376 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
hesda | +0.286 |
Arizona | +0.267 |
anyahu | +0.263 |
Catal | +0.247 |
orno | +0.242 |
Neg logit contributions | |
cius | -0.392 |
rapes | -0.286 |
lic | -0.280 |
Comes | -0.277 |
:= | -0.274 |
Token | History |
Token ID | 18122 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
hesda | +0.172 |
Arizona | +0.162 |
anyahu | +0.158 |
Catal | +0.149 |
offense | +0.149 |
Neg logit contributions | |
cius | -0.198 |
rapes | -0.139 |
lic | -0.138 |
Comes | -0.134 |
:= | -0.133 |
Token | / |
Token ID | 14 |
Feature activation | +6.60e-02 |
Pos logit contributions | |
hesda | +0.238 |
Arizona | +0.224 |
anyahu | +0.218 |
Catal | +0.205 |
offense | +0.204 |
Neg logit contributions | |
cius | -0.310 |
rapes | -0.223 |
lic | -0.220 |
Comes | -0.216 |
:= | -0.214 |
Token | x |
Token ID | 87 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
cius | +0.063 |
rapes | +0.044 |
lic | +0.044 |
Comes | +0.043 |
:= | +0.043 |
Neg logit contributions | |
hesda | -0.050 |
Arizona | -0.047 |
anyahu | -0.046 |
offense | -0.043 |
Catal | -0.043 |
Token | 1 |
Token ID | 16 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
hesda | +0.211 |
Arizona | +0.201 |
anyahu | +0.194 |
Catal | +0.184 |
offense | +0.181 |
Neg logit contributions | |
cius | -0.276 |
rapes | -0.200 |
Comes | -0.194 |
lic | -0.194 |
:= | -0.190 |
Token | / |
Token ID | 14 |
Feature activation | -9.31e-03 |
Pos logit contributions | |
hesda | +0.225 |
Arizona | +0.214 |
anyahu | +0.208 |
Catal | +0.197 |
offense | +0.195 |
Neg logit contributions | |
cius | -0.265 |
rapes | -0.187 |
lic | -0.183 |
Comes | -0.181 |
:= | -0.178 |
Token | ch |
Token ID | 354 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
hesda | +0.007 |
Arizona | +0.007 |
anyahu | +0.007 |
Catal | +0.006 |
offense | +0.006 |
Neg logit contributions | |
cius | -0.008 |
rapes | -0.006 |
lic | -0.006 |
Comes | -0.006 |
:= | -0.006 |
Token | uck |
Token ID | 1347 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
hesda | +1.332 |
Arizona | +1.267 |
anyahu | +1.232 |
Catal | +1.169 |
offense | +1.159 |
Neg logit contributions | |
cius | -1.489 |
rapes | -1.042 |
lic | -1.015 |
Comes | -1.009 |
:= | -0.991 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
cius | +0.372 |
rapes | +0.264 |
lic | +0.258 |
Comes | +0.256 |
:= | +0.252 |
Neg logit contributions | |
hesda | -0.310 |
Arizona | -0.294 |
anyahu | -0.285 |
Catal | -0.271 |
offense | -0.268 |
Token | html |
Token ID | 6494 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
hesda | +0.084 |
Arizona | +0.079 |
anyahu | +0.077 |
Catal | +0.073 |
offense | +0.073 |
Neg logit contributions | |
cius | -0.096 |
rapes | -0.067 |
lic | -0.066 |
Comes | -0.065 |
:= | -0.064 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
hesda | +1.168 |
Arizona | +1.126 |
anyahu | +1.076 |
Catal | +1.042 |
offense | +1.023 |
Neg logit contributions | |
cius | -1.392 |
rapes | -0.983 |
lic | -0.953 |
Comes | -0.941 |
:= | -0.932 |
Token | Sen |
Token ID | 10445 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
hesda | +0.020 |
Arizona | +0.018 |
anyahu | +0.018 |
offense | +0.017 |
Catal | +0.017 |
Neg logit contributions | |
cius | -0.024 |
rapes | -0.017 |
lic | -0.017 |
Comes | -0.017 |
:= | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
hesda | +0.098 |
Arizona | +0.093 |
anyahu | +0.091 |
Catal | +0.086 |
offense | +0.085 |
Neg logit contributions | |
cius | -0.108 |
rapes | -0.075 |
lic | -0.074 |
Comes | -0.073 |
:= | -0.072 |
Token | sweet |
Token ID | 6029 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
hesda | +0.285 |
Arizona | +0.270 |
anyahu | +0.262 |
Catal | +0.248 |
orno | +0.243 |
Neg logit contributions | |
cius | -0.350 |
rapes | -0.252 |
lic | -0.245 |
Comes | -0.242 |
:= | -0.239 |
Token | ingredients |
Token ID | 9391 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
hesda | +0.111 |
Arizona | +0.106 |
anyahu | +0.103 |
Catal | +0.098 |
offense | +0.096 |
Neg logit contributions | |
cius | -0.126 |
rapes | -0.089 |
lic | -0.087 |
Comes | -0.085 |
:= | -0.084 |
Token | in |
Token ID | 287 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
hesda | +0.381 |
Arizona | +0.364 |
anyahu | +0.354 |
Catal | +0.337 |
orno | +0.332 |
Neg logit contributions | |
cius | -0.376 |
rapes | -0.259 |
lic | -0.253 |
Comes | -0.249 |
:= | -0.246 |
Token | your |
Token ID | 534 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
hesda | +0.230 |
Arizona | +0.218 |
anyahu | +0.212 |
Catal | +0.201 |
offense | +0.198 |
Neg logit contributions | |
cius | -0.278 |
rapes | -0.198 |
lic | -0.194 |
Comes | -0.191 |
:= | -0.188 |
Token | recipe |
Token ID | 8364 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
hesda | +0.211 |
Arizona | +0.200 |
anyahu | +0.195 |
Catal | +0.185 |
offense | +0.181 |
Neg logit contributions | |
cius | -0.238 |
rapes | -0.168 |
lic | -0.164 |
Comes | -0.162 |
:= | -0.159 |
Token | if |
Token ID | 611 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
hesda | +1.511 |
Arizona | +1.441 |
anyahu | +1.403 |
Catal | +1.341 |
offense | +1.328 |
Neg logit contributions | |
cius | -1.497 |
rapes | -1.017 |
lic | -0.993 |
Comes | -0.980 |
:= | -0.963 |
Token | you |
Token ID | 345 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
hesda | +0.199 |
Arizona | +0.190 |
anyahu | +0.185 |
Catal | +0.177 |
offense | +0.174 |
Neg logit contributions | |
cius | -0.200 |
rapes | -0.137 |
lic | -0.134 |
Comes | -0.132 |
:= | -0.130 |
Token | are |
Token ID | 389 |
Feature activation | -4.54e-02 |
Pos logit contributions | |
hesda | +0.297 |
Arizona | +0.281 |
anyahu | +0.273 |
Catal | +0.260 |
offense | +0.257 |
Neg logit contributions | |
cius | -0.347 |
rapes | -0.245 |
lic | -0.240 |
Comes | -0.237 |
:= | -0.234 |
Token | using |
Token ID | 1262 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
hesda | +0.039 |
Arizona | +0.037 |
anyahu | +0.036 |
Catal | +0.034 |
offense | +0.034 |
Neg logit contributions | |
cius | -0.038 |
rapes | -0.026 |
lic | -0.026 |
Comes | -0.025 |
:= | -0.025 |
Token | this |
Token ID | 428 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
hesda | +0.550 |
Arizona | +0.522 |
anyahu | +0.509 |
Catal | +0.482 |
offense | +0.472 |
Neg logit contributions | |
cius | -0.622 |
rapes | -0.443 |
lic | -0.431 |
Comes | -0.425 |
:= | -0.418 |
Token | {{ |
Token ID | 22935 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
hesda | +1.087 |
Arizona | +1.035 |
anyahu | +1.007 |
Catal | +0.960 |
offense | +0.951 |
Neg logit contributions | |
cius | -1.140 |
rapes | -0.786 |
lic | -0.769 |
Comes | -0.758 |
:= | -0.747 |
Token | 8 |
Token ID | 23 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
hesda | +1.140 |
Arizona | +1.080 |
anyahu | +1.047 |
Catal | +0.992 |
offense | +0.981 |
Neg logit contributions | |
cius | -1.469 |
rapes | -1.054 |
lic | -1.033 |
Comes | -1.021 |
:= | -1.007 |
Token | , |
Token ID | 11 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
hesda | +0.373 |
Arizona | +0.350 |
anyahu | +0.343 |
Catal | +0.324 |
orno | +0.323 |
Neg logit contributions | |
cius | -0.363 |
rapes | -0.248 |
lic | -0.247 |
:= | -0.246 |
Comes | -0.242 |
Token | 15 |
Token ID | 1315 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
hesda | +0.008 |
Arizona | +0.007 |
anyahu | +0.007 |
Catal | +0.006 |
offense | +0.006 |
Neg logit contributions | |
cius | -0.012 |
rapes | -0.009 |
lic | -0.009 |
Comes | -0.008 |
:= | -0.008 |
Token | }, |
Token ID | 5512 |
Feature activation | +4.97e-02 |
Pos logit contributions | |
hesda | +0.606 |
Arizona | +0.578 |
anyahu | +0.562 |
Catal | +0.537 |
offense | +0.533 |
Neg logit contributions | |
cius | -0.671 |
rapes | -0.469 |
lic | -0.456 |
Comes | -0.451 |
:= | -0.439 |
Token | {{ |
Token ID | 22935 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
cius | +0.047 |
rapes | +0.033 |
lic | +0.033 |
Comes | +0.032 |
:= | +0.032 |
Neg logit contributions | |
hesda | -0.037 |
Arizona | -0.036 |
anyahu | -0.034 |
Catal | -0.033 |
offense | -0.033 |
Token | 7 |
Token ID | 22 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
hesda | +1.451 |
Arizona | +1.378 |
anyahu | +1.342 |
Catal | +1.275 |
offense | +1.263 |
Neg logit contributions | |
cius | -1.589 |
rapes | -1.105 |
lic | -1.085 |
Comes | -1.069 |
:= | -1.055 |
Token | , |
Token ID | 11 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
hesda | +0.265 |
Arizona | +0.252 |
anyahu | +0.246 |
Catal | +0.233 |
offense | +0.232 |
Neg logit contributions | |
cius | -0.309 |
rapes | -0.218 |
lic | -0.213 |
Comes | -0.210 |
:= | -0.206 |
Token | 14 |
Token ID | 1478 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
hesda | +0.093 |
Arizona | +0.087 |
anyahu | +0.085 |
Catal | +0.079 |
orno | +0.078 |
Neg logit contributions | |
cius | -0.137 |
rapes | -0.101 |
lic | -0.100 |
Comes | -0.099 |
:= | -0.098 |
Token | }, |
Token ID | 5512 |
Feature activation | +7.34e-02 |
Pos logit contributions | |
hesda | +0.382 |
Arizona | +0.366 |
anyahu | +0.356 |
Catal | +0.339 |
offense | +0.337 |
Neg logit contributions | |
cius | -0.439 |
rapes | -0.309 |
lic | -0.300 |
Comes | -0.296 |
esian | -0.287 |
Token | { |
Token ID | 1391 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
cius | +0.074 |
rapes | +0.053 |
lic | +0.053 |
Comes | +0.052 |
esian | +0.051 |
Neg logit contributions | |
hesda | -0.051 |
Arizona | -0.049 |
anyahu | -0.047 |
Catal | -0.044 |
offense | -0.044 |
Token | For |
Token ID | 1114 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
hesda | +0.045 |
Arizona | +0.042 |
anyahu | +0.042 |
Catal | +0.039 |
orno | +0.039 |
Neg logit contributions | |
cius | -0.040 |
rapes | -0.026 |
Comes | -0.026 |
lic | -0.026 |
:= | -0.025 |
Token | instance |
Token ID | 4554 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
cius | +0.256 |
rapes | +0.175 |
lic | +0.172 |
Comes | +0.168 |
:= | +0.166 |
Neg logit contributions | |
hesda | -0.269 |
Arizona | -0.254 |
anyahu | -0.251 |
Catal | -0.238 |
orno | -0.232 |
Token | , |
Token ID | 11 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
hesda | +0.503 |
Arizona | +0.478 |
anyahu | +0.463 |
Catal | +0.440 |
offense | +0.438 |
Neg logit contributions | |
cius | -0.593 |
rapes | -0.418 |
lic | -0.408 |
Comes | -0.403 |
:= | -0.397 |
Token | a |
Token ID | 257 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
hesda | +0.403 |
Arizona | +0.382 |
anyahu | +0.375 |
Catal | +0.355 |
orno | +0.348 |
Neg logit contributions | |
cius | -0.428 |
rapes | -0.298 |
lic | -0.294 |
Comes | -0.290 |
:= | -0.283 |
Token | British |
Token ID | 3517 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
hesda | +0.272 |
Arizona | +0.257 |
anyahu | +0.251 |
Catal | +0.237 |
offense | +0.233 |
Neg logit contributions | |
cius | -0.320 |
rapes | -0.227 |
lic | -0.224 |
Comes | -0.220 |
:= | -0.217 |
Token | Doodle |
Token ID | 45634 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
hesda | +0.361 |
Arizona | +0.342 |
anyahu | +0.334 |
Catal | +0.316 |
offense | +0.312 |
Neg logit contributions | |
cius | -0.408 |
rapes | -0.286 |
lic | -0.281 |
Comes | -0.277 |
:= | -0.273 |
Token | bug |
Token ID | 25456 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
hesda | +1.455 |
Arizona | +1.378 |
anyahu | +1.346 |
Catal | +1.275 |
offense | +1.260 |
Neg logit contributions | |
cius | -1.529 |
rapes | -1.058 |
lic | -1.038 |
Comes | -1.025 |
:= | -1.008 |
Token | harness |
Token ID | 19356 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
cius | +0.327 |
rapes | +0.230 |
lic | +0.227 |
Comes | +0.224 |
:= | +0.219 |
Neg logit contributions | |
hesda | -0.295 |
Arizona | -0.279 |
anyahu | -0.274 |
Catal | -0.258 |
orno | -0.252 |
Token | powered |
Token ID | 13232 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
cius | +0.090 |
rapes | +0.063 |
lic | +0.062 |
Comes | +0.061 |
esian | +0.060 |
Neg logit contributions | |
hesda | -0.085 |
Arizona | -0.081 |
anyahu | -0.079 |
Catal | -0.074 |
orno | -0.073 |
Token | by |
Token ID | 416 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
cius | +0.384 |
rapes | +0.243 |
lic | +0.238 |
Comes | +0.233 |
:= | +0.228 |
Neg logit contributions | |
hesda | -0.508 |
Arizona | -0.486 |
anyahu | -0.476 |
Catal | -0.456 |
offense | -0.450 |
Token |
|
Token ID | 198 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
hesda | +0.082 |
Arizona | +0.077 |
anyahu | +0.075 |
Catal | +0.071 |
offense | +0.070 |
Neg logit contributions | |
cius | -0.105 |
rapes | -0.075 |
lic | -0.074 |
Comes | -0.073 |
:= | -0.072 |