Token | him |
Token ID | 683 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
Chick | +0.099 |
burn | +0.094 |
lor | +0.083 |
Bunny | +0.080 |
pt | +0.080 |
Neg logit contributions | |
2 | -0.085 |
dice | -0.082 |
2 | -0.081 |
1 | -0.077 |
seven | -0.076 |
Token | from |
Token ID | 422 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
Chick | +0.034 |
burn | +0.030 |
lor | +0.029 |
Bunny | +0.028 |
Sleep | +0.027 |
Neg logit contributions | |
dice | -0.021 |
2 | -0.020 |
2 | -0.019 |
agree | -0.019 |
sign | -0.018 |
Token | getting |
Token ID | 1972 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
Chick | +0.034 |
burn | +0.032 |
pt | +0.028 |
lor | +0.028 |
Bunny | +0.028 |
Neg logit contributions | |
2 | -0.023 |
dice | -0.023 |
2 | -0.022 |
equation | -0.021 |
seven | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
2 | +0.032 |
2 | +0.029 |
busy | +0.029 |
seven | +0.029 |
dice | +0.028 |
Neg logit contributions | |
Chick | -0.061 |
lor | -0.059 |
burn | -0.057 |
aby | -0.054 |
maid | -0.052 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
dice | +0.032 |
2 | +0.031 |
2 | +0.029 |
equation | +0.028 |
seven | +0.028 |
Neg logit contributions | |
Chick | -0.044 |
burn | -0.041 |
pt | -0.037 |
lor | -0.036 |
seed | -0.036 |
Token | burn |
Token ID | 10899 |
Feature activation | +9.67e+00 |
Pos logit contributions | |
2 | +0.081 |
seven | +0.080 |
man | +0.079 |
dice | +0.079 |
2 | +0.079 |
Neg logit contributions | |
Chick | -0.046 |
Madd | -0.034 |
Bunny | -0.034 |
pt | -0.033 |
lor | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
Chick | +0.815 |
burn | +0.711 |
lor | +0.706 |
seed | +0.689 |
Madd | +0.687 |
Neg logit contributions | |
dice | -0.377 |
2 | -0.361 |
man | -0.357 |
seven | -0.326 |
2 | -0.325 |
Token |
|
Token ID | 198 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
burn | +0.020 |
Chick | +0.020 |
pt | +0.017 |
Bunny | +0.017 |
lull | +0.017 |
Neg logit contributions | |
2 | -0.011 |
dice | -0.011 |
2 | -0.011 |
1 | -0.010 |
equation | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
Chick | +0.057 |
burn | +0.056 |
Bunny | +0.049 |
pt | +0.048 |
seed | +0.047 |
Neg logit contributions | |
dice | -0.034 |
2 | -0.034 |
2 | -0.031 |
equation | -0.030 |
seven | -0.029 |
Token | Tim |
Token ID | 14967 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Chick | +0.046 |
burn | +0.044 |
Bunny | +0.038 |
lull | +0.036 |
pt | +0.036 |
Neg logit contributions | |
dice | -0.039 |
2 | -0.039 |
2 | -0.037 |
seven | -0.036 |
1 | -0.035 |
Token | my |
Token ID | 1820 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
dice | +0.059 |
2 | +0.058 |
2 | +0.054 |
equation | +0.052 |
seven | +0.052 |
Neg logit contributions | |
Chick | -0.074 |
burn | -0.072 |
Bunny | -0.062 |
pt | -0.061 |
seed | -0.059 |
Token | to |
Token ID | 284 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
2 | +0.126 |
dice | +0.123 |
2 | +0.117 |
equation | +0.115 |
3 | +0.114 |
Neg logit contributions | |
Chick | -0.159 |
burn | -0.159 |
Bunny | -0.135 |
pt | -0.130 |
seed | -0.127 |
Token | put |
Token ID | 1234 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
Chick | +0.036 |
burn | +0.034 |
Bunny | +0.030 |
pt | +0.029 |
seed | +0.028 |
Neg logit contributions | |
2 | -0.028 |
dice | -0.028 |
2 | -0.026 |
equation | -0.025 |
seven | -0.025 |
Token | on |
Token ID | 319 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
2 | +0.017 |
dice | +0.016 |
equation | +0.015 |
2 | +0.015 |
4 | +0.015 |
Neg logit contributions | |
Chick | -0.017 |
burn | -0.016 |
Bunny | -0.014 |
seed | -0.014 |
pt | -0.013 |
Token | his |
Token ID | 465 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
Chick | +0.088 |
burn | +0.084 |
Bunny | +0.072 |
pt | +0.069 |
seed | +0.068 |
Neg logit contributions | |
2 | -0.076 |
dice | -0.075 |
2 | -0.071 |
equation | -0.069 |
seven | -0.068 |
Token | sun |
Token ID | 4252 |
Feature activation | -9.85e-01 |
Pos logit contributions | |
Chick | +0.049 |
burn | +0.047 |
Bunny | +0.041 |
pt | +0.039 |
seed | +0.038 |
Neg logit contributions | |
2 | -0.041 |
dice | -0.040 |
2 | -0.038 |
equation | -0.037 |
3 | -0.037 |
Token | burn |
Token ID | 10899 |
Feature activation | +9.52e+00 |
Pos logit contributions | |
dice | +0.047 |
2 | +0.045 |
seven | +0.044 |
2 | +0.042 |
man | +0.042 |
Neg logit contributions | |
Chick | -0.075 |
Madd | -0.066 |
pt | -0.065 |
burn | -0.064 |
lor | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
Chick | +0.814 |
burn | +0.742 |
Madd | +0.708 |
ulp | +0.693 |
ectar | +0.691 |
Neg logit contributions | |
dice | -0.368 |
man | -0.346 |
2 | -0.341 |
2 | -0.317 |
seven | -0.313 |
Token | Tim |
Token ID | 5045 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Chick | +0.046 |
burn | +0.044 |
Bunny | +0.038 |
pt | +0.035 |
seed | +0.035 |
Neg logit contributions | |
dice | -0.048 |
2 | -0.047 |
2 | -0.045 |
seven | -0.044 |
equation | -0.044 |
Token | my |
Token ID | 1820 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
Chick | +0.010 |
burn | +0.010 |
Bunny | +0.009 |
pt | +0.009 |
seed | +0.008 |
Neg logit contributions | |
dice | -0.007 |
2 | -0.007 |
2 | -0.007 |
equation | -0.006 |
seven | -0.006 |
Token | thought |
Token ID | 1807 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
dice | +0.019 |
2 | +0.019 |
2 | +0.018 |
equation | +0.017 |
seven | +0.017 |
Neg logit contributions | |
Chick | -0.020 |
burn | -0.019 |
Bunny | -0.017 |
pt | -0.016 |
seed | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
dice | +0.114 |
2 | +0.113 |
2 | +0.107 |
seven | +0.102 |
1 | +0.102 |
Neg logit contributions | |
Chick | -0.130 |
burn | -0.130 |
Bunny | -0.108 |
pt | -0.107 |
seed | -0.106 |
Token | don |
Token ID | 836 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
dice | +0.053 |
2 | +0.053 |
2 | +0.050 |
equation | +0.048 |
seven | +0.048 |
Neg logit contributions | |
Chick | -0.065 |
burn | -0.063 |
Bunny | -0.054 |
pt | -0.053 |
seed | -0.051 |
Token | 't |
Token ID | 470 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
dice | +0.099 |
2 | +0.098 |
2 | +0.093 |
seven | +0.089 |
equation | +0.089 |
Neg logit contributions | |
Chick | -0.106 |
burn | -0.103 |
Bunny | -0.087 |
pt | -0.084 |
seed | -0.082 |
Token | get |
Token ID | 651 |
Feature activation | -8.22e-01 |
Pos logit contributions | |
Chick | +0.029 |
burn | +0.029 |
Bunny | +0.025 |
pt | +0.024 |
seed | +0.023 |
Neg logit contributions | |
dice | -0.019 |
2 | -0.019 |
2 | -0.018 |
equation | -0.017 |
seven | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
2 | +0.038 |
dice | +0.038 |
2 | +0.038 |
seven | +0.036 |
3 | +0.034 |
Neg logit contributions | |
Chick | -0.064 |
burn | -0.060 |
lor | -0.057 |
aby | -0.053 |
lull | -0.053 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
dice | +0.044 |
2 | +0.042 |
2 | +0.040 |
seven | +0.039 |
equation | +0.038 |
Neg logit contributions | |
Chick | -0.045 |
burn | -0.040 |
Bunny | -0.036 |
pt | -0.035 |
seed | -0.035 |
Token | burn |
Token ID | 10899 |
Feature activation | +9.38e+00 |
Pos logit contributions | |
dice | +0.102 |
seven | +0.102 |
2 | +0.101 |
2 | +0.100 |
man | +0.097 |
Neg logit contributions | |
Chick | -0.029 |
Madd | -0.018 |
Bunny | -0.017 |
pt | -0.016 |
burn | -0.013 |
Token | ." |
Token ID | 526 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
Chick | +0.689 |
Madd | +0.588 |
seed | +0.562 |
ulp | +0.562 |
ectar | +0.561 |
Neg logit contributions | |
dice | -0.476 |
man | -0.462 |
seven | -0.443 |
five | -0.438 |
2 | -0.432 |
Token | Lily |
Token ID | 20037 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
Chick | +0.130 |
burn | +0.129 |
pt | +0.106 |
Bunny | +0.105 |
seed | +0.102 |
Neg logit contributions | |
2 | -0.127 |
dice | -0.126 |
2 | -0.120 |
equation | -0.115 |
seven | -0.114 |
Token | yawn |
Token ID | 40908 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
Chick | +0.042 |
burn | +0.040 |
Bunny | +0.035 |
pt | +0.034 |
lull | +0.033 |
Neg logit contributions | |
dice | -0.036 |
2 | -0.034 |
2 | -0.032 |
equation | -0.032 |
seven | -0.031 |
Token | ed |
Token ID | 276 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
Chick | +0.215 |
burn | +0.202 |
Bunny | +0.173 |
seed | +0.167 |
pt | +0.167 |
Neg logit contributions | |
2 | -0.234 |
dice | -0.227 |
2 | -0.222 |
seven | -0.214 |
3 | -0.211 |
Token | and |
Token ID | 290 |
Feature activation | -7.10e-02 |
Pos logit contributions | |
Chick | +0.166 |
burn | +0.162 |
Bunny | +0.145 |
pt | +0.142 |
seed | +0.139 |
Neg logit contributions | |
dice | -0.067 |
2 | -0.066 |
2 | -0.060 |
equation | -0.056 |
seven | -0.055 |
Token | want |
Token ID | 765 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
Chick | +0.031 |
burn | +0.030 |
Bunny | +0.026 |
pt | +0.026 |
D | +0.025 |
Neg logit contributions | |
2 | -0.019 |
dice | -0.019 |
2 | -0.017 |
1 | -0.016 |
seven | -0.016 |
Token | Lily |
Token ID | 20037 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
dice | +0.106 |
2 | +0.102 |
2 | +0.099 |
seven | +0.097 |
1 | +0.096 |
Neg logit contributions | |
Chick | -0.184 |
burn | -0.181 |
lor | -0.163 |
seed | -0.159 |
maid | -0.157 |
Token | to |
Token ID | 284 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
Chick | +0.041 |
burn | +0.036 |
Bunny | +0.033 |
lor | +0.033 |
unic | +0.033 |
Neg logit contributions | |
dice | -0.021 |
2 | -0.021 |
2 | -0.020 |
seven | -0.019 |
equation | -0.019 |
Token | get |
Token ID | 651 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
Chick | +0.034 |
burn | +0.031 |
lor | +0.030 |
seed | +0.030 |
ectar | +0.028 |
Neg logit contributions | |
agree | -0.018 |
2 | -0.017 |
dice | -0.017 |
sign | -0.016 |
2 | -0.016 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
2 | +0.041 |
dice | +0.040 |
seven | +0.040 |
2 | +0.038 |
1 | +0.036 |
Neg logit contributions | |
Chick | -0.071 |
lor | -0.069 |
burn | -0.068 |
lull | -0.063 |
aby | -0.061 |
Token | burn |
Token ID | 10899 |
Feature activation | +9.38e+00 |
Pos logit contributions | |
2 | +0.103 |
2 | +0.102 |
seven | +0.102 |
man | +0.101 |
dice | +0.101 |
Neg logit contributions | |
Chick | -0.034 |
Madd | -0.022 |
lor | -0.022 |
ulp | -0.021 |
Bunny | -0.020 |
Token | ed |
Token ID | 276 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
Chick | +0.710 |
unic | +0.613 |
lull | +0.613 |
lor | +0.610 |
rim | +0.589 |
Neg logit contributions | |
dice | -0.411 |
2 | -0.404 |
man | -0.394 |
five | -0.380 |
2 | -0.371 |
Token | . |
Token ID | 13 |
Feature activation | -7.76e-02 |
Pos logit contributions | |
Chick | +0.144 |
burn | +0.137 |
lor | +0.123 |
Bunny | +0.120 |
seed | +0.117 |
Neg logit contributions | |
dice | -0.078 |
2 | -0.076 |
2 | -0.075 |
seven | -0.074 |
1 | -0.071 |
Token |
|
Token ID | 198 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
2 | +0.003 |
dice | +0.003 |
2 | +0.003 |
equation | +0.003 |
1 | +0.003 |
Neg logit contributions | |
burn | -0.007 |
Chick | -0.006 |
pt | -0.006 |
seed | -0.005 |
Bunny | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
Chick | +0.049 |
burn | +0.048 |
Bunny | +0.041 |
pt | +0.040 |
seed | +0.040 |
Neg logit contributions | |
dice | -0.030 |
2 | -0.029 |
2 | -0.027 |
equation | -0.026 |
seven | -0.026 |
Token | L |
Token ID | 43 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
Chick | +0.041 |
burn | +0.039 |
Bunny | +0.034 |
pt | +0.033 |
lull | +0.033 |
Neg logit contributions | |
dice | -0.034 |
2 | -0.034 |
2 | -0.032 |
seven | -0.031 |
1 | -0.031 |
Token | she |
Token ID | 673 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Chick | +0.093 |
burn | +0.090 |
Bunny | +0.077 |
pt | +0.075 |
seed | +0.073 |
Neg logit contributions | |
2 | -0.073 |
dice | -0.073 |
2 | -0.069 |
seven | -0.066 |
equation | -0.066 |
Token | knew |
Token ID | 2993 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
Chick | +0.071 |
burn | +0.067 |
Bunny | +0.059 |
pt | +0.057 |
seed | +0.055 |
Neg logit contributions | |
dice | -0.067 |
2 | -0.066 |
2 | -0.062 |
equation | -0.060 |
seven | -0.060 |
Token | the |
Token ID | 262 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
2 | +0.038 |
dice | +0.038 |
2 | +0.036 |
1 | +0.034 |
seven | +0.034 |
Neg logit contributions | |
Chick | -0.049 |
burn | -0.048 |
Bunny | -0.040 |
seed | -0.039 |
pt | -0.039 |
Token | word |
Token ID | 1573 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
dice | +0.054 |
2 | +0.053 |
2 | +0.048 |
3 | +0.048 |
4 | +0.047 |
Neg logit contributions | |
Chick | -0.043 |
burn | -0.039 |
Bunny | -0.034 |
lull | -0.033 |
chick | -0.031 |
Token | ' |
Token ID | 705 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
dice | +0.156 |
2 | +0.156 |
2 | +0.146 |
equation | +0.141 |
seven | +0.140 |
Neg logit contributions | |
Chick | -0.177 |
burn | -0.169 |
Bunny | -0.147 |
pt | -0.142 |
seed | -0.138 |
Token | burn |
Token ID | 10899 |
Feature activation | +9.31e+00 |
Pos logit contributions | |
dice | +0.245 |
2 | +0.237 |
2 | +0.226 |
equation | +0.220 |
seven | +0.219 |
Neg logit contributions | |
Chick | -0.264 |
burn | -0.257 |
Bunny | -0.217 |
seed | -0.209 |
pt | -0.209 |
Token | '. |
Token ID | 4458 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
Chick | +0.627 |
burn | +0.592 |
Bunny | +0.507 |
pt | +0.494 |
seed | +0.475 |
Neg logit contributions | |
2 | -0.569 |
dice | -0.568 |
2 | -0.541 |
seven | -0.518 |
equation | -0.517 |
Token | Her |
Token ID | 2332 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
2 | +0.021 |
dice | +0.021 |
2 | +0.020 |
seven | +0.018 |
1 | +0.018 |
Neg logit contributions | |
burn | -0.031 |
Chick | -0.031 |
pt | -0.026 |
Bunny | -0.026 |
seed | -0.025 |
Token | friends |
Token ID | 2460 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
Chick | +0.187 |
burn | +0.179 |
Bunny | +0.148 |
pt | +0.145 |
seed | +0.141 |
Neg logit contributions | |
2 | -0.207 |
dice | -0.206 |
2 | -0.196 |
equation | -0.190 |
seven | -0.189 |
Token | were |
Token ID | 547 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Chick | +0.034 |
burn | +0.032 |
Bunny | +0.028 |
pt | +0.027 |
seed | +0.027 |
Neg logit contributions | |
dice | -0.027 |
2 | -0.027 |
2 | -0.025 |
equation | -0.024 |
seven | -0.024 |
Token | so |
Token ID | 523 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
Chick | +0.109 |
burn | +0.105 |
Bunny | +0.094 |
pt | +0.091 |
seed | +0.088 |
Neg logit contributions | |
dice | -0.075 |
2 | -0.073 |
equation | -0.065 |
2 | -0.064 |
3 | -0.062 |
Token | arms |
Token ID | 5101 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
Chick | +0.100 |
burn | +0.097 |
pt | +0.086 |
Bunny | +0.084 |
ectar | +0.083 |
Neg logit contributions | |
dice | -0.049 |
2 | -0.049 |
2 | -0.045 |
seven | -0.044 |
equation | -0.042 |
Token | and |
Token ID | 290 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
Chick | +0.049 |
burn | +0.047 |
Bunny | +0.041 |
pt | +0.041 |
seed | +0.039 |
Neg logit contributions | |
dice | -0.032 |
2 | -0.032 |
2 | -0.029 |
equation | -0.028 |
seven | -0.028 |
Token | sing |
Token ID | 1702 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
Chick | +0.011 |
burn | +0.011 |
Bunny | +0.010 |
pt | +0.009 |
seed | +0.009 |
Neg logit contributions | |
dice | -0.007 |
2 | -0.007 |
2 | -0.007 |
equation | -0.007 |
seven | -0.007 |
Token | him |
Token ID | 683 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
Chick | +0.229 |
burn | +0.226 |
Bunny | +0.192 |
seed | +0.189 |
pt | +0.188 |
Neg logit contributions | |
dice | -0.150 |
2 | -0.147 |
2 | -0.141 |
seven | -0.134 |
3 | -0.131 |
Token | a |
Token ID | 257 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
Chick | +0.040 |
burn | +0.039 |
Bunny | +0.034 |
pt | +0.033 |
seed | +0.033 |
Neg logit contributions | |
dice | -0.025 |
2 | -0.024 |
2 | -0.023 |
seven | -0.022 |
equation | -0.022 |
Token | lull |
Token ID | 42858 |
Feature activation | +9.13e+00 |
Pos logit contributions | |
2 | +0.040 |
dice | +0.040 |
2 | +0.038 |
equation | +0.036 |
seven | +0.036 |
Neg logit contributions | |
Chick | -0.034 |
burn | -0.033 |
Bunny | -0.027 |
pt | -0.026 |
lull | -0.026 |
Token | aby |
Token ID | 3930 |
Feature activation | +5.12e+00 |
Pos logit contributions | |
seed | +0.440 |
Chick | +0.372 |
burn | +0.367 |
Dod | +0.338 |
Betsy | +0.336 |
Neg logit contributions | |
man | -0.631 |
line | -0.584 |
worker | -0.562 |
driver | -0.555 |
old | -0.540 |
Token | . |
Token ID | 13 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
Chick | +0.423 |
burn | +0.406 |
Bunny | +0.364 |
pt | +0.357 |
Madd | +0.356 |
Neg logit contributions | |
dice | -0.219 |
2 | -0.216 |
2 | -0.209 |
seven | -0.204 |
1 | -0.192 |
Token | As |
Token ID | 1081 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
Chick | +0.041 |
burn | +0.037 |
Bunny | +0.033 |
D | +0.031 |
Betsy | +0.031 |
Neg logit contributions | |
dice | -0.041 |
2 | -0.040 |
2 | -0.038 |
seven | -0.037 |
equation | -0.037 |
Token | she |
Token ID | 673 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Chick | +0.145 |
burn | +0.145 |
lor | +0.132 |
pt | +0.130 |
seed | +0.127 |
Neg logit contributions | |
dice | -0.097 |
2 | -0.095 |
2 | -0.090 |
seven | -0.086 |
1 | -0.085 |
Token | rocked |
Token ID | 36872 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
Chick | +0.089 |
burn | +0.089 |
ectar | +0.083 |
Madd | +0.078 |
arter | +0.078 |
Neg logit contributions | |
dice | -0.057 |
2 | -0.056 |
tug | -0.053 |
2 | -0.051 |
man | -0.051 |
Token | decided |
Token ID | 3066 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
burn | +0.008 |
Chick | +0.008 |
lor | +0.007 |
aby | +0.007 |
text | +0.007 |
Neg logit contributions | |
2 | -0.003 |
man | -0.003 |
seven | -0.003 |
old | -0.003 |
busy | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
Chick | +0.168 |
burn | +0.164 |
seed | +0.140 |
pt | +0.138 |
Bunny | +0.138 |
Neg logit contributions | |
2 | -0.090 |
2 | -0.089 |
dice | -0.086 |
seven | -0.085 |
man | -0.084 |
Token | sing |
Token ID | 1702 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
Chick | +0.048 |
burn | +0.046 |
seed | +0.040 |
ectar | +0.040 |
pt | +0.039 |
Neg logit contributions | |
agree | -0.022 |
sign | -0.022 |
dice | -0.021 |
2 | -0.020 |
2 | -0.020 |
Token | her |
Token ID | 607 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Chick | +0.259 |
burn | +0.254 |
seed | +0.216 |
lor | +0.214 |
Bunny | +0.213 |
Neg logit contributions | |
dice | -0.117 |
2 | -0.115 |
seven | -0.113 |
2 | -0.112 |
1 | -0.105 |
Token | a |
Token ID | 257 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
Chick | +0.098 |
burn | +0.092 |
Bunny | +0.080 |
pt | +0.080 |
seed | +0.079 |
Neg logit contributions | |
dice | -0.050 |
2 | -0.048 |
2 | -0.047 |
seven | -0.046 |
equation | -0.044 |
Token | lull |
Token ID | 42858 |
Feature activation | +9.05e+00 |
Pos logit contributions | |
dice | +0.032 |
2 | +0.031 |
2 | +0.030 |
seven | +0.029 |
equation | +0.029 |
Neg logit contributions | |
Chick | -0.027 |
burn | -0.026 |
pt | -0.022 |
Bunny | -0.021 |
seed | -0.021 |
Token | aby |
Token ID | 3930 |
Feature activation | +5.07e+00 |
Pos logit contributions | |
seed | +0.403 |
burn | +0.386 |
Chick | +0.382 |
Dod | +0.346 |
pic | +0.342 |
Neg logit contributions | |
man | -0.568 |
line | -0.525 |
and | -0.496 |
old | -0.495 |
first | -0.495 |
Token | . |
Token ID | 13 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
Chick | +0.424 |
burn | +0.407 |
Bunny | +0.357 |
pt | +0.352 |
Dod | +0.346 |
Neg logit contributions | |
2 | -0.208 |
2 | -0.206 |
dice | -0.205 |
seven | -0.199 |
1 | -0.190 |
Token | |
Token ID | 220 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
Chick | +0.027 |
burn | +0.026 |
pt | +0.023 |
Bunny | +0.022 |
lull | +0.022 |
Neg logit contributions | |
2 | -0.016 |
dice | -0.016 |
2 | -0.015 |
seven | -0.014 |
1 | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
burn | +0.043 |
Chick | +0.043 |
pt | +0.037 |
lull | +0.036 |
Bunny | +0.036 |
Neg logit contributions | |
2 | -0.020 |
dice | -0.018 |
2 | -0.018 |
1 | -0.016 |
3 | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
Chick | +0.047 |
burn | +0.045 |
Bunny | +0.040 |
pt | +0.038 |
D | +0.037 |
Neg logit contributions | |
dice | -0.036 |
2 | -0.035 |
2 | -0.033 |
equation | -0.032 |
seven | -0.032 |
Token | watered |
Token ID | 48024 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
Chick | +0.080 |
burn | +0.078 |
Bunny | +0.066 |
pt | +0.065 |
seed | +0.064 |
Neg logit contributions | |
2 | -0.064 |
dice | -0.063 |
2 | -0.060 |
seven | -0.058 |
equation | -0.057 |
Token | it |
Token ID | 340 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Chick | +0.280 |
burn | +0.276 |
pt | +0.236 |
Bunny | +0.236 |
seed | +0.225 |
Neg logit contributions | |
dice | -0.184 |
2 | -0.184 |
2 | -0.173 |
seven | -0.164 |
1 | -0.163 |
Token | and |
Token ID | 290 |
Feature activation | +1.23e-03 |
Pos logit contributions | |
Chick | +0.069 |
burn | +0.067 |
Bunny | +0.057 |
pt | +0.056 |
seed | +0.054 |
Neg logit contributions | |
dice | -0.060 |
2 | -0.060 |
2 | -0.057 |
seven | -0.055 |
equation | -0.055 |
Token | sang |
Token ID | 25889 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
burn | +0.000 |
Chick | +0.000 |
pt | +0.000 |
Bunny | +0.000 |
lor | +0.000 |
Neg logit contributions | |
2 | -0.000 |
dice | -0.000 |
2 | -0.000 |
seven | -0.000 |
1 | -0.000 |
Token | it |
Token ID | 340 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Chick | +0.252 |
burn | +0.250 |
Bunny | +0.212 |
pt | +0.209 |
seed | +0.204 |
Neg logit contributions | |
2 | -0.184 |
dice | -0.183 |
2 | -0.175 |
seven | -0.167 |
3 | -0.163 |
Token | lull |
Token ID | 42858 |
Feature activation | +8.89e+00 |
Pos logit contributions | |
Chick | +0.076 |
burn | +0.075 |
Bunny | +0.064 |
pt | +0.063 |
seed | +0.061 |
Neg logit contributions | |
dice | -0.056 |
2 | -0.055 |
2 | -0.053 |
seven | -0.052 |
equation | -0.051 |
Token | abies |
Token ID | 43256 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
burn | +0.593 |
seed | +0.483 |
Chick | +0.483 |
Dod | +0.449 |
Bunny | +0.448 |
Neg logit contributions | |
2 | -0.506 |
2 | -0.480 |
1 | -0.465 |
4 | -0.456 |
seven | -0.453 |
Token | , |
Token ID | 11 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
Chick | +0.245 |
burn | +0.237 |
Bunny | +0.208 |
pt | +0.203 |
seed | +0.201 |
Neg logit contributions | |
dice | -0.146 |
2 | -0.145 |
2 | -0.138 |
seven | -0.132 |
equation | -0.129 |
Token | hoping |
Token ID | 7725 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
Chick | +0.024 |
burn | +0.024 |
pt | +0.021 |
Bunny | +0.021 |
lor | +0.020 |
Neg logit contributions | |
2 | -0.017 |
dice | -0.017 |
2 | -0.016 |
seven | -0.016 |
1 | -0.015 |
Token | that |
Token ID | 326 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
burn | +0.168 |
Chick | +0.158 |
pt | +0.140 |
seed | +0.138 |
lor | +0.136 |
Neg logit contributions | |
2 | -0.097 |
2 | -0.095 |
dice | -0.090 |
1 | -0.090 |
seven | -0.089 |
Token | it |
Token ID | 340 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
burn | +0.095 |
Chick | +0.089 |
lor | +0.083 |
pt | +0.082 |
rim | +0.081 |
Neg logit contributions | |
2 | -0.052 |
1 | -0.050 |
2 | -0.050 |
seven | -0.048 |
dice | -0.048 |
Token | it |
Token ID | 340 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
burn | +0.013 |
Chick | +0.013 |
ectar | +0.011 |
rim | +0.011 |
seed | +0.011 |
Neg logit contributions | |
2 | -0.006 |
2 | -0.005 |
dice | -0.005 |
man | -0.005 |
seven | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
burn | +0.090 |
Chick | +0.088 |
ectar | +0.076 |
seed | +0.073 |
Betsy | +0.073 |
Neg logit contributions | |
2 | -0.047 |
seven | -0.047 |
2 | -0.046 |
man | -0.046 |
dice | -0.046 |
Token | singing |
Token ID | 13777 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
Chick | +0.103 |
burn | +0.098 |
lor | +0.094 |
seed | +0.089 |
maid | +0.085 |
Neg logit contributions | |
seven | -0.042 |
2 | -0.041 |
1 | -0.038 |
busy | -0.038 |
3 | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
Chick | +0.197 |
burn | +0.194 |
seed | +0.168 |
Madd | +0.167 |
lor | +0.164 |
Neg logit contributions | |
dice | -0.072 |
seven | -0.071 |
2 | -0.070 |
2 | -0.070 |
1 | -0.064 |
Token | gentle |
Token ID | 10296 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
dice | +0.031 |
2 | +0.030 |
2 | +0.029 |
seven | +0.028 |
equation | +0.027 |
Neg logit contributions | |
Chick | -0.037 |
burn | -0.036 |
pt | -0.031 |
Bunny | -0.031 |
seed | -0.030 |
Token | lull |
Token ID | 42858 |
Feature activation | +8.86e+00 |
Pos logit contributions | |
Chick | +0.034 |
burn | +0.031 |
pt | +0.027 |
Bunny | +0.027 |
seed | +0.026 |
Neg logit contributions | |
dice | -0.029 |
2 | -0.028 |
seven | -0.027 |
2 | -0.027 |
equation | -0.026 |
Token | aby |
Token ID | 3930 |
Feature activation | +4.90e+00 |
Pos logit contributions | |
seed | +0.396 |
Chick | +0.374 |
burn | +0.367 |
pt | +0.340 |
Betsy | +0.336 |
Neg logit contributions | |
man | -0.606 |
line | -0.592 |
sign | -0.558 |
seven | -0.555 |
number | -0.551 |
Token | . |
Token ID | 13 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
Chick | +0.414 |
burn | +0.396 |
Bunny | +0.354 |
pt | +0.347 |
seed | +0.347 |
Neg logit contributions | |
2 | -0.199 |
dice | -0.196 |
2 | -0.193 |
seven | -0.190 |
1 | -0.179 |
Token | The |
Token ID | 383 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
dice | +0.008 |
2 | +0.008 |
2 | +0.007 |
equation | +0.007 |
seven | +0.007 |
Neg logit contributions | |
Chick | -0.012 |
burn | -0.012 |
Bunny | -0.010 |
pt | -0.010 |
seed | -0.010 |
Token | boy |
Token ID | 2933 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
Chick | +0.072 |
burn | +0.069 |
Bunny | +0.061 |
pt | +0.057 |
D | +0.057 |
Neg logit contributions | |
2 | -0.068 |
dice | -0.068 |
2 | -0.065 |
equation | -0.064 |
1 | -0.063 |
Token | was |
Token ID | 373 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
2 | +0.106 |
2 | +0.106 |
seven | +0.104 |
man | +0.098 |
dice | +0.098 |
Neg logit contributions | |
burn | -0.177 |
Chick | -0.174 |
ectar | -0.154 |
lor | -0.147 |
seed | -0.145 |
Token | and |
Token ID | 290 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
2 | +0.081 |
dice | +0.079 |
Kyle | +0.078 |
1 | +0.078 |
2 | +0.077 |
Neg logit contributions | |
Chick | -0.093 |
burn | -0.081 |
light | -0.081 |
M | -0.073 |
lull | -0.072 |
Token | even |
Token ID | 772 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
dice | +0.009 |
2 | +0.009 |
2 | +0.008 |
equation | +0.008 |
seven | +0.008 |
Neg logit contributions | |
Chick | -0.012 |
burn | -0.012 |
Bunny | -0.010 |
pt | -0.010 |
lor | -0.010 |
Token | sang |
Token ID | 25889 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
dice | +0.014 |
2 | +0.014 |
2 | +0.013 |
seven | +0.013 |
equation | +0.012 |
Neg logit contributions | |
Chick | -0.019 |
burn | -0.019 |
Bunny | -0.016 |
pt | -0.016 |
lor | -0.015 |
Token | her |
Token ID | 607 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Chick | +0.256 |
burn | +0.251 |
Bunny | +0.214 |
pt | +0.211 |
seed | +0.208 |
Neg logit contributions | |
dice | -0.175 |
2 | -0.174 |
2 | -0.165 |
seven | -0.157 |
3 | -0.154 |
Token | brother |
Token ID | 3956 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
Chick | +0.080 |
burn | +0.077 |
Bunny | +0.066 |
pt | +0.065 |
seed | +0.064 |
Neg logit contributions | |
dice | -0.063 |
2 | -0.062 |
2 | -0.059 |
seven | -0.057 |
equation | -0.057 |
Token | lull |
Token ID | 42858 |
Feature activation | +8.85e+00 |
Pos logit contributions | |
Chick | +0.142 |
burn | +0.137 |
Bunny | +0.120 |
pt | +0.116 |
seed | +0.114 |
Neg logit contributions | |
dice | -0.105 |
2 | -0.105 |
2 | -0.098 |
equation | -0.094 |
seven | -0.093 |
Token | abies |
Token ID | 43256 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
burn | +0.538 |
seed | +0.485 |
Chick | +0.469 |
Dod | +0.439 |
unic | +0.428 |
Neg logit contributions | |
2 | -0.471 |
2 | -0.462 |
1 | -0.444 |
man | -0.441 |
first | -0.423 |
Token | . |
Token ID | 13 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
Chick | +0.221 |
burn | +0.214 |
Bunny | +0.185 |
pt | +0.180 |
seed | +0.175 |
Neg logit contributions | |
dice | -0.169 |
2 | -0.168 |
2 | -0.157 |
equation | -0.151 |
seven | -0.150 |
Token |
|
Token ID | 198 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
Chick | +0.037 |
burn | +0.036 |
Bunny | +0.031 |
pt | +0.031 |
seed | +0.030 |
Neg logit contributions | |
2 | -0.026 |
dice | -0.026 |
2 | -0.025 |
equation | -0.023 |
seven | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
Chick | +0.047 |
burn | +0.045 |
Bunny | +0.039 |
pt | +0.038 |
seed | +0.037 |
Neg logit contributions | |
dice | -0.031 |
2 | -0.031 |
2 | -0.029 |
equation | -0.028 |
seven | -0.028 |
Token | Every |
Token ID | 6109 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
Chick | +0.047 |
burn | +0.045 |
Bunny | +0.039 |
pt | +0.037 |
Madd | +0.037 |
Neg logit contributions | |
dice | -0.028 |
2 | -0.026 |
2 | -0.025 |
equation | -0.024 |
seven | -0.024 |
Token | by |
Token ID | 416 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
2 | +0.083 |
dice | +0.083 |
2 | +0.079 |
seven | +0.076 |
1 | +0.074 |
Neg logit contributions | |
Chick | -0.121 |
burn | -0.116 |
Bunny | -0.100 |
pt | -0.098 |
seed | -0.097 |
Token | and |
Token ID | 290 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
2 | +0.161 |
dice | +0.160 |
2 | +0.157 |
seven | +0.148 |
1 | +0.147 |
Neg logit contributions | |
Chick | -0.269 |
burn | -0.266 |
lor | -0.224 |
seed | -0.222 |
pt | -0.220 |
Token | sang |
Token ID | 25889 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
dice | +0.008 |
2 | +0.008 |
2 | +0.008 |
seven | +0.007 |
equation | +0.007 |
Neg logit contributions | |
Chick | -0.011 |
burn | -0.011 |
Bunny | -0.009 |
pt | -0.009 |
lor | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
Chick | +0.255 |
burn | +0.250 |
Bunny | +0.212 |
pt | +0.209 |
seed | +0.208 |
Neg logit contributions | |
dice | -0.164 |
2 | -0.164 |
2 | -0.157 |
seven | -0.150 |
1 | -0.145 |
Token | special |
Token ID | 2041 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
dice | +0.039 |
2 | +0.039 |
2 | +0.036 |
equation | +0.035 |
seven | +0.035 |
Neg logit contributions | |
Chick | -0.048 |
burn | -0.046 |
Bunny | -0.040 |
pt | -0.039 |
lull | -0.038 |
Token | lull |
Token ID | 42858 |
Feature activation | +8.84e+00 |
Pos logit contributions | |
Chick | +0.013 |
burn | +0.013 |
Bunny | +0.010 |
pt | +0.010 |
seed | +0.010 |
Neg logit contributions | |
dice | -0.016 |
2 | -0.016 |
2 | -0.015 |
equation | -0.015 |
seven | -0.015 |
Token | aby |
Token ID | 3930 |
Feature activation | +4.86e+00 |
Pos logit contributions | |
Chick | +0.391 |
burn | +0.378 |
seed | +0.353 |
pt | +0.313 |
Betsy | +0.310 |
Neg logit contributions | |
man | -0.637 |
line | -0.596 |
sign | -0.580 |
worker | -0.574 |
number | -0.558 |
Token | to |
Token ID | 284 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
Chick | +0.407 |
burn | +0.390 |
Bunny | +0.345 |
pt | +0.337 |
seed | +0.333 |
Neg logit contributions | |
2 | -0.204 |
dice | -0.204 |
2 | -0.200 |
seven | -0.198 |
1 | -0.184 |
Token | her |
Token ID | 607 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
burn | +0.029 |
Chick | +0.028 |
pt | +0.024 |
seed | +0.023 |
lor | +0.023 |
Neg logit contributions | |
2 | -0.018 |
2 | -0.018 |
dice | -0.018 |
seven | -0.017 |
1 | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
Chick | +0.088 |
burn | +0.086 |
pt | +0.073 |
Bunny | +0.072 |
seed | +0.072 |
Neg logit contributions | |
dice | -0.049 |
2 | -0.049 |
2 | -0.047 |
seven | -0.047 |
1 | -0.045 |
Token | The |
Token ID | 383 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
2 | +0.011 |
dice | +0.011 |
2 | +0.010 |
seven | +0.010 |
equation | +0.010 |
Neg logit contributions | |
Chick | -0.015 |
burn | -0.015 |
Bunny | -0.012 |
pt | -0.012 |
seed | -0.012 |
Token | mouth |
Token ID | 5422 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
Chick | +0.039 |
burn | +0.038 |
Bunny | +0.031 |
pt | +0.030 |
Madd | +0.029 |
Neg logit contributions | |
dice | -0.042 |
2 | -0.042 |
2 | -0.041 |
seven | -0.040 |
equation | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
Chick | +0.204 |
burn | +0.198 |
Bunny | +0.178 |
pt | +0.174 |
seed | +0.170 |
Neg logit contributions | |
dice | -0.090 |
2 | -0.088 |
2 | -0.079 |
equation | -0.076 |
seven | -0.075 |
Token | sang |
Token ID | 25889 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
2 | +0.008 |
dice | +0.008 |
2 | +0.008 |
seven | +0.008 |
1 | +0.007 |
Neg logit contributions | |
burn | -0.014 |
Chick | -0.014 |
ectar | -0.012 |
lor | -0.012 |
Bunny | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
Chick | +0.260 |
burn | +0.254 |
Bunny | +0.219 |
pt | +0.214 |
seed | +0.212 |
Neg logit contributions | |
dice | -0.165 |
2 | -0.164 |
2 | -0.155 |
seven | -0.147 |
equation | -0.144 |
Token | sweet |
Token ID | 6029 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
dice | +0.044 |
2 | +0.044 |
2 | +0.041 |
seven | +0.040 |
equation | +0.040 |
Neg logit contributions | |
Chick | -0.048 |
burn | -0.046 |
Bunny | -0.039 |
pt | -0.039 |
seed | -0.037 |
Token | lull |
Token ID | 42858 |
Feature activation | +8.84e+00 |
Pos logit contributions | |
Chick | +0.133 |
burn | +0.128 |
Bunny | +0.107 |
pt | +0.106 |
seed | +0.100 |
Neg logit contributions | |
dice | -0.135 |
2 | -0.134 |
2 | -0.129 |
seven | -0.123 |
equation | -0.123 |
Token | aby |
Token ID | 3930 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
burn | +0.380 |
seed | +0.346 |
Chick | +0.342 |
Betsy | +0.294 |
unic | +0.291 |
Neg logit contributions | |
man | -0.627 |
line | -0.583 |
2 | -0.576 |
seven | -0.569 |
sign | -0.562 |
Token | . |
Token ID | 13 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
Chick | +0.398 |
burn | +0.385 |
Bunny | +0.338 |
pt | +0.331 |
seed | +0.328 |
Neg logit contributions | |
dice | -0.205 |
2 | -0.205 |
2 | -0.202 |
seven | -0.200 |
1 | -0.185 |
Token | The |
Token ID | 383 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
2 | +0.008 |
dice | +0.008 |
2 | +0.007 |
seven | +0.007 |
3 | +0.007 |
Neg logit contributions | |
Chick | -0.013 |
burn | -0.013 |
pt | -0.011 |
Bunny | -0.011 |
seed | -0.010 |
Token | bird |
Token ID | 6512 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
Chick | +0.064 |
burn | +0.062 |
Bunny | +0.052 |
pt | +0.051 |
seed | +0.049 |
Neg logit contributions | |
2 | -0.060 |
dice | -0.060 |
2 | -0.057 |
seven | -0.055 |
equation | -0.054 |
Token | came |
Token ID | 1625 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
burn | +0.215 |
Chick | +0.211 |
ectar | +0.180 |
lor | +0.177 |
ulp | +0.175 |
Neg logit contributions | |
2 | -0.142 |
seven | -0.142 |
2 | -0.142 |
dice | -0.135 |
1 | -0.131 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
Chick | +0.026 |
burn | +0.024 |
Bunny | +0.022 |
pt | +0.021 |
lull | +0.020 |
Neg logit contributions | |
dice | -0.019 |
2 | -0.018 |
2 | -0.017 |
equation | -0.017 |
seven | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
dice | +0.027 |
2 | +0.027 |
2 | +0.026 |
seven | +0.025 |
1 | +0.024 |
Neg logit contributions | |
burn | -0.050 |
Chick | -0.050 |
pt | -0.042 |
Bunny | -0.042 |
seed | -0.041 |
Token | she |
Token ID | 673 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Chick | +0.013 |
burn | +0.012 |
pt | +0.010 |
Bunny | +0.010 |
seed | +0.010 |
Neg logit contributions | |
dice | -0.010 |
2 | -0.010 |
2 | -0.010 |
seven | -0.009 |
1 | -0.009 |
Token | noticed |
Token ID | 6810 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
Chick | +0.081 |
burn | +0.079 |
Bunny | +0.068 |
pt | +0.066 |
seed | +0.065 |
Neg logit contributions | |
2 | -0.051 |
dice | -0.051 |
2 | -0.048 |
seven | -0.046 |
equation | -0.045 |
Token | a |
Token ID | 257 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
burn | +0.170 |
Chick | +0.169 |
Bunny | +0.140 |
seed | +0.139 |
pt | +0.139 |
Neg logit contributions | |
2 | -0.103 |
dice | -0.101 |
2 | -0.097 |
1 | -0.091 |
seven | -0.090 |
Token | lull |
Token ID | 42858 |
Feature activation | +8.83e+00 |
Pos logit contributions | |
dice | +0.028 |
2 | +0.028 |
2 | +0.026 |
seven | +0.025 |
1 | +0.025 |
Neg logit contributions | |
Chick | -0.035 |
burn | -0.034 |
Bunny | -0.031 |
lull | -0.029 |
chick | -0.028 |
Token | aby |
Token ID | 3930 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
burn | +0.338 |
Chick | +0.329 |
seed | +0.308 |
pt | +0.265 |
Dod | +0.242 |
Neg logit contributions | |
man | -0.697 |
2 | -0.653 |
line | -0.643 |
seven | -0.638 |
sign | -0.633 |
Token | playing |
Token ID | 2712 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
Chick | +0.421 |
burn | +0.406 |
Bunny | +0.357 |
ectar | +0.348 |
lor | +0.347 |
Neg logit contributions | |
2 | -0.189 |
dice | -0.183 |
2 | -0.181 |
seven | -0.168 |
1 | -0.164 |
Token | in |
Token ID | 287 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Chick | +0.077 |
burn | +0.075 |
Bunny | +0.064 |
pt | +0.063 |
seed | +0.062 |
Neg logit contributions | |
dice | -0.049 |
2 | -0.048 |
2 | -0.045 |
equation | -0.044 |
seven | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
dice | +0.074 |
2 | +0.073 |
2 | +0.069 |
seven | +0.066 |
equation | +0.065 |
Neg logit contributions | |
Chick | -0.108 |
burn | -0.106 |
Bunny | -0.091 |
pt | -0.090 |
seed | -0.088 |
Token | distance |
Token ID | 5253 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
dice | +0.026 |
2 | +0.025 |
2 | +0.024 |
seven | +0.024 |
equation | +0.023 |
Neg logit contributions | |
Chick | -0.037 |
burn | -0.035 |
pt | -0.031 |
Bunny | -0.030 |
ectar | -0.030 |
Token | can |
Token ID | 460 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
2 | +0.113 |
dice | +0.111 |
2 | +0.111 |
1 | +0.105 |
seven | +0.103 |
Neg logit contributions | |
burn | -0.171 |
Chick | -0.167 |
pt | -0.149 |
seed | -0.146 |
lor | -0.144 |
Token | you |
Token ID | 345 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
2 | +0.022 |
dice | +0.022 |
2 | +0.021 |
man | +0.020 |
seven | +0.020 |
Neg logit contributions | |
burn | -0.040 |
Chick | -0.040 |
ectar | -0.037 |
pt | -0.036 |
ulp | -0.036 |
Token | whistle |
Token ID | 16121 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
dice | +0.046 |
2 | +0.046 |
2 | +0.044 |
seven | +0.042 |
agree | +0.040 |
Neg logit contributions | |
Chick | -0.082 |
burn | -0.079 |
seed | -0.067 |
Bunny | -0.067 |
pt | -0.066 |
Token | me |
Token ID | 502 |
Feature activation | +9.72e-02 |
Pos logit contributions | |
Chick | +0.136 |
burn | +0.131 |
Bunny | +0.114 |
pt | +0.111 |
seed | +0.108 |
Neg logit contributions | |
dice | -0.101 |
2 | -0.101 |
2 | -0.095 |
equation | -0.091 |
seven | -0.090 |
Token | a |
Token ID | 257 |
Feature activation | -8.22e-01 |
Pos logit contributions | |
Chick | +0.007 |
burn | +0.007 |
Bunny | +0.006 |
pt | +0.006 |
seed | +0.005 |
Neg logit contributions | |
dice | -0.006 |
2 | -0.006 |
2 | -0.005 |
seven | -0.005 |
equation | -0.005 |
Token | lull |
Token ID | 42858 |
Feature activation | +8.82e+00 |
Pos logit contributions | |
dice | +0.047 |
2 | +0.047 |
2 | +0.044 |
seven | +0.042 |
equation | +0.042 |
Neg logit contributions | |
Chick | -0.059 |
burn | -0.057 |
Bunny | -0.049 |
pt | -0.048 |
seed | -0.047 |
Token | aby |
Token ID | 3930 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
seed | +0.403 |
Chick | +0.396 |
pt | +0.364 |
burn | +0.330 |
streaming | +0.328 |
Neg logit contributions | |
man | -0.619 |
line | -0.561 |
first | -0.551 |
sign | -0.549 |
seven | -0.539 |
Token | so |
Token ID | 523 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
Chick | +0.321 |
burn | +0.303 |
Bunny | +0.263 |
pt | +0.256 |
seed | +0.249 |
Neg logit contributions | |
2 | -0.286 |
dice | -0.286 |
2 | -0.274 |
seven | -0.266 |
equation | -0.259 |
Token | I |
Token ID | 314 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
burn | +0.045 |
Chick | +0.043 |
streaming | +0.037 |
lor | +0.037 |
seed | +0.037 |
Neg logit contributions | |
dice | -0.024 |
2 | -0.023 |
seven | -0.023 |
2 | -0.022 |
3 | -0.021 |
Token | can |
Token ID | 460 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
Chick | +0.054 |
burn | +0.052 |
Bunny | +0.045 |
seed | +0.043 |
pt | +0.043 |
Neg logit contributions | |
dice | -0.038 |
2 | -0.037 |
2 | -0.035 |
seven | -0.034 |
equation | -0.033 |
Token | fall |
Token ID | 2121 |
Feature activation | +9.70e-01 |
Pos logit contributions | |
dice | +0.023 |
2 | +0.023 |
2 | +0.021 |
seven | +0.021 |
equation | +0.020 |
Neg logit contributions | |
Chick | -0.035 |
burn | -0.033 |
Bunny | -0.029 |
seed | -0.029 |
pt | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
Chick | +0.030 |
burn | +0.029 |
Bunny | +0.027 |
pt | +0.025 |
lull | +0.025 |
Neg logit contributions | |
dice | -0.017 |
2 | -0.016 |
equation | -0.015 |
2 | -0.014 |
seven | -0.013 |
Token | sang |
Token ID | 25889 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
2 | +0.010 |
dice | +0.009 |
2 | +0.009 |
man | +0.009 |
agree | +0.008 |
Neg logit contributions | |
burn | -0.029 |
Chick | -0.029 |
ectar | -0.026 |
lor | -0.026 |
pt | -0.025 |
Token | him |
Token ID | 683 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
Chick | +0.253 |
burn | +0.245 |
Bunny | +0.213 |
pt | +0.208 |
seed | +0.204 |
Neg logit contributions | |
dice | -0.169 |
2 | -0.169 |
2 | -0.158 |
seven | -0.151 |
equation | -0.150 |
Token | a |
Token ID | 257 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
Chick | +0.029 |
burn | +0.028 |
Bunny | +0.024 |
pt | +0.024 |
seed | +0.024 |
Neg logit contributions | |
dice | -0.017 |
2 | -0.017 |
2 | -0.016 |
seven | -0.015 |
equation | -0.015 |
Token | soft |
Token ID | 2705 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
dice | +0.041 |
2 | +0.041 |
2 | +0.039 |
seven | +0.037 |
equation | +0.037 |
Neg logit contributions | |
Chick | -0.045 |
burn | -0.043 |
Bunny | -0.037 |
pt | -0.036 |
seed | -0.035 |
Token | lull |
Token ID | 42858 |
Feature activation | +8.82e+00 |
Pos logit contributions | |
Chick | +0.144 |
burn | +0.136 |
Bunny | +0.112 |
pt | +0.112 |
seed | +0.107 |
Neg logit contributions | |
dice | -0.172 |
2 | -0.169 |
2 | -0.163 |
seven | -0.159 |
equation | -0.159 |
Token | aby |
Token ID | 3930 |
Feature activation | +4.87e+00 |
Pos logit contributions | |
seed | +0.402 |
burn | +0.382 |
Chick | +0.358 |
text | +0.329 |
unic | +0.328 |
Neg logit contributions | |
man | -0.631 |
worker | -0.572 |
line | -0.548 |
first | -0.538 |
2 | -0.530 |
Token | . |
Token ID | 13 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
Chick | +0.400 |
burn | +0.384 |
Bunny | +0.340 |
seed | +0.331 |
pt | +0.331 |
Neg logit contributions | |
2 | -0.213 |
dice | -0.211 |
2 | -0.205 |
seven | -0.198 |
1 | -0.187 |
Token | The |
Token ID | 383 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Chick | +0.001 |
burn | +0.001 |
Bunny | +0.001 |
pt | +0.001 |
seed | +0.001 |
Neg logit contributions | |
2 | -0.001 |
dice | -0.001 |
2 | -0.001 |
equation | -0.001 |
seven | -0.001 |
Token | little |
Token ID | 1310 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Chick | +0.074 |
burn | +0.072 |
Bunny | +0.063 |
pt | +0.060 |
lull | +0.059 |
Neg logit contributions | |
dice | -0.068 |
2 | -0.067 |
2 | -0.063 |
equation | -0.061 |
seven | -0.061 |
Token | boy |
Token ID | 2933 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
Chick | +0.123 |
burn | +0.121 |
Bunny | +0.110 |
pt | +0.106 |
seed | +0.104 |
Neg logit contributions | |
dice | -0.051 |
2 | -0.050 |
2 | -0.045 |
equation | -0.043 |
seven | -0.042 |
Token | wind |
Token ID | 2344 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
Chick | +0.084 |
burn | +0.082 |
Bunny | +0.069 |
pt | +0.069 |
seed | +0.068 |
Neg logit contributions | |
dice | -0.066 |
2 | -0.065 |
2 | -0.062 |
seven | -0.060 |
equation | -0.059 |
Token | is |
Token ID | 318 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
dice | +0.122 |
2 | +0.121 |
2 | +0.113 |
seven | +0.108 |
equation | +0.107 |
Neg logit contributions | |
Chick | -0.208 |
burn | -0.198 |
Bunny | -0.175 |
pt | -0.170 |
seed | -0.167 |
Token | just |
Token ID | 655 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
2 | +0.022 |
2 | +0.022 |
dice | +0.022 |
seven | +0.021 |
1 | +0.020 |
Neg logit contributions | |
Chick | -0.038 |
burn | -0.036 |
lor | -0.032 |
pt | -0.032 |
seed | -0.031 |
Token | singing |
Token ID | 13777 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
2 | +0.084 |
2 | +0.084 |
dice | +0.082 |
seven | +0.080 |
1 | +0.077 |
Neg logit contributions | |
Chick | -0.140 |
burn | -0.135 |
lor | -0.120 |
pt | -0.117 |
seed | -0.116 |
Token | a |
Token ID | 257 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
Chick | +0.163 |
burn | +0.162 |
Madd | +0.140 |
seed | +0.139 |
Bunny | +0.139 |
Neg logit contributions | |
dice | -0.082 |
2 | -0.080 |
seven | -0.078 |
2 | -0.078 |
1 | -0.071 |
Token | lull |
Token ID | 42858 |
Feature activation | +8.80e+00 |
Pos logit contributions | |
dice | +0.037 |
2 | +0.036 |
2 | +0.034 |
seven | +0.033 |
equation | +0.033 |
Neg logit contributions | |
Chick | -0.050 |
burn | -0.049 |
pt | -0.043 |
Bunny | -0.042 |
seed | -0.042 |
Token | aby |
Token ID | 3930 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
seed | +0.439 |
Chick | +0.353 |
burn | +0.339 |
pt | +0.339 |
Betsy | +0.331 |
Neg logit contributions | |
man | -0.598 |
line | -0.556 |
first | -0.537 |
driver | -0.523 |
sign | -0.523 |
Token | to |
Token ID | 284 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
Chick | +0.356 |
burn | +0.342 |
Bunny | +0.304 |
Madd | +0.301 |
pt | +0.299 |
Neg logit contributions | |
dice | -0.237 |
2 | -0.234 |
seven | -0.229 |
2 | -0.228 |
1 | -0.211 |
Token | help |
Token ID | 1037 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
burn | +0.026 |
Chick | +0.025 |
lor | +0.024 |
seed | +0.023 |
maid | +0.023 |
Neg logit contributions | |
2 | -0.014 |
2 | -0.014 |
seven | -0.014 |
dice | -0.014 |
sign | -0.013 |
Token | you |
Token ID | 345 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
burn | +0.017 |
Chick | +0.016 |
seed | +0.015 |
lor | +0.015 |
pt | +0.015 |
Neg logit contributions | |
2 | -0.009 |
dice | -0.009 |
2 | -0.009 |
3 | -0.008 |
1 | -0.008 |
Token | sleep |
Token ID | 3993 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
agree | +0.042 |
2 | +0.040 |
2 | +0.040 |
dice | +0.039 |
seven | +0.038 |
Neg logit contributions | |
Chick | -0.077 |
burn | -0.075 |
lor | -0.067 |
seed | -0.067 |
streaming | -0.065 |
Token | she |
Token ID | 673 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
burn | +0.010 |
Chick | +0.010 |
rim | +0.009 |
lor | +0.009 |
seed | +0.009 |
Neg logit contributions | |
dice | -0.005 |
2 | -0.005 |
2 | -0.005 |
man | -0.005 |
equation | -0.005 |
Token | started |
Token ID | 2067 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
burn | +0.080 |
Chick | +0.079 |
Bunny | +0.068 |
seed | +0.067 |
Betsy | +0.067 |
Neg logit contributions | |
2 | -0.054 |
dice | -0.052 |
2 | -0.051 |
seven | -0.049 |
3 | -0.048 |
Token | to |
Token ID | 284 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
2 | +0.048 |
dice | +0.046 |
2 | +0.046 |
equation | +0.045 |
3 | +0.043 |
Neg logit contributions | |
Chick | -0.092 |
burn | -0.088 |
seed | -0.082 |
lor | -0.080 |
Bunny | -0.079 |
Token | sing |
Token ID | 1702 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
Chick | +0.028 |
burn | +0.028 |
seed | +0.024 |
lor | +0.024 |
Bunny | +0.024 |
Neg logit contributions | |
dice | -0.017 |
2 | -0.017 |
2 | -0.016 |
equation | -0.015 |
agree | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
Chick | +0.230 |
burn | +0.225 |
Bunny | +0.194 |
seed | +0.194 |
pt | +0.190 |
Neg logit contributions | |
dice | -0.122 |
2 | -0.122 |
2 | -0.119 |
seven | -0.114 |
1 | -0.109 |
Token | lull |
Token ID | 42858 |
Feature activation | +8.78e+00 |
Pos logit contributions | |
dice | +0.041 |
2 | +0.041 |
2 | +0.039 |
seven | +0.038 |
equation | +0.037 |
Neg logit contributions | |
Chick | -0.040 |
burn | -0.039 |
Bunny | -0.033 |
pt | -0.032 |
seed | -0.031 |
Token | aby |
Token ID | 3930 |
Feature activation | +4.77e+00 |
Pos logit contributions | |
seed | +0.395 |
burn | +0.379 |
Chick | +0.334 |
Dod | +0.316 |
pt | +0.310 |
Neg logit contributions | |
man | -0.606 |
line | -0.582 |
and | -0.556 |
2 | -0.551 |
sign | -0.548 |
Token | to |
Token ID | 284 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
Chick | +0.405 |
burn | +0.387 |
Bunny | +0.347 |
pt | +0.343 |
seed | +0.342 |
Neg logit contributions | |
2 | -0.190 |
2 | -0.184 |
dice | -0.184 |
seven | -0.177 |
1 | -0.168 |
Token | herself |
Token ID | 5223 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
burn | +0.030 |
Chick | +0.028 |
seed | +0.027 |
lor | +0.025 |
pt | +0.025 |
Neg logit contributions | |
2 | -0.015 |
dice | -0.015 |
2 | -0.015 |
seven | -0.014 |
agree | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
2 | +0.044 |
dice | +0.044 |
2 | +0.043 |
equation | +0.040 |
seven | +0.039 |
Neg logit contributions | |
Chick | -0.091 |
burn | -0.088 |
Bunny | -0.078 |
seed | -0.077 |
pt | -0.076 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
2 | +0.010 |
2 | +0.010 |
dice | +0.009 |
3 | +0.009 |
1 | +0.009 |
Neg logit contributions | |
burn | -0.024 |
Chick | -0.022 |
seed | -0.020 |
pt | -0.020 |
rim | -0.020 |
Token | started |
Token ID | 2067 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Chick | +0.006 |
burn | +0.006 |
Bunny | +0.005 |
pt | +0.005 |
seed | +0.005 |
Neg logit contributions | |
dice | -0.005 |
2 | -0.005 |
2 | -0.005 |
seven | -0.004 |
equation | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
2 | +0.062 |
dice | +0.060 |
2 | +0.059 |
equation | +0.056 |
seven | +0.056 |
Neg logit contributions | |
Chick | -0.087 |
burn | -0.083 |
pt | -0.073 |
lor | -0.071 |
Bunny | -0.070 |
Token | hum |
Token ID | 1311 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
Chick | +0.026 |
burn | +0.026 |
Bunny | +0.022 |
pt | +0.022 |
lor | +0.021 |
Neg logit contributions | |
dice | -0.016 |
2 | -0.016 |
2 | -0.015 |
equation | -0.014 |
seven | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
dice | +0.023 |
2 | +0.023 |
2 | +0.022 |
equation | +0.021 |
seven | +0.021 |
Neg logit contributions | |
Chick | -0.030 |
burn | -0.029 |
Bunny | -0.025 |
pt | -0.024 |
seed | -0.024 |
Token | little |
Token ID | 1310 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
dice | +0.058 |
2 | +0.058 |
2 | +0.054 |
equation | +0.053 |
1 | +0.053 |
Neg logit contributions | |
Chick | -0.045 |
burn | -0.042 |
lull | -0.037 |
Bunny | -0.035 |
pt | -0.033 |
Token | lull |
Token ID | 42858 |
Feature activation | +8.76e+00 |
Pos logit contributions | |
Chick | +0.084 |
burn | +0.080 |
Bunny | +0.071 |
lull | +0.071 |
seed | +0.066 |
Neg logit contributions | |
dice | -0.071 |
2 | -0.069 |
2 | -0.063 |
equation | -0.063 |
3 | -0.061 |
Token | aby |
Token ID | 3930 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
burn | +0.371 |
seed | +0.345 |
Chick | +0.341 |
pt | +0.298 |
unic | +0.291 |
Neg logit contributions | |
man | -0.616 |
2 | -0.611 |
line | -0.607 |
seven | -0.590 |
2 | -0.585 |
Token | , |
Token ID | 11 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
Chick | +0.397 |
burn | +0.384 |
Bunny | +0.338 |
pt | +0.334 |
seed | +0.327 |
Neg logit contributions | |
2 | -0.209 |
dice | -0.206 |
2 | -0.199 |
seven | -0.191 |
1 | -0.182 |
Token | before |
Token ID | 878 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
Chick | +0.008 |
burn | +0.008 |
Bunny | +0.007 |
pt | +0.007 |
seed | +0.007 |
Neg logit contributions | |
2 | -0.005 |
dice | -0.005 |
2 | -0.005 |
seven | -0.005 |
equation | -0.005 |
Token | heading |
Token ID | 9087 |
Feature activation | +6.63e-02 |
Pos logit contributions | |
2 | +0.020 |
dice | +0.019 |
2 | +0.019 |
1 | +0.018 |
3 | +0.018 |
Neg logit contributions | |
Chick | -0.026 |
burn | -0.026 |
seed | -0.022 |
pt | -0.022 |
lor | -0.022 |
Token | back |
Token ID | 736 |
Feature activation | +3.52e-02 |
Pos logit contributions | |
Chick | +0.005 |
burn | +0.004 |
Bunny | +0.004 |
pt | +0.004 |
seed | +0.004 |
Neg logit contributions | |
dice | -0.004 |
2 | -0.004 |
2 | -0.004 |
seven | -0.004 |
equation | -0.004 |
Token | She |
Token ID | 1375 |
Feature activation | +5.72e-02 |
Pos logit contributions | |
dice | +0.023 |
2 | +0.022 |
2 | +0.021 |
equation | +0.020 |
seven | +0.020 |
Neg logit contributions | |
Chick | -0.032 |
burn | -0.030 |
Bunny | -0.027 |
pt | -0.026 |
seed | -0.025 |
Token | quickly |
Token ID | 2952 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
Chick | +0.004 |
burn | +0.004 |
Bunny | +0.003 |
pt | +0.003 |
seed | +0.003 |
Neg logit contributions | |
dice | -0.003 |
2 | -0.003 |
2 | -0.003 |
equation | -0.003 |
seven | -0.003 |
Token | sang |
Token ID | 25889 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
2 | +0.020 |
dice | +0.020 |
2 | +0.019 |
equation | +0.019 |
seven | +0.018 |
Neg logit contributions | |
Chick | -0.025 |
burn | -0.024 |
Bunny | -0.021 |
pt | -0.021 |
D | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | -8.97e-01 |
Pos logit contributions | |
Chick | +0.221 |
burn | +0.209 |
Bunny | +0.185 |
pt | +0.177 |
lull | +0.173 |
Neg logit contributions | |
dice | -0.194 |
2 | -0.193 |
2 | -0.177 |
equation | -0.175 |
seven | -0.170 |
Token | short |
Token ID | 1790 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
2 | +0.058 |
dice | +0.057 |
2 | +0.054 |
1 | +0.054 |
equation | +0.053 |
Neg logit contributions | |
Chick | -0.057 |
burn | -0.054 |
lull | -0.049 |
Bunny | -0.047 |
pt | -0.044 |
Token | lull |
Token ID | 42858 |
Feature activation | +8.76e+00 |
Pos logit contributions | |
2 | +0.019 |
dice | +0.018 |
2 | +0.017 |
1 | +0.017 |
1 | +0.017 |
Neg logit contributions | |
burn | -0.015 |
Chick | -0.015 |
lull | -0.013 |
Bunny | -0.012 |
streaming | -0.011 |
Token | aby |
Token ID | 3930 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
burn | +0.381 |
Chick | +0.365 |
seed | +0.336 |
pt | +0.289 |
Dod | +0.274 |
Neg logit contributions | |
man | -0.674 |
2 | -0.644 |
dice | -0.639 |
2 | -0.632 |
line | -0.625 |
Token | to |
Token ID | 284 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
Chick | +0.395 |
burn | +0.381 |
Bunny | +0.336 |
pt | +0.331 |
seed | +0.324 |
Neg logit contributions | |
dice | -0.211 |
2 | -0.211 |
2 | -0.198 |
seven | -0.190 |
equation | -0.182 |
Token | it |
Token ID | 340 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
Chick | +0.019 |
burn | +0.019 |
pt | +0.016 |
seed | +0.016 |
Bunny | +0.016 |
Neg logit contributions | |
2 | -0.012 |
dice | -0.012 |
2 | -0.011 |
seven | -0.011 |
1 | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
Chick | +0.070 |
burn | +0.068 |
Bunny | +0.059 |
pt | +0.058 |
seed | +0.058 |
Neg logit contributions | |
dice | -0.038 |
2 | -0.038 |
2 | -0.037 |
seven | -0.035 |
equation | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | +5.06e-02 |
Pos logit contributions | |
2 | +0.022 |
dice | +0.022 |
2 | +0.021 |
3 | +0.019 |
1 | +0.019 |
Neg logit contributions | |
burn | -0.037 |
Chick | -0.036 |
pt | -0.031 |
Bunny | -0.030 |
seed | -0.030 |
Token | 's |
Token ID | 338 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
Chick | +0.234 |
burn | +0.229 |
pt | +0.202 |
Bunny | +0.200 |
lor | +0.197 |
Neg logit contributions | |
2 | -0.110 |
dice | -0.109 |
2 | -0.102 |
seven | -0.098 |
1 | -0.093 |
Token | feathers |
Token ID | 27400 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
Chick | +0.101 |
burn | +0.098 |
pt | +0.082 |
Bunny | +0.081 |
seed | +0.078 |
Neg logit contributions | |
2 | -0.090 |
seven | -0.087 |
dice | -0.087 |
2 | -0.087 |
3 | -0.080 |
Token | and |
Token ID | 290 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
Chick | +0.263 |
burn | +0.253 |
Bunny | +0.226 |
lor | +0.223 |
pt | +0.223 |
Neg logit contributions | |
2 | -0.066 |
dice | -0.062 |
2 | -0.059 |
seven | -0.055 |
1 | -0.050 |
Token | sang |
Token ID | 25889 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
2 | +0.012 |
dice | +0.012 |
2 | +0.011 |
seven | +0.011 |
man | +0.010 |
Neg logit contributions | |
burn | -0.018 |
Chick | -0.018 |
lor | -0.016 |
pt | -0.016 |
ectar | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | -8.29e-01 |
Pos logit contributions | |
burn | +0.254 |
Chick | +0.250 |
seed | +0.212 |
pt | +0.211 |
Bunny | +0.209 |
Neg logit contributions | |
2 | -0.146 |
dice | -0.144 |
2 | -0.143 |
seven | -0.137 |
1 | -0.131 |
Token | lull |
Token ID | 42858 |
Feature activation | +8.75e+00 |
Pos logit contributions | |
dice | +0.051 |
2 | +0.051 |
2 | +0.048 |
seven | +0.046 |
equation | +0.046 |
Neg logit contributions | |
Chick | -0.056 |
burn | -0.054 |
Bunny | -0.046 |
pt | -0.045 |
seed | -0.044 |
Token | aby |
Token ID | 3930 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
burn | +0.379 |
seed | +0.357 |
Chick | +0.338 |
pic | +0.331 |
pt | +0.325 |
Neg logit contributions | |
man | -0.571 |
line | -0.541 |
seven | -0.516 |
sign | -0.513 |
ars | -0.513 |
Token | . |
Token ID | 13 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
Chick | +0.390 |
burn | +0.375 |
Bunny | +0.334 |
pt | +0.331 |
lor | +0.322 |
Neg logit contributions | |
2 | -0.200 |
dice | -0.198 |
seven | -0.197 |
2 | -0.195 |
1 | -0.179 |
Token | The |
Token ID | 383 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
2 | +0.008 |
2 | +0.008 |
dice | +0.007 |
1 | +0.007 |
3 | +0.007 |
Neg logit contributions | |
burn | -0.016 |
Chick | -0.015 |
pt | -0.014 |
seed | -0.013 |
maid | -0.013 |
Token | bird |
Token ID | 6512 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
Chick | +0.053 |
burn | +0.051 |
Bunny | +0.042 |
pt | +0.040 |
seed | +0.039 |
Neg logit contributions | |
dice | -0.068 |
2 | -0.068 |
2 | -0.065 |
equation | -0.063 |
seven | -0.062 |
Token | slowly |
Token ID | 6364 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
burn | +0.200 |
Chick | +0.195 |
lor | +0.171 |
ectar | +0.168 |
ulp | +0.165 |
Neg logit contributions | |
seven | -0.130 |
2 | -0.129 |
2 | -0.126 |
dice | -0.125 |
man | -0.123 |
Token | � |
Token ID | 6184 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
dice | +0.050 |
2 | +0.050 |
2 | +0.046 |
equation | +0.044 |
3 | +0.044 |
Neg logit contributions | |
Chick | -0.062 |
burn | -0.060 |
Bunny | -0.052 |
pt | -0.051 |
seed | -0.050 |
Token | � |
Token ID | 95 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
Chick | +0.005 |
burn | +0.004 |
Bunny | +0.004 |
Sleep | +0.004 |
D | +0.004 |
Neg logit contributions | |
dice | -0.004 |
2 | -0.004 |
equation | -0.004 |
2 | -0.004 |
seven | -0.003 |
Token | € |
Token ID | 26391 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
dice | +0.056 |
2 | +0.048 |
2 | +0.046 |
seven | +0.044 |
agree | +0.044 |
Neg logit contributions | |
Chick | -0.055 |
lor | -0.051 |
Sleep | -0.050 |
burn | -0.049 |
Bunny | -0.045 |
Token | � |
Token ID | 447 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
dice | +0.072 |
2 | +0.070 |
2 | +0.067 |
equation | +0.064 |
seven | +0.063 |
Neg logit contributions | |
Chick | -0.097 |
burn | -0.092 |
Bunny | -0.081 |
pt | -0.077 |
lor | -0.077 |
Token | � |
Token ID | 250 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
dice | +0.191 |
2 | +0.178 |
2 | +0.177 |
equation | +0.173 |
seven | +0.171 |
Neg logit contributions | |
Chick | -0.146 |
burn | -0.140 |
Bunny | -0.119 |
lor | -0.116 |
Sleep | -0.112 |
Token | 1 |
Token ID | 352 |
Feature activation | -9.22e+00 |
Pos logit contributions | |
dice | +0.057 |
2 | +0.053 |
2 | +0.052 |
equation | +0.051 |
seven | +0.050 |
Neg logit contributions | |
Chick | -0.067 |
burn | -0.066 |
Bunny | -0.055 |
Sleep | -0.053 |
D | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
dice | +0.553 |
2 | +0.529 |
equation | +0.514 |
scoreboard | +0.481 |
Kyle | +0.472 |
Neg logit contributions | |
Chick | -0.563 |
burn | -0.547 |
Bunny | -0.491 |
pt | -0.479 |
seed | -0.458 |
Token | 2 |
Token ID | 362 |
Feature activation | -7.89e+00 |
Pos logit contributions | |
dice | +0.015 |
equation | +0.014 |
2 | +0.014 |
bench | +0.013 |
Kyle | +0.012 |
Neg logit contributions | |
Chick | -0.024 |
burn | -0.023 |
Bunny | -0.021 |
D | -0.020 |
Pig | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
dice | +0.474 |
equation | +0.446 |
2 | +0.439 |
scoreboard | +0.415 |
five | +0.411 |
Neg logit contributions | |
Chick | -0.508 |
burn | -0.460 |
Bunny | -0.421 |
pt | -0.396 |
D | -0.390 |
Token | 3 |
Token ID | 513 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
dice | +0.022 |
equation | +0.021 |
2 | +0.021 |
bench | +0.019 |
Kyle | +0.018 |
Neg logit contributions | |
Chick | -0.034 |
burn | -0.032 |
Bunny | -0.030 |
D | -0.028 |
Pig | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
dice | +0.135 |
2 | +0.130 |
equation | +0.123 |
2 | +0.118 |
3 | +0.117 |
Neg logit contributions | |
Chick | -0.134 |
burn | -0.117 |
Bunny | -0.110 |
pt | -0.108 |
seed | -0.106 |
Token | that |
Token ID | 326 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
2 | +0.356 |
dice | +0.352 |
equation | +0.325 |
2 | +0.323 |
3 | +0.322 |
Neg logit contributions | |
burn | -0.249 |
Chick | -0.247 |
pt | -0.218 |
Bunny | -0.203 |
lull | -0.201 |
Token | said |
Token ID | 531 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
Chick | +0.077 |
burn | +0.074 |
Bunny | +0.065 |
pt | +0.064 |
seed | +0.062 |
Neg logit contributions | |
dice | -0.049 |
2 | -0.049 |
2 | -0.045 |
equation | -0.043 |
seven | -0.043 |
Token | " |
Token ID | 366 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
2 | +0.097 |
dice | +0.095 |
2 | +0.092 |
seven | +0.085 |
1 | +0.084 |
Neg logit contributions | |
Chick | -0.202 |
burn | -0.199 |
Bunny | -0.172 |
pt | -0.171 |
seed | -0.170 |
Token | Park |
Token ID | 25478 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
dice | +0.069 |
2 | +0.067 |
2 | +0.063 |
equation | +0.062 |
seven | +0.061 |
Neg logit contributions | |
Chick | -0.080 |
burn | -0.079 |
Bunny | -0.066 |
pt | -0.064 |
seed | -0.063 |
Token | - |
Token ID | 532 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Chick | +0.045 |
burn | +0.043 |
Bunny | +0.037 |
pt | +0.036 |
lor | +0.036 |
Neg logit contributions | |
dice | -0.041 |
2 | -0.041 |
2 | -0.037 |
equation | -0.037 |
seven | -0.036 |
Token | 1 |
Token ID | 352 |
Feature activation | -9.18e+00 |
Pos logit contributions | |
dice | +0.077 |
2 | +0.073 |
equation | +0.071 |
2 | +0.067 |
seven | +0.065 |
Neg logit contributions | |
Chick | -0.117 |
burn | -0.110 |
Bunny | -0.099 |
D | -0.093 |
Sleep | -0.092 |
Token | mile |
Token ID | 10591 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
dice | +0.551 |
2 | +0.529 |
equation | +0.523 |
2 | +0.495 |
3 | +0.476 |
Neg logit contributions | |
burn | -0.580 |
Chick | -0.572 |
lor | -0.475 |
Bunny | -0.472 |
pt | -0.453 |
Token | ". |
Token ID | 1911 |
Feature activation | +9.61e-01 |
Pos logit contributions | |
Chick | +0.023 |
burn | +0.022 |
Bunny | +0.019 |
pt | +0.018 |
lor | +0.018 |
Neg logit contributions | |
dice | -0.023 |
2 | -0.023 |
equation | -0.022 |
2 | -0.021 |
3 | -0.021 |
Token | They |
Token ID | 1119 |
Feature activation | -4.69e-02 |
Pos logit contributions | |
Chick | +0.066 |
burn | +0.058 |
Bunny | +0.056 |
D | +0.054 |
pt | +0.052 |
Neg logit contributions | |
dice | -0.058 |
2 | -0.057 |
equation | -0.055 |
2 | -0.053 |
seven | -0.052 |
Token | cheered |
Token ID | 34767 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
dice | +0.003 |
equation | +0.003 |
2 | +0.003 |
2 | +0.003 |
scoreboard | +0.003 |
Neg logit contributions | |
Chick | -0.003 |
burn | -0.003 |
pt | -0.002 |
Bunny | -0.002 |
D | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
dice | +0.086 |
2 | +0.082 |
equation | +0.077 |
2 | +0.075 |
3 | +0.073 |
Neg logit contributions | |
Chick | -0.105 |
burn | -0.100 |
Bunny | -0.089 |
pt | -0.085 |
lull | -0.084 |
Token | , |
Token ID | 11 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
dice | +0.265 |
2 | +0.256 |
equation | +0.244 |
2 | +0.240 |
3 | +0.230 |
Neg logit contributions | |
Chick | -0.303 |
burn | -0.287 |
Bunny | -0.242 |
pt | -0.233 |
lor | -0.233 |
Token | 3 |
Token ID | 513 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
dice | +0.006 |
equation | +0.006 |
Kyle | +0.006 |
2 | +0.005 |
bench | +0.005 |
Neg logit contributions | |
Chick | -0.016 |
burn | -0.015 |
Bunny | -0.013 |
Pig | -0.013 |
D | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
dice | +0.131 |
2 | +0.129 |
2 | +0.122 |
equation | +0.121 |
3 | +0.116 |
Neg logit contributions | |
Chick | -0.153 |
burn | -0.143 |
Bunny | -0.124 |
pt | -0.121 |
seed | -0.119 |
Token | 2 |
Token ID | 362 |
Feature activation | -7.81e+00 |
Pos logit contributions | |
dice | +0.008 |
equation | +0.008 |
2 | +0.007 |
Kyle | +0.007 |
bench | +0.007 |
Neg logit contributions | |
Chick | -0.018 |
burn | -0.017 |
Bunny | -0.015 |
Pig | -0.014 |
D | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
dice | +0.449 |
2 | +0.432 |
equation | +0.415 |
2 | +0.403 |
seven | +0.388 |
Neg logit contributions | |
Chick | -0.552 |
burn | -0.522 |
Bunny | -0.448 |
pt | -0.436 |
seed | -0.426 |
Token | 1 |
Token ID | 352 |
Feature activation | -9.18e+00 |
Pos logit contributions | |
dice | +0.008 |
equation | +0.008 |
2 | +0.007 |
Kyle | +0.007 |
bench | +0.007 |
Neg logit contributions | |
Chick | -0.020 |
burn | -0.019 |
Bunny | -0.017 |
Pig | -0.016 |
D | -0.016 |
Token | ". |
Token ID | 1911 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
dice | +0.612 |
2 | +0.592 |
equation | +0.591 |
2 | +0.556 |
Kyle | +0.543 |
Neg logit contributions | |
Chick | -0.533 |
burn | -0.519 |
Bunny | -0.418 |
lor | -0.409 |
pt | -0.389 |
Token | They |
Token ID | 1119 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
Chick | +0.075 |
burn | +0.065 |
Bunny | +0.063 |
Madd | +0.060 |
D | +0.059 |
Neg logit contributions | |
dice | -0.075 |
2 | -0.074 |
equation | -0.069 |
2 | -0.069 |
seven | -0.067 |
Token | hear |
Token ID | 3285 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
Chick | +0.001 |
burn | +0.001 |
pt | +0.001 |
Bunny | +0.001 |
M | +0.001 |
Neg logit contributions | |
equation | -0.001 |
2 | -0.001 |
dice | -0.001 |
bench | -0.001 |
equations | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
dice | +0.035 |
2 | +0.035 |
2 | +0.033 |
seven | +0.031 |
equation | +0.031 |
Neg logit contributions | |
Chick | -0.052 |
burn | -0.051 |
Bunny | -0.044 |
pt | -0.043 |
seed | -0.042 |
Token | big |
Token ID | 1263 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
dice | +0.060 |
2 | +0.058 |
equation | +0.055 |
1 | +0.054 |
seven | +0.054 |
Neg logit contributions | |
Chick | -0.077 |
burn | -0.069 |
lull | -0.068 |
Bunny | -0.064 |
pt | -0.059 |
Token | stars |
Token ID | 5788 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
2 | +0.090 |
dice | +0.089 |
equation | +0.084 |
2 | +0.084 |
seven | +0.082 |
Neg logit contributions | |
burn | -0.053 |
Chick | -0.051 |
Bunny | -0.044 |
Betsy | -0.038 |
D | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
dice | +0.079 |
2 | +0.079 |
2 | +0.074 |
seven | +0.070 |
equation | +0.069 |
Neg logit contributions | |
Chick | -0.113 |
burn | -0.109 |
Bunny | -0.095 |
pt | -0.092 |
seed | -0.090 |
Token | They |
Token ID | 1119 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
2 | +0.029 |
dice | +0.028 |
2 | +0.027 |
equation | +0.027 |
seven | +0.026 |
Neg logit contributions | |
Chick | -0.034 |
burn | -0.032 |
Bunny | -0.030 |
D | -0.028 |
Sleep | -0.027 |
Token | would |
Token ID | 561 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
Chick | +0.014 |
burn | +0.013 |
Bunny | +0.012 |
pt | +0.011 |
unic | +0.011 |
Neg logit contributions | |
2 | -0.015 |
dice | -0.015 |
equation | -0.014 |
2 | -0.014 |
3 | -0.013 |
Token | count |
Token ID | 954 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
Chick | +0.170 |
burn | +0.163 |
Bunny | +0.144 |
unic | +0.136 |
pt | +0.135 |
Neg logit contributions | |
2 | -0.141 |
dice | -0.137 |
equation | -0.131 |
2 | -0.128 |
3 | -0.120 |
Token | 1 |
Token ID | 352 |
Feature activation | -9.13e+00 |
Pos logit contributions | |
dice | +0.249 |
2 | +0.247 |
2 | +0.233 |
seven | +0.221 |
1 | +0.218 |
Neg logit contributions | |
Chick | -0.350 |
burn | -0.339 |
Bunny | -0.293 |
pt | -0.287 |
seed | -0.282 |
Token | , |
Token ID | 11 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
equation | +0.511 |
dice | +0.508 |
2 | +0.480 |
adamant | +0.469 |
bench | +0.461 |
Neg logit contributions | |
Chick | -0.584 |
burn | -0.567 |
Bunny | -0.501 |
light | -0.471 |
seed | -0.467 |
Token | 2 |
Token ID | 362 |
Feature activation | -7.77e+00 |
Pos logit contributions | |
dice | +0.007 |
bench | +0.007 |
equation | +0.007 |
agree | +0.006 |
ars | +0.006 |
Neg logit contributions | |
Chick | -0.013 |
Bunny | -0.012 |
burn | -0.011 |
Pig | -0.011 |
M | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
dice | +0.423 |
equation | +0.410 |
2 | +0.407 |
2 | +0.384 |
seven | +0.382 |
Neg logit contributions | |
Chick | -0.547 |
burn | -0.508 |
Bunny | -0.466 |
pt | -0.438 |
unic | -0.435 |
Token | 3 |
Token ID | 513 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
dice | +0.008 |
bench | +0.007 |
equation | +0.007 |
ars | +0.007 |
agree | +0.007 |
Neg logit contributions | |
Chick | -0.016 |
Bunny | -0.014 |
burn | -0.014 |
M | -0.014 |
Pig | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
dice | +0.125 |
2 | +0.121 |
equation | +0.116 |
2 | +0.115 |
seven | +0.111 |
Neg logit contributions | |
Chick | -0.144 |
burn | -0.132 |
Bunny | -0.119 |
pt | -0.114 |
lull | -0.113 |
Token | the |
Token ID | 262 |
Feature activation | -7.84e-02 |
Pos logit contributions | |
dice | +0.008 |
2 | +0.008 |
2 | +0.007 |
seven | +0.007 |
equation | +0.007 |
Neg logit contributions | |
Chick | -0.012 |
burn | -0.012 |
Bunny | -0.010 |
lor | -0.010 |
pt | -0.010 |
Token | birds |
Token ID | 10087 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
2 | +0.005 |
dice | +0.004 |
2 | +0.004 |
3 | +0.004 |
equation | +0.004 |
Neg logit contributions | |
Chick | -0.005 |
burn | -0.005 |
Bunny | -0.005 |
seed | -0.005 |
pt | -0.005 |
Token | - |
Token ID | 532 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Chick | +0.040 |
burn | +0.039 |
Bunny | +0.033 |
lor | +0.032 |
pt | +0.032 |
Neg logit contributions | |
2 | -0.021 |
dice | -0.021 |
2 | -0.020 |
seven | -0.019 |
1 | -0.019 |
Token | 1 |
Token ID | 352 |
Feature activation | -9.52e+00 |
Pos logit contributions | |
2 | +0.081 |
dice | +0.081 |
2 | +0.078 |
seven | +0.075 |
1 | +0.073 |
Neg logit contributions | |
Chick | -0.107 |
burn | -0.104 |
pt | -0.090 |
Bunny | -0.087 |
lor | -0.087 |
Token | , |
Token ID | 11 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
dice | +0.559 |
2 | +0.537 |
equation | +0.515 |
2 | +0.495 |
3 | +0.479 |
Neg logit contributions | |
Chick | -0.652 |
burn | -0.633 |
Bunny | -0.567 |
seed | -0.553 |
pt | -0.542 |
Token | 2 |
Token ID | 17 |
Feature activation | -9.12e+00 |
Pos logit contributions | |
dice | +0.010 |
2 | +0.010 |
equation | +0.009 |
five | +0.009 |
2 | +0.009 |
Neg logit contributions | |
Chick | -0.014 |
burn | -0.013 |
Bunny | -0.012 |
D | -0.011 |
Pig | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
dice | +0.535 |
2 | +0.511 |
equation | +0.493 |
2 | +0.480 |
3 | +0.466 |
Neg logit contributions | |
Chick | -0.634 |
burn | -0.609 |
Bunny | -0.528 |
pt | -0.520 |
seed | -0.510 |
Token | 3 |
Token ID | 18 |
Feature activation | -7.39e+00 |
Pos logit contributions | |
dice | +0.015 |
2 | +0.014 |
equation | +0.013 |
2 | +0.013 |
3 | +0.012 |
Neg logit contributions | |
Chick | -0.020 |
burn | -0.019 |
Bunny | -0.018 |
D | -0.016 |
Pig | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
dice | +0.423 |
2 | +0.408 |
equation | +0.390 |
2 | +0.381 |
3 | +0.369 |
Neg logit contributions | |
Chick | -0.521 |
burn | -0.494 |
Bunny | -0.434 |
pt | -0.431 |
D | -0.416 |
Token | 4 |
Token ID | 19 |
Feature activation | -6.38e+00 |
Pos logit contributions | |
dice | +0.020 |
equation | +0.019 |
2 | +0.018 |
bench | +0.017 |
Kyle | +0.017 |
Neg logit contributions | |
Chick | -0.033 |
burn | -0.030 |
Bunny | -0.028 |
D | -0.026 |
Pig | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
dice | +0.366 |
2 | +0.351 |
equation | +0.337 |
2 | +0.326 |
3 | +0.316 |
Neg logit contributions | |
Chick | -0.450 |
burn | -0.429 |
Bunny | -0.374 |
pt | -0.367 |
seed | -0.358 |
Token | around |
Token ID | 1088 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
2 | +0.072 |
dice | +0.069 |
equation | +0.066 |
2 | +0.065 |
3 | +0.063 |
Neg logit contributions | |
Chick | -0.069 |
burn | -0.068 |
Bunny | -0.060 |
pt | -0.058 |
D | -0.055 |
Token | the |
Token ID | 262 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
2 | +0.040 |
dice | +0.040 |
2 | +0.037 |
equation | +0.036 |
3 | +0.036 |
Neg logit contributions | |
Chick | -0.048 |
burn | -0.043 |
Bunny | -0.041 |
D | -0.038 |
pt | -0.038 |
Token | house |
Token ID | 2156 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
dice | +0.054 |
2 | +0.052 |
2 | +0.049 |
seven | +0.047 |
equation | +0.046 |
Neg logit contributions | |
burn | -0.077 |
Chick | -0.075 |
Bunny | -0.070 |
Betsy | -0.067 |
Sleep | -0.064 |
Token | , |
Token ID | 11 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
dice | +0.060 |
2 | +0.060 |
2 | +0.056 |
equation | +0.054 |
3 | +0.054 |
Neg logit contributions | |
Chick | -0.071 |
burn | -0.069 |
Bunny | -0.060 |
pt | -0.058 |
lull | -0.056 |
Token | counting |
Token ID | 14143 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
dice | +0.015 |
2 | +0.015 |
2 | +0.014 |
equation | +0.014 |
3 | +0.013 |
Neg logit contributions | |
Chick | -0.018 |
burn | -0.018 |
Bunny | -0.016 |
D | -0.015 |
pt | -0.014 |
Token | 1 |
Token ID | 352 |
Feature activation | -9.12e+00 |
Pos logit contributions | |
2 | +0.211 |
dice | +0.210 |
2 | +0.195 |
equation | +0.191 |
seven | +0.186 |
Neg logit contributions | |
Chick | -0.284 |
burn | -0.271 |
Bunny | -0.241 |
pt | -0.234 |
seed | -0.224 |
Token | , |
Token ID | 11 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
dice | +0.503 |
equation | +0.482 |
2 | +0.480 |
2 | +0.455 |
3 | +0.443 |
Neg logit contributions | |
burn | -0.588 |
Chick | -0.585 |
Bunny | -0.509 |
light | -0.487 |
seed | -0.482 |
Token | 2 |
Token ID | 362 |
Feature activation | -7.76e+00 |
Pos logit contributions | |
dice | +0.010 |
bench | +0.010 |
equation | +0.009 |
agree | +0.009 |
ars | +0.009 |
Neg logit contributions | |
Chick | -0.023 |
Bunny | -0.021 |
burn | -0.021 |
M | -0.020 |
Pig | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
dice | +0.413 |
2 | +0.400 |
equation | +0.390 |
2 | +0.379 |
seven | +0.375 |
Neg logit contributions | |
Chick | -0.557 |
burn | -0.529 |
Bunny | -0.479 |
pt | -0.460 |
unic | -0.444 |
Token | 3 |
Token ID | 513 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
dice | +0.011 |
bench | +0.010 |
equation | +0.010 |
agree | +0.009 |
ars | +0.009 |
Neg logit contributions | |
Chick | -0.024 |
burn | -0.022 |
Bunny | -0.021 |
M | -0.021 |
Pig | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
dice | +0.127 |
2 | +0.124 |
2 | +0.117 |
equation | +0.116 |
seven | +0.113 |
Neg logit contributions | |
Chick | -0.145 |
burn | -0.135 |
Bunny | -0.121 |
pt | -0.118 |
lull | -0.115 |
Token | counted |
Token ID | 14789 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
2 | +0.023 |
dice | +0.023 |
2 | +0.023 |
seven | +0.022 |
3 | +0.020 |
Neg logit contributions | |
burn | -0.049 |
Chick | -0.049 |
pt | -0.043 |
lor | -0.042 |
Bunny | -0.042 |
Token | her |
Token ID | 607 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
2 | +0.180 |
dice | +0.176 |
2 | +0.174 |
1 | +0.165 |
seven | +0.164 |
Neg logit contributions | |
Chick | -0.259 |
burn | -0.256 |
pt | -0.219 |
Bunny | -0.217 |
seed | -0.213 |
Token | lucky |
Token ID | 9670 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Chick | +0.055 |
burn | +0.052 |
Bunny | +0.046 |
pt | +0.043 |
seed | +0.043 |
Neg logit contributions | |
2 | -0.052 |
dice | -0.052 |
2 | -0.049 |
equation | -0.047 |
3 | -0.047 |
Token | stars |
Token ID | 5788 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Chick | +0.071 |
burn | +0.068 |
Bunny | +0.058 |
pt | +0.057 |
seed | +0.055 |
Neg logit contributions | |
dice | -0.061 |
2 | -0.061 |
2 | -0.058 |
seven | -0.055 |
equation | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
2 | +0.074 |
dice | +0.074 |
2 | +0.070 |
seven | +0.067 |
1 | +0.066 |
Neg logit contributions | |
Chick | -0.123 |
burn | -0.120 |
Bunny | -0.104 |
pt | -0.101 |
lor | -0.099 |
Token | 1 |
Token ID | 352 |
Feature activation | -9.11e+00 |
Pos logit contributions | |
dice | +0.038 |
2 | +0.037 |
2 | +0.035 |
equation | +0.034 |
seven | +0.034 |
Neg logit contributions | |
Chick | -0.051 |
burn | -0.048 |
Bunny | -0.043 |
pt | -0.041 |
seed | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | -8.96e-02 |
Pos logit contributions | |
dice | +0.508 |
2 | +0.491 |
equation | +0.465 |
2 | +0.449 |
3 | +0.432 |
Neg logit contributions | |
Chick | -0.678 |
burn | -0.641 |
Bunny | -0.570 |
pt | -0.547 |
seed | -0.546 |
Token | 2 |
Token ID | 362 |
Feature activation | -7.72e+00 |
Pos logit contributions | |
dice | +0.004 |
equation | +0.003 |
five | +0.003 |
ars | +0.003 |
scoreboard | +0.003 |
Neg logit contributions | |
Chick | -0.008 |
Bunny | -0.007 |
burn | -0.007 |
M | -0.007 |
Pig | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
dice | +0.441 |
2 | +0.429 |
equation | +0.404 |
2 | +0.394 |
3 | +0.383 |
Neg logit contributions | |
Chick | -0.558 |
burn | -0.514 |
Bunny | -0.460 |
pt | -0.450 |
seed | -0.443 |
Token | 3 |
Token ID | 513 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
dice | +0.005 |
equation | +0.004 |
five | +0.004 |
ars | +0.004 |
scoreboard | +0.004 |
Neg logit contributions | |
Chick | -0.010 |
burn | -0.009 |
Bunny | -0.009 |
M | -0.009 |
Pig | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
dice | +0.125 |
2 | +0.122 |
2 | +0.113 |
equation | +0.113 |
3 | +0.109 |
Neg logit contributions | |
Chick | -0.147 |
burn | -0.135 |
Bunny | -0.121 |
pt | -0.119 |
seed | -0.117 |
Token | very |
Token ID | 845 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
dice | +0.205 |
2 | +0.197 |
equation | +0.195 |
five | +0.180 |
scoreboard | +0.179 |
Neg logit contributions | |
Chick | -0.231 |
burn | -0.213 |
Bunny | -0.190 |
M | -0.181 |
pt | -0.178 |
Token | slowly |
Token ID | 6364 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
dice | +0.071 |
bench | +0.068 |
booth | +0.068 |
equation | +0.064 |
scoreboard | +0.064 |
Neg logit contributions | |
Chick | -0.090 |
M | -0.080 |
Madd | -0.076 |
apy | -0.073 |
Bunny | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
dice | +0.062 |
2 | +0.060 |
Kyle | +0.057 |
equation | +0.055 |
scoreboard | +0.054 |
Neg logit contributions | |
Chick | -0.052 |
burn | -0.049 |
streaming | -0.042 |
pt | -0.042 |
light | -0.042 |
Token | He |
Token ID | 679 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
dice | +0.020 |
2 | +0.019 |
equation | +0.018 |
seven | +0.017 |
agree | +0.017 |
Neg logit contributions | |
Chick | -0.023 |
burn | -0.019 |
Bunny | -0.019 |
D | -0.018 |
M | -0.018 |
Token | counted |
Token ID | 14789 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
dice | +0.074 |
2 | +0.072 |
bench | +0.069 |
equation | +0.068 |
booth | +0.067 |
Neg logit contributions | |
Chick | -0.085 |
burn | -0.070 |
M | -0.069 |
Bunny | -0.068 |
unic | -0.066 |
Token | 1 |
Token ID | 352 |
Feature activation | -9.09e+00 |
Pos logit contributions | |
dice | +0.208 |
equation | +0.202 |
2 | +0.198 |
five | +0.186 |
scoreboard | +0.185 |
Neg logit contributions | |
Chick | -0.229 |
burn | -0.210 |
Bunny | -0.188 |
M | -0.182 |
Madd | -0.174 |
Token | , |
Token ID | 11 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
dice | +0.524 |
bench | +0.515 |
equation | +0.509 |
adamant | +0.504 |
Kyle | +0.490 |
Neg logit contributions | |
Chick | -0.497 |
burn | -0.449 |
light | -0.433 |
M | -0.419 |
ie | -0.417 |
Token | 2 |
Token ID | 17 |
Feature activation | -8.60e+00 |
Pos logit contributions | |
bench | +0.004 |
dice | +0.004 |
agree | +0.004 |
equation | +0.004 |
scoreboard | +0.004 |
Neg logit contributions | |
Chick | -0.011 |
M | -0.010 |
Bunny | -0.009 |
Pig | -0.009 |
B | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
dice | +0.538 |
equation | +0.513 |
scoreboard | +0.491 |
2 | +0.490 |
Kyle | +0.487 |
Neg logit contributions | |
Chick | -0.500 |
burn | -0.445 |
Bunny | -0.386 |
ie | -0.382 |
M | -0.382 |
Token | 3 |
Token ID | 18 |
Feature activation | -6.93e+00 |
Pos logit contributions | |
bench | +0.006 |
dice | +0.005 |
equation | +0.005 |
adamant | +0.005 |
scoreboard | +0.005 |
Neg logit contributions | |
Chick | -0.012 |
M | -0.010 |
Bunny | -0.010 |
B | -0.010 |
Pig | -0.010 |
Token | ... |
Token ID | 986 |
Feature activation | -4.67e+00 |
Pos logit contributions | |
dice | +0.432 |
equation | +0.418 |
2 | +0.395 |
booth | +0.395 |
scoreboard | +0.395 |
Neg logit contributions | |
Chick | -0.401 |
burn | -0.354 |
D | -0.314 |
pt | -0.310 |
M | -0.309 |
Token | furry |
Token ID | 40857 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Chick | +0.106 |
burn | +0.102 |
Bunny | +0.089 |
pt | +0.086 |
seed | +0.083 |
Neg logit contributions | |
2 | -0.090 |
dice | -0.089 |
2 | -0.084 |
equation | -0.081 |
seven | -0.080 |
Token | legs |
Token ID | 7405 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
Chick | +0.143 |
burn | +0.135 |
Bunny | +0.112 |
pt | +0.111 |
lor | +0.111 |
Neg logit contributions | |
dice | -0.123 |
2 | -0.120 |
2 | -0.115 |
seven | -0.112 |
equation | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
Chick | +0.049 |
burn | +0.048 |
Bunny | +0.041 |
pt | +0.041 |
seed | +0.039 |
Neg logit contributions | |
dice | -0.038 |
2 | -0.038 |
2 | -0.035 |
equation | -0.034 |
seven | -0.034 |
Token | He |
Token ID | 679 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
dice | +0.001 |
2 | +0.001 |
equation | +0.001 |
2 | +0.001 |
seven | +0.001 |
Neg logit contributions | |
Chick | -0.001 |
Bunny | -0.001 |
burn | -0.001 |
D | -0.001 |
Mitt | -0.001 |
Token | counted |
Token ID | 14789 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
dice | +0.064 |
2 | +0.064 |
equation | +0.060 |
2 | +0.059 |
3 | +0.056 |
Neg logit contributions | |
Chick | -0.077 |
burn | -0.069 |
Bunny | -0.064 |
pt | -0.061 |
D | -0.059 |
Token | 1 |
Token ID | 352 |
Feature activation | -9.04e+00 |
Pos logit contributions | |
dice | +0.210 |
2 | +0.208 |
equation | +0.198 |
2 | +0.192 |
seven | +0.186 |
Neg logit contributions | |
Chick | -0.224 |
burn | -0.213 |
Bunny | -0.187 |
pt | -0.176 |
seed | -0.170 |
Token | , |
Token ID | 11 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
equation | +0.574 |
dice | +0.569 |
bench | +0.558 |
scoreboard | +0.525 |
agree | +0.524 |
Neg logit contributions | |
Chick | -0.455 |
burn | -0.421 |
Bunny | -0.390 |
ie | -0.383 |
seed | -0.379 |
Token | 2 |
Token ID | 362 |
Feature activation | -7.66e+00 |
Pos logit contributions | |
Chick | +0.006 |
Bunny | +0.005 |
burn | +0.005 |
Pig | +0.005 |
D | +0.005 |
Neg logit contributions | |
dice | -0.003 |
bench | -0.002 |
equation | -0.002 |
agree | -0.002 |
ars | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
dice | +0.479 |
equation | +0.470 |
2 | +0.443 |
bench | +0.435 |
five | +0.430 |
Neg logit contributions | |
Chick | -0.475 |
burn | -0.417 |
Bunny | -0.402 |
pt | -0.371 |
seed | -0.368 |
Token | 3 |
Token ID | 513 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
Chick | +0.001 |
Bunny | +0.001 |
burn | +0.001 |
Pig | +0.001 |
M | +0.001 |
Neg logit contributions | |
dice | -0.001 |
bench | -0.001 |
equation | -0.000 |
agree | -0.000 |
ars | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
dice | +0.124 |
2 | +0.120 |
equation | +0.116 |
2 | +0.114 |
3 | +0.109 |
Neg logit contributions | |
Chick | -0.122 |
burn | -0.106 |
Bunny | -0.099 |
seed | -0.097 |
pt | -0.095 |
Token | . |
Token ID | 13 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
2 | +0.311 |
dice | +0.308 |
2 | +0.287 |
3 | +0.284 |
seven | +0.284 |
Neg logit contributions | |
Chick | -0.293 |
burn | -0.269 |
Bunny | -0.249 |
pt | -0.248 |
D | -0.235 |
Token | |
Token ID | 220 |
Feature activation | -9.65e-02 |
Pos logit contributions | |
dice | +0.026 |
2 | +0.025 |
2 | +0.023 |
equation | +0.023 |
seven | +0.023 |
Neg logit contributions | |
Chick | -0.032 |
burn | -0.030 |
Bunny | -0.028 |
D | -0.026 |
pt | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
dice | +0.005 |
2 | +0.005 |
2 | +0.005 |
equation | +0.005 |
seven | +0.005 |
Neg logit contributions | |
Chick | -0.007 |
burn | -0.007 |
Bunny | -0.006 |
pt | -0.006 |
D | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
dice | +0.002 |
2 | +0.002 |
equation | +0.002 |
2 | +0.002 |
seven | +0.002 |
Neg logit contributions | |
Chick | -0.003 |
burn | -0.002 |
Bunny | -0.002 |
D | -0.002 |
Madd | -0.002 |
Token | Friend |
Token ID | 23331 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
dice | +0.001 |
2 | +0.001 |
equation | +0.001 |
2 | +0.001 |
1 | +0.001 |
Neg logit contributions | |
Chick | -0.002 |
burn | -0.002 |
Bunny | -0.001 |
D | -0.001 |
lull | -0.001 |
Token | 1 |
Token ID | 352 |
Feature activation | -9.01e+00 |
Pos logit contributions | |
dice | +0.092 |
equation | +0.086 |
bench | +0.082 |
2 | +0.075 |
sign | +0.073 |
Neg logit contributions | |
Chick | -0.163 |
pt | -0.159 |
D | -0.150 |
Bunny | -0.149 |
burn | -0.146 |
Token | : |
Token ID | 25 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
dice | +0.527 |
equation | +0.497 |
2 | +0.475 |
scoreboard | +0.448 |
bench | +0.430 |
Neg logit contributions | |
Chick | -0.567 |
burn | -0.558 |
pt | -0.514 |
Bunny | -0.511 |
D | -0.490 |
Token | � |
Token ID | 6184 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
dice | +0.191 |
2 | +0.176 |
equation | +0.173 |
ars | +0.163 |
2 | +0.160 |
Neg logit contributions | |
Chick | -0.218 |
burn | -0.207 |
Bunny | -0.190 |
D | -0.184 |
Sleep | -0.178 |
Token | � |
Token ID | 95 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
dice | +0.024 |
2 | +0.021 |
equation | +0.021 |
bench | +0.021 |
2 | +0.021 |
Neg logit contributions | |
Chick | -0.030 |
burn | -0.027 |
Bunny | -0.025 |
D | -0.025 |
Sleep | -0.025 |
Token | € |
Token ID | 26391 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
dice | +0.066 |
2 | +0.057 |
man | +0.057 |
2 | +0.057 |
weights | +0.054 |
Neg logit contributions | |
Chick | -0.066 |
lor | -0.065 |
burn | -0.063 |
Sleep | -0.062 |
Bunny | -0.055 |
Token | � |
Token ID | 129 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
dice | +0.099 |
2 | +0.096 |
2 | +0.093 |
equation | +0.091 |
seven | +0.089 |
Neg logit contributions | |
Chick | -0.093 |
burn | -0.089 |
Bunny | -0.075 |
seed | -0.071 |
lor | -0.070 |
Token | it |
Token ID | 340 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
burn | +0.017 |
Chick | +0.016 |
lor | +0.015 |
pt | +0.014 |
seed | +0.014 |
Neg logit contributions | |
2 | -0.011 |
dice | -0.010 |
2 | -0.010 |
1 | -0.009 |
3 | -0.009 |
Token | ." |
Token ID | 526 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
burn | +0.050 |
Chick | +0.049 |
streaming | +0.044 |
lor | +0.043 |
Dod | +0.042 |
Neg logit contributions | |
dice | -0.032 |
2 | -0.031 |
agree | -0.030 |
2 | -0.030 |
sign | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
burn | +0.152 |
Chick | +0.149 |
pt | +0.129 |
Bunny | +0.125 |
lull | +0.125 |
Neg logit contributions | |
2 | -0.090 |
dice | -0.087 |
2 | -0.083 |
1 | -0.077 |
seven | -0.077 |
Token |
|
Token ID | 198 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
Chick | +0.018 |
burn | +0.018 |
Bunny | +0.016 |
pt | +0.015 |
seed | +0.015 |
Neg logit contributions | |
2 | -0.010 |
dice | -0.010 |
2 | -0.010 |
seven | -0.009 |
equation | -0.009 |
Token | Friend |
Token ID | 23331 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
Chick | +0.012 |
burn | +0.011 |
Bunny | +0.009 |
lull | +0.009 |
pt | +0.008 |
Neg logit contributions | |
dice | -0.017 |
2 | -0.017 |
2 | -0.016 |
equation | -0.016 |
1 | -0.016 |
Token | 1 |
Token ID | 352 |
Feature activation | -8.98e+00 |
Pos logit contributions | |
dice | +0.103 |
adamant | +0.098 |
bench | +0.097 |
equation | +0.094 |
trailer | +0.091 |
Neg logit contributions | |
pt | -0.135 |
Chick | -0.134 |
Bunny | -0.119 |
maid | -0.116 |
ie | -0.115 |
Token | : |
Token ID | 25 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
dice | +0.593 |
equation | +0.557 |
scoreboard | +0.527 |
2 | +0.510 |
Ready | +0.496 |
Neg logit contributions | |
Chick | -0.483 |
burn | -0.477 |
pt | -0.466 |
ie | -0.446 |
Bunny | -0.435 |
Token | " |
Token ID | 366 |
Feature activation | -9.74e-01 |
Pos logit contributions | |
dice | +0.201 |
equation | +0.182 |
2 | +0.181 |
scoreboard | +0.173 |
ars | +0.172 |
Neg logit contributions | |
Chick | -0.209 |
burn | -0.194 |
Bunny | -0.178 |
D | -0.165 |
Pig | -0.161 |
Token | I |
Token ID | 40 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
dice | +0.061 |
equation | +0.057 |
2 | +0.057 |
2 | +0.056 |
seven | +0.055 |
Neg logit contributions | |
Chick | -0.066 |
burn | -0.062 |
Bunny | -0.053 |
seed | -0.051 |
D | -0.051 |
Token | don |
Token ID | 836 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
Chick | +0.098 |
burn | +0.097 |
Bunny | +0.081 |
lor | +0.080 |
streaming | +0.079 |
Neg logit contributions | |
2 | -0.067 |
dice | -0.067 |
2 | -0.065 |
seven | -0.060 |
equation | -0.060 |
Token | 't |
Token ID | 470 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
dice | +0.113 |
2 | +0.111 |
2 | +0.106 |
seven | +0.102 |
equation | +0.102 |
Neg logit contributions | |
Chick | -0.114 |
burn | -0.109 |
Bunny | -0.093 |
pt | -0.089 |
seed | -0.086 |
Token | the |
Token ID | 262 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
2 | +0.373 |
dice | +0.370 |
equation | +0.353 |
2 | +0.350 |
seven | +0.341 |
Neg logit contributions | |
Chick | -0.327 |
burn | -0.306 |
Bunny | -0.263 |
pt | -0.257 |
D | -0.241 |
Token | cars |
Token ID | 5006 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
2 | +0.051 |
3 | +0.047 |
4 | +0.047 |
2 | +0.046 |
five | +0.045 |
Neg logit contributions | |
Chick | -0.046 |
burn | -0.045 |
pt | -0.040 |
Bunny | -0.039 |
unic | -0.038 |
Token | in |
Token ID | 287 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
2 | +0.231 |
dice | +0.223 |
equation | +0.220 |
2 | +0.218 |
seven | +0.215 |
Neg logit contributions | |
burn | -0.201 |
Chick | -0.200 |
pt | -0.174 |
Bunny | -0.164 |
D | -0.153 |
Token | order |
Token ID | 1502 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
2 | +0.095 |
dice | +0.094 |
2 | +0.088 |
equation | +0.087 |
seven | +0.085 |
Neg logit contributions | |
Chick | -0.129 |
burn | -0.123 |
Bunny | -0.109 |
pt | -0.106 |
D | -0.102 |
Token | from |
Token ID | 422 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
2 | +0.159 |
dice | +0.155 |
equation | +0.147 |
2 | +0.147 |
seven | +0.143 |
Neg logit contributions | |
Chick | -0.172 |
burn | -0.164 |
Bunny | -0.145 |
pt | -0.144 |
D | -0.135 |
Token | 1 |
Token ID | 352 |
Feature activation | -8.97e+00 |
Pos logit contributions | |
Chick | +0.017 |
burn | +0.016 |
Bunny | +0.014 |
pt | +0.014 |
seed | +0.013 |
Neg logit contributions | |
2 | -0.014 |
dice | -0.014 |
2 | -0.013 |
equation | -0.013 |
seven | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
equation | +0.488 |
dice | +0.487 |
2 | +0.486 |
2 | +0.468 |
adamant | +0.453 |
Neg logit contributions | |
burn | -0.548 |
Chick | -0.524 |
light | -0.453 |
Bunny | -0.446 |
pt | -0.444 |
Token | 10 |
Token ID | 838 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
Chick | +0.017 |
burn | +0.016 |
Bunny | +0.015 |
pt | +0.015 |
D | +0.014 |
Neg logit contributions | |
2 | -0.010 |
dice | -0.010 |
equation | -0.010 |
2 | -0.009 |
seven | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
2 | +0.297 |
resa | +0.291 |
dice | +0.288 |
equation | +0.286 |
five | +0.283 |
Neg logit contributions | |
Chick | -0.306 |
burn | -0.274 |
pt | -0.257 |
Bunny | -0.242 |
unic | -0.236 |
Token | Tim |
Token ID | 5045 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
Chick | +0.015 |
burn | +0.012 |
Bunny | +0.012 |
Betsy | +0.011 |
D | +0.011 |
Neg logit contributions | |
dice | -0.026 |
2 | -0.026 |
seven | -0.025 |
2 | -0.025 |
equation | -0.025 |
Token | my |
Token ID | 1820 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
dice | +0.015 |
2 | +0.014 |
2 | +0.013 |
seven | +0.013 |
equation | +0.013 |
Neg logit contributions | |
burn | -0.013 |
Chick | -0.013 |
Bunny | -0.011 |
pt | -0.011 |
seed | -0.010 |
Token | characters |
Token ID | 3435 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
2 | +0.037 |
dice | +0.034 |
2 | +0.034 |
3 | +0.033 |
equation | +0.033 |
Neg logit contributions | |
Chick | -0.045 |
burn | -0.044 |
Bunny | -0.038 |
lull | -0.038 |
seed | -0.037 |
Token | on |
Token ID | 319 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
2 | +0.049 |
dice | +0.048 |
2 | +0.046 |
equation | +0.044 |
3 | +0.044 |
Neg logit contributions | |
Chick | -0.053 |
burn | -0.052 |
pt | -0.044 |
Bunny | -0.044 |
lull | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
Chick | +0.081 |
burn | +0.076 |
Bunny | +0.067 |
pt | +0.063 |
D | +0.062 |
Neg logit contributions | |
2 | -0.065 |
dice | -0.064 |
2 | -0.060 |
equation | -0.059 |
seven | -0.057 |
Token | screen |
Token ID | 3159 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
2 | +0.037 |
2 | +0.034 |
dice | +0.033 |
3 | +0.033 |
1 | +0.032 |
Neg logit contributions | |
Chick | -0.046 |
burn | -0.044 |
lull | -0.040 |
Bunny | -0.038 |
unic | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
2 | +0.108 |
dice | +0.106 |
2 | +0.101 |
3 | +0.097 |
equation | +0.096 |
Neg logit contributions | |
Chick | -0.119 |
burn | -0.115 |
Bunny | -0.098 |
pt | -0.096 |
lull | -0.094 |
Token | 1 |
Token ID | 352 |
Feature activation | -8.96e+00 |
Pos logit contributions | |
dice | +0.019 |
2 | +0.018 |
equation | +0.017 |
2 | +0.017 |
seven | +0.017 |
Neg logit contributions | |
Chick | -0.022 |
burn | -0.019 |
Bunny | -0.018 |
Madd | -0.017 |
D | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
dice | +0.530 |
2 | +0.503 |
equation | +0.499 |
2 | +0.464 |
seven | +0.456 |
Neg logit contributions | |
Chick | -0.606 |
burn | -0.573 |
Bunny | -0.513 |
pt | -0.493 |
seed | -0.479 |
Token | 2 |
Token ID | 362 |
Feature activation | -7.59e+00 |
Pos logit contributions | |
Chick | +0.008 |
Bunny | +0.007 |
M | +0.007 |
burn | +0.007 |
Pig | +0.007 |
Neg logit contributions | |
dice | -0.005 |
five | -0.004 |
equation | -0.004 |
bench | -0.004 |
ars | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
dice | +0.439 |
2 | +0.424 |
equation | +0.413 |
2 | +0.392 |
3 | +0.386 |
Neg logit contributions | |
Chick | -0.522 |
burn | -0.473 |
Bunny | -0.430 |
pt | -0.420 |
seed | -0.407 |
Token | 3 |
Token ID | 513 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
Chick | +0.005 |
Bunny | +0.004 |
burn | +0.004 |
M | +0.004 |
Pig | +0.004 |
Neg logit contributions | |
dice | -0.002 |
equation | -0.002 |
bench | -0.002 |
five | -0.002 |
ars | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
dice | +0.120 |
2 | +0.117 |
equation | +0.111 |
2 | +0.110 |
3 | +0.106 |
Neg logit contributions | |
Chick | -0.128 |
burn | -0.112 |
Bunny | -0.103 |
pt | -0.101 |
seed | -0.099 |
Token | went |
Token ID | 1816 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
dice | +0.015 |
2 | +0.015 |
2 | +0.014 |
equation | +0.014 |
Kyle | +0.014 |
Neg logit contributions | |
Chick | -0.017 |
burn | -0.015 |
pt | -0.014 |
light | -0.014 |
seed | -0.014 |
Token | first |
Token ID | 717 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
burn | +0.024 |
Bunny | +0.022 |
Chick | +0.022 |
M | +0.020 |
asleep | +0.017 |
Neg logit contributions | |
2 | -0.064 |
agree | -0.062 |
ars | -0.061 |
dice | -0.061 |
4 | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +9.13e-02 |
Pos logit contributions | |
dice | +0.350 |
2 | +0.350 |
3 | +0.329 |
4 | +0.325 |
2 | +0.324 |
Neg logit contributions | |
Chick | -0.160 |
M | -0.148 |
burn | -0.146 |
Bunny | -0.135 |
light | -0.131 |
Token | He |
Token ID | 679 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Chick | +0.006 |
Bunny | +0.005 |
burn | +0.004 |
M | +0.004 |
D | +0.004 |
Neg logit contributions | |
dice | -0.006 |
equation | -0.006 |
2 | -0.006 |
ars | -0.005 |
seven | -0.005 |
Token | counted |
Token ID | 14789 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
dice | +0.056 |
2 | +0.055 |
scoreboard | +0.051 |
equation | +0.050 |
booth | +0.050 |
Neg logit contributions | |
Chick | -0.069 |
Bunny | -0.058 |
M | -0.055 |
burn | -0.055 |
pt | -0.055 |
Token | 1 |
Token ID | 352 |
Feature activation | -8.85e+00 |
Pos logit contributions | |
dice | +0.203 |
equation | +0.196 |
2 | +0.193 |
scoreboard | +0.184 |
five | +0.183 |
Neg logit contributions | |
Chick | -0.208 |
burn | -0.187 |
Bunny | -0.168 |
M | -0.160 |
pt | -0.156 |
Token | , |
Token ID | 11 |
Feature activation | +9.62e-02 |
Pos logit contributions | |
dice | +0.565 |
Kyle | +0.551 |
bench | +0.546 |
sidelines | +0.544 |
equation | +0.541 |
Neg logit contributions | |
Chick | -0.420 |
ie | -0.366 |
light | -0.365 |
burn | -0.360 |
M | -0.352 |
Token | 2 |
Token ID | 17 |
Feature activation | -8.41e+00 |
Pos logit contributions | |
Chick | +0.008 |
M | +0.007 |
Bunny | +0.007 |
Pig | +0.007 |
B | +0.006 |
Neg logit contributions | |
bench | -0.004 |
dice | -0.003 |
Kyle | -0.003 |
agree | -0.003 |
scoreboard | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +7.06e-02 |
Pos logit contributions | |
dice | +0.553 |
equation | +0.531 |
Kyle | +0.516 |
scoreboard | +0.516 |
adamant | +0.507 |
Neg logit contributions | |
Chick | -0.472 |
burn | -0.410 |
ie | -0.360 |
Bunny | -0.355 |
M | -0.348 |
Token | 3 |
Token ID | 18 |
Feature activation | -6.72e+00 |
Pos logit contributions | |
Chick | +0.005 |
M | +0.005 |
Bunny | +0.004 |
Pig | +0.004 |
B | +0.004 |
Neg logit contributions | |
bench | -0.003 |
dice | -0.003 |
Kyle | -0.003 |
scoreboard | -0.003 |
equation | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
dice | +0.428 |
equation | +0.412 |
2 | +0.395 |
scoreboard | +0.395 |
booth | +0.389 |
Neg logit contributions | |
Chick | -0.396 |
burn | -0.347 |
D | -0.304 |
pt | -0.303 |
Bunny | -0.302 |
Token | around |
Token ID | 1088 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
Chick | +0.099 |
burn | +0.091 |
Bunny | +0.086 |
pt | +0.080 |
streaming | +0.078 |
Neg logit contributions | |
2 | -0.073 |
dice | -0.073 |
equation | -0.067 |
five | -0.067 |
agree | -0.062 |
Token | it |
Token ID | 340 |
Feature activation | +9.37e-01 |
Pos logit contributions | |
dice | +0.029 |
2 | +0.029 |
2 | +0.027 |
equation | +0.026 |
seven | +0.026 |
Neg logit contributions | |
Chick | -0.035 |
burn | -0.033 |
Bunny | -0.030 |
pt | -0.029 |
seed | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
Chick | +0.064 |
burn | +0.060 |
Bunny | +0.054 |
pt | +0.052 |
seed | +0.051 |
Neg logit contributions | |
2 | -0.056 |
dice | -0.056 |
2 | -0.052 |
equation | -0.050 |
3 | -0.050 |
Token | He |
Token ID | 679 |
Feature activation | -9.70e-01 |
Pos logit contributions | |
dice | +0.007 |
2 | +0.006 |
equation | +0.006 |
seven | +0.006 |
2 | +0.006 |
Neg logit contributions | |
Chick | -0.009 |
Bunny | -0.007 |
burn | -0.007 |
D | -0.007 |
M | -0.007 |
Token | counted |
Token ID | 14789 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
2 | +0.053 |
dice | +0.053 |
equation | +0.050 |
booth | +0.048 |
2 | +0.047 |
Neg logit contributions | |
Chick | -0.067 |
burn | -0.056 |
Bunny | -0.055 |
pt | -0.053 |
M | -0.052 |
Token | 1 |
Token ID | 352 |
Feature activation | -8.80e+00 |
Pos logit contributions | |
dice | +0.197 |
equation | +0.194 |
2 | +0.189 |
five | +0.177 |
scoreboard | +0.176 |
Neg logit contributions | |
Chick | -0.199 |
burn | -0.183 |
Bunny | -0.164 |
pt | -0.152 |
M | -0.151 |
Token | , |
Token ID | 11 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
dice | +0.541 |
equation | +0.523 |
bench | +0.517 |
Kyle | +0.490 |
five | +0.490 |
Neg logit contributions | |
Chick | -0.495 |
burn | -0.433 |
Bunny | -0.426 |
seed | -0.414 |
ie | -0.413 |
Token | 2 |
Token ID | 362 |
Feature activation | -7.44e+00 |
Pos logit contributions | |
Chick | +0.010 |
Bunny | +0.009 |
M | +0.009 |
Pig | +0.009 |
B | +0.008 |
Neg logit contributions | |
bench | -0.004 |
dice | -0.004 |
ars | -0.004 |
equation | -0.004 |
five | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +7.52e-02 |
Pos logit contributions | |
dice | +0.457 |
equation | +0.433 |
five | +0.413 |
bench | +0.412 |
2 | +0.407 |
Neg logit contributions | |
Chick | -0.479 |
burn | -0.403 |
Bunny | -0.402 |
pt | -0.373 |
Madd | -0.369 |
Token | 3 |
Token ID | 513 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
Chick | +0.006 |
Bunny | +0.005 |
M | +0.005 |
Pig | +0.005 |
B | +0.005 |
Neg logit contributions | |
bench | -0.003 |
dice | -0.003 |
equation | -0.003 |
ars | -0.003 |
Kyle | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
dice | +0.110 |
2 | +0.103 |
equation | +0.100 |
2 | +0.097 |
3 | +0.093 |
Neg logit contributions | |
Chick | -0.120 |
burn | -0.104 |
Bunny | -0.100 |
seed | -0.095 |
pt | -0.094 |
Token | him |
Token ID | 683 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
Chick | +0.029 |
burn | +0.028 |
Bunny | +0.023 |
pt | +0.023 |
seed | +0.022 |
Neg logit contributions | |
dice | -0.028 |
2 | -0.028 |
2 | -0.027 |
seven | -0.026 |
equation | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
Chick | +0.037 |
burn | +0.037 |
Bunny | +0.031 |
pt | +0.030 |
seed | +0.030 |
Neg logit contributions | |
2 | -0.022 |
dice | -0.021 |
2 | -0.020 |
seven | -0.019 |
1 | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
Chick | +0.009 |
D | +0.008 |
Bunny | +0.007 |
M | +0.007 |
burn | +0.007 |
Neg logit contributions | |
dice | -0.010 |
equation | -0.009 |
2 | -0.009 |
seven | -0.008 |
ars | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
Chick | +0.025 |
Bunny | +0.020 |
burn | +0.020 |
D | +0.019 |
lor | +0.019 |
Neg logit contributions | |
dice | -0.029 |
2 | -0.027 |
equation | -0.027 |
seven | -0.026 |
2 | -0.026 |
Token | Mouse |
Token ID | 39643 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
Chick | +0.024 |
D | +0.021 |
burn | +0.020 |
lor | +0.020 |
Br | +0.020 |
Neg logit contributions | |
dice | -0.023 |
2 | -0.021 |
equation | -0.021 |
five | -0.021 |
2 | -0.020 |
Token | 1 |
Token ID | 352 |
Feature activation | -8.74e+00 |
Pos logit contributions | |
Chick | +0.036 |
burn | +0.033 |
Bunny | +0.031 |
pt | +0.030 |
seed | +0.029 |
Neg logit contributions | |
dice | -0.031 |
2 | -0.030 |
equation | -0.028 |
2 | -0.027 |
seven | -0.027 |
Token | : |
Token ID | 25 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
dice | +0.536 |
equation | +0.511 |
2 | +0.494 |
scoreboard | +0.458 |
3 | +0.449 |
Neg logit contributions | |
Chick | -0.553 |
burn | -0.523 |
Bunny | -0.504 |
pt | -0.486 |
seed | -0.479 |
Token | " |
Token ID | 366 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
dice | +0.177 |
equation | +0.160 |
2 | +0.160 |
ars | +0.155 |
agree | +0.152 |
Neg logit contributions | |
Chick | -0.203 |
burn | -0.187 |
Bunny | -0.182 |
D | -0.168 |
Pig | -0.164 |
Token | Hey |
Token ID | 10814 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
dice | +0.037 |
2 | +0.036 |
2 | +0.034 |
equation | +0.034 |
seven | +0.033 |
Neg logit contributions | |
Chick | -0.046 |
burn | -0.045 |
Bunny | -0.039 |
pt | -0.037 |
seed | -0.037 |
Token | little |
Token ID | 1310 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
dice | +0.038 |
2 | +0.037 |
2 | +0.035 |
equation | +0.034 |
seven | +0.033 |
Neg logit contributions | |
Chick | -0.049 |
burn | -0.047 |
Bunny | -0.041 |
pt | -0.039 |
seed | -0.039 |
Token | fish |
Token ID | 5916 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
Chick | +0.094 |
burn | +0.091 |
Bunny | +0.081 |
D | +0.076 |
seed | +0.074 |
Neg logit contributions | |
dice | -0.084 |
2 | -0.083 |
equation | -0.080 |
2 | -0.077 |
3 | -0.075 |
Token | names |
Token ID | 3891 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
Chick | +0.085 |
burn | +0.082 |
Bunny | +0.071 |
pt | +0.070 |
seed | +0.068 |
Neg logit contributions | |
dice | -0.055 |
2 | -0.055 |
2 | -0.051 |
seven | -0.049 |
equation | -0.049 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
2 | +0.061 |
dice | +0.060 |
equation | +0.056 |
2 | +0.056 |
3 | +0.055 |
Neg logit contributions | |
Chick | -0.043 |
burn | -0.042 |
Bunny | -0.035 |
pt | -0.034 |
Sleep | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
Chick | +0.092 |
Bunny | +0.078 |
burn | +0.074 |
D | +0.071 |
Pig | +0.070 |
Neg logit contributions | |
dice | -0.094 |
2 | -0.090 |
equation | -0.089 |
scoreboard | -0.084 |
seven | -0.083 |
Token |
|
Token ID | 198 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
Chick | +0.016 |
burn | +0.014 |
Bunny | +0.013 |
D | +0.012 |
Pig | +0.012 |
Neg logit contributions | |
dice | -0.015 |
2 | -0.014 |
equation | -0.014 |
2 | -0.013 |
seven | -0.013 |
Token | The |
Token ID | 464 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
Chick | +0.012 |
burn | +0.010 |
lull | +0.010 |
Bunny | +0.010 |
lor | +0.009 |
Neg logit contributions | |
equation | -0.014 |
dice | -0.014 |
bench | -0.013 |
scoreboard | -0.013 |
2 | -0.013 |
Token | 1 |
Token ID | 352 |
Feature activation | -8.66e+00 |
Pos logit contributions | |
Chick | +0.049 |
burn | +0.045 |
Bunny | +0.041 |
unic | +0.039 |
Pig | +0.038 |
Neg logit contributions | |
dice | -0.050 |
2 | -0.050 |
equation | -0.047 |
3 | -0.045 |
2 | -0.045 |
Token | st |
Token ID | 301 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
dice | +0.553 |
2 | +0.515 |
equation | +0.511 |
4 | +0.485 |
scoreboard | +0.476 |
Neg logit contributions | |
Chick | -0.486 |
burn | -0.467 |
seed | -0.456 |
ie | -0.451 |
pt | -0.444 |
Token | person |
Token ID | 1048 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
Chick | +0.123 |
burn | +0.112 |
Bunny | +0.103 |
pt | +0.101 |
seed | +0.098 |
Neg logit contributions | |
dice | -0.119 |
2 | -0.118 |
equation | -0.109 |
2 | -0.107 |
3 | -0.107 |
Token | said |
Token ID | 531 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
dice | +0.027 |
2 | +0.027 |
equation | +0.024 |
2 | +0.023 |
4 | +0.023 |
Neg logit contributions | |
Chick | -0.034 |
burn | -0.032 |
pt | -0.030 |
Bunny | -0.029 |
seed | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
dice | +0.088 |
2 | +0.088 |
2 | +0.085 |
seven | +0.079 |
1 | +0.078 |
Neg logit contributions | |
Chick | -0.174 |
burn | -0.172 |
Bunny | -0.147 |
pt | -0.144 |
seed | -0.143 |
Token | " |
Token ID | 366 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
Chick | +0.008 |
burn | +0.007 |
Bunny | +0.007 |
D | +0.007 |
Pig | +0.007 |
Neg logit contributions | |
dice | -0.008 |
2 | -0.007 |
equation | -0.007 |
scoreboard | -0.007 |
ars | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
dice | +0.062 |
2 | +0.060 |
Kyle | +0.057 |
equation | +0.055 |
scoreboard | +0.054 |
Neg logit contributions | |
Chick | -0.052 |
burn | -0.049 |
streaming | -0.042 |
pt | -0.042 |
light | -0.042 |
Token | He |
Token ID | 679 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
dice | +0.020 |
2 | +0.019 |
equation | +0.018 |
seven | +0.017 |
agree | +0.017 |
Neg logit contributions | |
Chick | -0.023 |
burn | -0.019 |
Bunny | -0.019 |
D | -0.018 |
M | -0.018 |
Token | counted |
Token ID | 14789 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
dice | +0.074 |
2 | +0.072 |
bench | +0.069 |
equation | +0.068 |
booth | +0.067 |
Neg logit contributions | |
Chick | -0.085 |
burn | -0.070 |
M | -0.069 |
Bunny | -0.068 |
unic | -0.066 |
Token | 1 |
Token ID | 352 |
Feature activation | -9.09e+00 |
Pos logit contributions | |
dice | +0.208 |
equation | +0.202 |
2 | +0.198 |
five | +0.186 |
scoreboard | +0.185 |
Neg logit contributions | |
Chick | -0.229 |
burn | -0.210 |
Bunny | -0.188 |
M | -0.182 |
Madd | -0.174 |
Token | , |
Token ID | 11 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
dice | +0.524 |
bench | +0.515 |
equation | +0.509 |
adamant | +0.504 |
Kyle | +0.490 |
Neg logit contributions | |
Chick | -0.497 |
burn | -0.449 |
light | -0.433 |
M | -0.419 |
ie | -0.417 |
Token | 2 |
Token ID | 17 |
Feature activation | -8.60e+00 |
Pos logit contributions | |
bench | +0.004 |
dice | +0.004 |
agree | +0.004 |
equation | +0.004 |
scoreboard | +0.004 |
Neg logit contributions | |
Chick | -0.011 |
M | -0.010 |
Bunny | -0.009 |
Pig | -0.009 |
B | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
dice | +0.538 |
equation | +0.513 |
scoreboard | +0.491 |
2 | +0.490 |
Kyle | +0.487 |
Neg logit contributions | |
Chick | -0.500 |
burn | -0.445 |
Bunny | -0.386 |
ie | -0.382 |
M | -0.382 |
Token | 3 |
Token ID | 18 |
Feature activation | -6.93e+00 |
Pos logit contributions | |
bench | +0.006 |
dice | +0.005 |
equation | +0.005 |
adamant | +0.005 |
scoreboard | +0.005 |
Neg logit contributions | |
Chick | -0.012 |
M | -0.010 |
Bunny | -0.010 |
B | -0.010 |
Pig | -0.010 |
Token | ... |
Token ID | 986 |
Feature activation | -4.67e+00 |
Pos logit contributions | |
dice | +0.432 |
equation | +0.418 |
2 | +0.395 |
booth | +0.395 |
scoreboard | +0.395 |
Neg logit contributions | |
Chick | -0.401 |
burn | -0.354 |
D | -0.314 |
pt | -0.310 |
M | -0.309 |
Token | all |
Token ID | 477 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
dice | +0.147 |
scoreboard | +0.142 |
equation | +0.141 |
adamant | +0.128 |
booth | +0.122 |
Neg logit contributions | |
Chick | -0.404 |
burn | -0.371 |
Bunny | -0.338 |
M | -0.337 |
B | -0.332 |
Token | the |
Token ID | 262 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
dice | +0.074 |
2 | +0.072 |
equation | +0.069 |
scoreboard | +0.069 |
booth | +0.068 |
Neg logit contributions | |
Chick | -0.064 |
burn | -0.056 |
M | -0.056 |
ie | -0.056 |
seed | -0.052 |
Token | € |
Token ID | 26391 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
dice | +0.054 |
2 | +0.052 |
2 | +0.050 |
man | +0.047 |
booth | +0.047 |
Neg logit contributions | |
Chick | -0.060 |
burn | -0.052 |
Sleep | -0.051 |
lor | -0.050 |
Bunny | -0.049 |
Token | � |
Token ID | 129 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
dice | +0.084 |
2 | +0.083 |
2 | +0.079 |
equation | +0.076 |
seven | +0.076 |
Neg logit contributions | |
Chick | -0.097 |
burn | -0.093 |
Bunny | -0.080 |
pt | -0.076 |
seed | -0.076 |
Token | � |
Token ID | 241 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
Chick | +0.212 |
burn | +0.181 |
D | +0.172 |
Bunny | +0.171 |
Dod | +0.166 |
Neg logit contributions | |
dice | -0.217 |
2 | -0.197 |
2 | -0.187 |
equation | -0.179 |
booth | -0.174 |
Token | 3 |
Token ID | 18 |
Feature activation | -6.80e+00 |
Pos logit contributions | |
dice | +0.104 |
2 | +0.102 |
2 | +0.099 |
equation | +0.095 |
1 | +0.092 |
Neg logit contributions | |
Chick | -0.127 |
burn | -0.120 |
Bunny | -0.106 |
D | -0.103 |
pt | -0.101 |
Token | , |
Token ID | 11 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
dice | +0.382 |
2 | +0.376 |
equation | +0.354 |
2 | +0.354 |
3 | +0.340 |
Neg logit contributions | |
Chick | -0.479 |
burn | -0.458 |
Bunny | -0.401 |
pt | -0.398 |
D | -0.383 |
Token | 2 |
Token ID | 17 |
Feature activation | -8.59e+00 |
Pos logit contributions | |
dice | +0.007 |
equation | +0.007 |
bench | +0.006 |
2 | +0.006 |
Kyle | +0.006 |
Neg logit contributions | |
Chick | -0.011 |
burn | -0.010 |
Bunny | -0.009 |
D | -0.009 |
Pig | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
dice | +0.531 |
2 | +0.515 |
equation | +0.513 |
2 | +0.487 |
3 | +0.478 |
Neg logit contributions | |
Chick | -0.537 |
burn | -0.498 |
Bunny | -0.440 |
pt | -0.424 |
D | -0.424 |
Token | 1 |
Token ID | 16 |
Feature activation | -6.76e+00 |
Pos logit contributions | |
dice | +0.009 |
equation | +0.008 |
2 | +0.008 |
bench | +0.007 |
Kyle | +0.007 |
Neg logit contributions | |
Chick | -0.013 |
burn | -0.012 |
Bunny | -0.011 |
Pig | -0.011 |
D | -0.011 |
Token | Go |
Token ID | 1514 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
dice | +0.360 |
2 | +0.354 |
2 | +0.331 |
equation | +0.324 |
seven | +0.317 |
Neg logit contributions | |
Chick | -0.513 |
burn | -0.496 |
Bunny | -0.434 |
pt | -0.423 |
seed | -0.409 |
Token | ! |
Token ID | 0 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
burn | +0.056 |
Chick | +0.053 |
Bunny | +0.048 |
pt | +0.047 |
D | +0.045 |
Neg logit contributions | |
2 | -0.037 |
dice | -0.037 |
equation | -0.037 |
2 | -0.034 |
4 | -0.032 |
Token | â |
Token ID | 22940 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
dice | +0.028 |
2 | +0.028 |
2 | +0.026 |
equation | +0.025 |
seven | +0.025 |
Neg logit contributions | |
Chick | -0.031 |
burn | -0.029 |
Bunny | -0.025 |
pt | -0.024 |
seed | -0.024 |
Token | He |
Token ID | 1544 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
Chick | +0.043 |
burn | +0.036 |
lull | +0.035 |
Bunny | +0.034 |
Sleep | +0.032 |
Neg logit contributions | |
equation | -0.040 |
2 | -0.040 |
2 | -0.040 |
1 | -0.039 |
dice | -0.038 |
Token | looked |
Token ID | 3114 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
dice | +0.088 |
2 | +0.087 |
2 | +0.081 |
equation | +0.079 |
seven | +0.077 |
Neg logit contributions | |
Chick | -0.101 |
burn | -0.095 |
Bunny | -0.084 |
pt | -0.081 |
seed | -0.078 |
Token | around |
Token ID | 1088 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
Chick | +0.029 |
burn | +0.027 |
Bunny | +0.025 |
pt | +0.024 |
Betsy | +0.023 |
Neg logit contributions | |
2 | -0.027 |
dice | -0.027 |
equation | -0.025 |
4 | -0.024 |
3 | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
dice | +0.025 |
2 | +0.025 |
equation | +0.023 |
4 | +0.023 |
3 | +0.022 |
Neg logit contributions | |
Chick | -0.026 |
Bunny | -0.023 |
M | -0.022 |
burn | -0.021 |
D | -0.021 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
Chick | +0.009 |
burn | +0.008 |
Bunny | +0.008 |
pt | +0.007 |
D | +0.007 |
Neg logit contributions | |
dice | -0.006 |
2 | -0.006 |
equation | -0.005 |
2 | -0.005 |
3 | -0.005 |
Token | 1 |
Token ID | 352 |
Feature activation | -8.57e+00 |
Pos logit contributions | |
dice | +0.007 |
2 | +0.007 |
2 | +0.007 |
seven | +0.006 |
1 | +0.006 |
Neg logit contributions | |
burn | -0.013 |
Chick | -0.012 |
pt | -0.010 |
lor | -0.010 |
seed | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
dice | +0.500 |
equation | +0.483 |
2 | +0.464 |
Kyle | +0.452 |
agree | +0.444 |
Neg logit contributions | |
Chick | -0.514 |
burn | -0.513 |
seed | -0.440 |
Bunny | -0.435 |
light | -0.433 |
Token | 2 |
Token ID | 362 |
Feature activation | -7.26e+00 |
Pos logit contributions | |
Chick | +0.031 |
Bunny | +0.027 |
Pig | +0.025 |
Betsy | +0.025 |
D | +0.025 |
Neg logit contributions | |
dice | -0.023 |
ars | -0.022 |
five | -0.022 |
agree | -0.021 |
equation | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
dice | +0.428 |
2 | +0.404 |
equation | +0.399 |
2 | +0.376 |
3 | +0.374 |
Neg logit contributions | |
Chick | -0.496 |
burn | -0.456 |
Bunny | -0.410 |
pt | -0.394 |
seed | -0.391 |
Token | 3 |
Token ID | 513 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
Chick | +0.028 |
Bunny | +0.025 |
Pig | +0.023 |
Betsy | +0.023 |
M | +0.023 |
Neg logit contributions | |
dice | -0.020 |
ars | -0.019 |
five | -0.019 |
agree | -0.018 |
bench | -0.018 |
Token | people |
Token ID | 661 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
dice | +0.109 |
2 | +0.105 |
equation | +0.100 |
2 | +0.099 |
3 | +0.097 |
Neg logit contributions | |
Chick | -0.099 |
burn | -0.089 |
Bunny | -0.080 |
pt | -0.077 |
seed | -0.077 |
Token | for |
Token ID | 329 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
Chick | +0.195 |
burn | +0.188 |
Bunny | +0.172 |
Dod | +0.167 |
seed | +0.167 |
Neg logit contributions | |
2 | -0.082 |
dice | -0.082 |
2 | -0.079 |
seven | -0.077 |
4 | -0.074 |
Token | it |
Token ID | 340 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
2 | +0.136 |
2 | +0.129 |
1 | +0.124 |
busy | +0.118 |
dice | +0.117 |
Neg logit contributions | |
burn | -0.211 |
lor | -0.197 |
Chick | -0.191 |
pt | -0.185 |
lull | -0.182 |
Token | to |
Token ID | 284 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
burn | +0.098 |
Chick | +0.096 |
lor | +0.085 |
rim | +0.083 |
Dod | +0.082 |
Neg logit contributions | |
work | -0.028 |
seven | -0.028 |
2 | -0.028 |
dice | -0.028 |
first | -0.028 |
Token | rest |
Token ID | 1334 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
burn | +0.039 |
Chick | +0.037 |
lor | +0.035 |
maid | +0.032 |
streaming | +0.032 |
Neg logit contributions | |
sign | -0.021 |
agree | -0.021 |
dice | -0.020 |
work | -0.019 |
seven | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
burn | +0.343 |
Chick | +0.331 |
lor | +0.304 |
text | +0.290 |
seed | +0.290 |
Neg logit contributions | |
seven | -0.068 |
busy | -0.066 |
first | -0.066 |
2 | -0.060 |
and | -0.059 |
Token | Mitt |
Token ID | 16627 |
Feature activation | +7.98e+00 |
Pos logit contributions | |
burn | +0.019 |
Chick | +0.018 |
pt | +0.016 |
lull | +0.015 |
lor | +0.015 |
Neg logit contributions | |
2 | -0.013 |
2 | -0.013 |
dice | -0.013 |
1 | -0.012 |
seven | -0.012 |
Token | ens |
Token ID | 641 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
Chick | +0.541 |
burn | +0.514 |
Bunny | +0.433 |
pt | +0.430 |
lor | +0.411 |
Neg logit contributions | |
2 | -0.496 |
dice | -0.481 |
2 | -0.460 |
equation | -0.444 |
seven | -0.439 |
Token | even |
Token ID | 772 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
Chick | +0.152 |
burn | +0.150 |
Bunny | +0.125 |
pt | +0.123 |
seed | +0.120 |
Neg logit contributions | |
2 | -0.122 |
dice | -0.121 |
2 | -0.116 |
seven | -0.112 |
3 | -0.109 |
Token | came |
Token ID | 1625 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
dice | +0.006 |
2 | +0.006 |
2 | +0.006 |
seven | +0.006 |
3 | +0.006 |
Neg logit contributions | |
burn | -0.010 |
Chick | -0.010 |
lor | -0.009 |
pt | -0.008 |
streaming | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
Chick | +0.150 |
burn | +0.143 |
lor | +0.127 |
pt | +0.125 |
Sleep | +0.123 |
Neg logit contributions | |
2 | -0.087 |
2 | -0.084 |
dice | -0.080 |
seven | -0.079 |
3 | -0.077 |
Token | check |
Token ID | 2198 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
burn | +0.041 |
Chick | +0.039 |
lor | +0.037 |
pt | +0.036 |
seed | +0.035 |
Neg logit contributions | |
2 | -0.018 |
2 | -0.018 |
dice | -0.017 |
agree | -0.017 |
seven | -0.017 |
Token | milk |
Token ID | 7545 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
2 | +0.031 |
dice | +0.031 |
2 | +0.029 |
equation | +0.028 |
seven | +0.028 |
Neg logit contributions | |
Chick | -0.047 |
burn | -0.045 |
Bunny | -0.040 |
pt | -0.039 |
seed | -0.038 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Chick | +0.228 |
burn | +0.218 |
Bunny | +0.193 |
pt | +0.189 |
lull | +0.183 |
Neg logit contributions | |
dice | -0.142 |
2 | -0.140 |
2 | -0.133 |
seven | -0.129 |
equation | -0.125 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Chick | +0.090 |
burn | +0.085 |
Bunny | +0.076 |
pt | +0.072 |
D | +0.071 |
Neg logit contributions | |
dice | -0.068 |
2 | -0.067 |
2 | -0.062 |
equation | -0.061 |
3 | -0.059 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
dice | +0.049 |
2 | +0.048 |
equation | +0.043 |
3 | +0.042 |
2 | +0.040 |
Neg logit contributions | |
Chick | -0.085 |
burn | -0.078 |
Bunny | -0.075 |
pt | -0.074 |
M | -0.071 |
Token | and |
Token ID | 290 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
dice | +0.073 |
2 | +0.072 |
2 | +0.066 |
equation | +0.063 |
seven | +0.062 |
Neg logit contributions | |
Chick | -0.137 |
burn | -0.133 |
Bunny | -0.118 |
pt | -0.115 |
seed | -0.112 |
Token | drank |
Token ID | 24070 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
dice | +0.031 |
2 | +0.031 |
2 | +0.029 |
seven | +0.028 |
equation | +0.027 |
Neg logit contributions | |
Chick | -0.056 |
burn | -0.055 |
Bunny | -0.047 |
pt | -0.047 |
seed | -0.046 |
Token | his |
Token ID | 465 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
Chick | +0.453 |
burn | +0.451 |
lor | +0.395 |
pt | +0.375 |
Bunny | +0.372 |
Neg logit contributions | |
dice | -0.265 |
2 | -0.257 |
2 | -0.254 |
seven | -0.251 |
1 | -0.230 |
Token | milk |
Token ID | 7545 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
Chick | +0.033 |
burn | +0.032 |
lor | +0.029 |
ectar | +0.027 |
pt | +0.026 |
Neg logit contributions | |
dice | -0.033 |
seven | -0.031 |
2 | -0.031 |
2 | -0.030 |
man | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
Chick | +0.226 |
burn | +0.213 |
lor | +0.192 |
Bunny | +0.191 |
pt | +0.189 |
Neg logit contributions | |
dice | -0.110 |
2 | -0.105 |
2 | -0.101 |
seven | -0.100 |
man | -0.095 |
Token | He |
Token ID | 679 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
dice | +0.023 |
2 | +0.023 |
2 | +0.021 |
equation | +0.020 |
seven | +0.020 |
Neg logit contributions | |
Chick | -0.038 |
burn | -0.037 |
Bunny | -0.033 |
pt | -0.032 |
seed | -0.031 |
Token | was |
Token ID | 373 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
dice | +0.080 |
2 | +0.079 |
2 | +0.075 |
seven | +0.075 |
equation | +0.071 |
Neg logit contributions | |
burn | -0.112 |
Chick | -0.111 |
Bunny | -0.094 |
pt | -0.091 |
ectar | -0.091 |
Token | strike |
Token ID | 5587 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
dice | +0.028 |
2 | +0.027 |
2 | +0.025 |
seven | +0.024 |
3 | +0.024 |
Neg logit contributions | |
Chick | -0.039 |
burn | -0.036 |
Bunny | -0.033 |
lull | -0.031 |
pt | -0.031 |
Token | ! |
Token ID | 0 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
Chick | +0.038 |
burn | +0.036 |
Bunny | +0.031 |
pt | +0.030 |
seed | +0.030 |
Neg logit contributions | |
2 | -0.026 |
dice | -0.026 |
2 | -0.024 |
equation | -0.023 |
seven | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
Chick | +0.002 |
burn | +0.002 |
Bunny | +0.001 |
pt | +0.001 |
seed | +0.001 |
Neg logit contributions | |
dice | -0.001 |
2 | -0.001 |
2 | -0.001 |
equation | -0.001 |
seven | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
Chick | +0.042 |
burn | +0.040 |
Bunny | +0.036 |
pt | +0.035 |
seed | +0.034 |
Neg logit contributions | |
dice | -0.028 |
2 | -0.028 |
2 | -0.026 |
equation | -0.025 |
seven | -0.025 |
Token | Jul |
Token ID | 16980 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
Chick | +0.039 |
burn | +0.035 |
Bunny | +0.031 |
pt | +0.030 |
lor | +0.030 |
Neg logit contributions | |
dice | -0.032 |
2 | -0.031 |
2 | -0.029 |
equation | -0.029 |
seven | -0.028 |
Token | ie |
Token ID | 494 |
Feature activation | +5.04e+00 |
Pos logit contributions | |
burn | +0.097 |
Chick | +0.094 |
Bunny | +0.070 |
Betsy | +0.058 |
Dod | +0.058 |
Neg logit contributions | |
2 | -0.237 |
dice | -0.235 |
2 | -0.233 |
seven | -0.228 |
1 | -0.225 |
Token | looked |
Token ID | 3114 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
Chick | +0.362 |
burn | +0.328 |
Bunny | +0.308 |
pt | +0.289 |
seed | +0.285 |
Neg logit contributions | |
dice | -0.310 |
2 | -0.290 |
equation | -0.276 |
2 | -0.269 |
seven | -0.262 |
Token | up |
Token ID | 510 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
Chick | +0.022 |
Bunny | +0.020 |
burn | +0.020 |
pt | +0.019 |
streaming | +0.017 |
Neg logit contributions | |
dice | -0.024 |
2 | -0.024 |
equation | -0.022 |
4 | -0.021 |
3 | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +7.51e-02 |
Pos logit contributions | |
dice | +0.049 |
2 | +0.045 |
equation | +0.043 |
2 | +0.041 |
scoreboard | +0.040 |
Neg logit contributions | |
Chick | -0.059 |
burn | -0.056 |
Bunny | -0.053 |
D | -0.050 |
M | -0.049 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
Chick | +0.006 |
burn | +0.006 |
Bunny | +0.005 |
pt | +0.005 |
seed | +0.005 |
Neg logit contributions | |
dice | -0.004 |
2 | -0.004 |
equation | -0.003 |
2 | -0.003 |
3 | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
dice | +0.008 |
2 | +0.008 |
2 | +0.007 |
1 | +0.006 |
seven | +0.006 |
Neg logit contributions | |
burn | -0.017 |
Chick | -0.016 |
lor | -0.014 |
lull | -0.014 |
seed | -0.014 |
Token | closer |
Token ID | 5699 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
Chick | +0.077 |
burn | +0.074 |
lor | +0.064 |
seed | +0.063 |
Bunny | +0.063 |
Neg logit contributions | |
2 | -0.049 |
dice | -0.049 |
2 | -0.048 |
seven | -0.046 |
1 | -0.046 |
Token | and |
Token ID | 290 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
dice | +0.039 |
2 | +0.039 |
2 | +0.036 |
equation | +0.034 |
seven | +0.034 |
Neg logit contributions | |
Chick | -0.063 |
burn | -0.061 |
Bunny | -0.054 |
pt | -0.053 |
seed | -0.051 |
Token | watch |
Token ID | 2342 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
dice | +0.011 |
2 | +0.010 |
2 | +0.010 |
seven | +0.009 |
equation | +0.009 |
Neg logit contributions | |
Chick | -0.016 |
burn | -0.016 |
Bunny | -0.013 |
pt | -0.013 |
seed | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
burn | +0.010 |
Chick | +0.010 |
lor | +0.008 |
pt | +0.008 |
seed | +0.008 |
Neg logit contributions | |
dice | -0.007 |
2 | -0.007 |
2 | -0.007 |
1 | -0.007 |
seven | -0.007 |
Token | The |
Token ID | 383 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
dice | +0.003 |
2 | +0.003 |
equation | +0.003 |
2 | +0.003 |
seven | +0.003 |
Neg logit contributions | |
Chick | -0.004 |
Bunny | -0.003 |
D | -0.003 |
burn | -0.003 |
M | -0.003 |
Token | c |
Token ID | 269 |
Feature activation | +5.22e+00 |
Pos logit contributions | |
Chick | +0.060 |
burn | +0.056 |
Bunny | +0.049 |
pt | +0.045 |
D | +0.045 |
Neg logit contributions | |
dice | -0.074 |
2 | -0.072 |
2 | -0.068 |
equation | -0.068 |
1 | -0.067 |
Token | actus |
Token ID | 34144 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Chick | +0.299 |
burn | +0.288 |
Bunny | +0.240 |
pt | +0.230 |
seed | +0.222 |
Neg logit contributions | |
2 | -0.373 |
dice | -0.361 |
2 | -0.342 |
equation | -0.339 |
seven | -0.332 |
Token | was |
Token ID | 373 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
Chick | +0.124 |
burn | +0.118 |
Bunny | +0.103 |
pt | +0.099 |
seed | +0.097 |
Neg logit contributions | |
dice | -0.111 |
2 | -0.111 |
2 | -0.104 |
equation | -0.100 |
seven | -0.099 |
Token | so |
Token ID | 523 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
Chick | +0.078 |
burn | +0.076 |
Bunny | +0.067 |
pt | +0.065 |
seed | +0.064 |
Neg logit contributions | |
dice | -0.047 |
2 | -0.047 |
2 | -0.043 |
equation | -0.041 |
seven | -0.041 |
Token | excited |
Token ID | 6568 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
Chick | +0.039 |
burn | +0.037 |
Bunny | +0.033 |
pt | +0.032 |
seed | +0.031 |
Neg logit contributions | |
dice | -0.022 |
2 | -0.022 |
2 | -0.020 |
equation | -0.019 |
seven | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -8.48e-02 |
Pos logit contributions | |
Chick | +0.001 |
burn | +0.001 |
Bunny | +0.001 |
pt | +0.001 |
D | +0.001 |
Neg logit contributions | |
dice | -0.001 |
2 | -0.001 |
2 | -0.001 |
3 | -0.001 |
equation | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
Chick | +0.030 |
burn | +0.028 |
Bunny | +0.025 |
pt | +0.024 |
seed | +0.023 |
Neg logit contributions | |
dice | -0.022 |
2 | -0.022 |
2 | -0.020 |
equation | -0.020 |
seven | -0.020 |
Token | One |
Token ID | 3198 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
Chick | +0.028 |
burn | +0.028 |
unic | +0.023 |
pt | +0.023 |
lull | +0.022 |
Neg logit contributions | |
dice | -0.020 |
2 | -0.019 |
2 | -0.018 |
scoreboard | -0.017 |
equation | -0.017 |
Token | day |
Token ID | 1110 |
Feature activation | -8.71e-02 |
Pos logit contributions | |
2 | +0.081 |
dice | +0.080 |
2 | +0.076 |
seven | +0.074 |
equation | +0.072 |
Neg logit contributions | |
Chick | -0.140 |
burn | -0.137 |
pt | -0.121 |
lor | -0.119 |
Bunny | -0.118 |
Token | , |
Token ID | 11 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
dice | +0.004 |
2 | +0.004 |
2 | +0.004 |
equation | +0.004 |
seven | +0.004 |
Neg logit contributions | |
Chick | -0.007 |
burn | -0.007 |
Bunny | -0.006 |
pt | -0.006 |
seed | -0.005 |
Token | Jenn |
Token ID | 9777 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
Chick | +0.016 |
burn | +0.015 |
Bunny | +0.012 |
Br | +0.012 |
pt | +0.012 |
Neg logit contributions | |
dice | -0.016 |
2 | -0.016 |
equation | -0.015 |
2 | -0.015 |
seven | -0.014 |
Token | ie |
Token ID | 494 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
2 | +0.171 |
dice | +0.167 |
2 | +0.164 |
seven | +0.159 |
1 | +0.159 |
Neg logit contributions | |
Chick | -0.059 |
burn | -0.052 |
Bunny | -0.040 |
Sleep | -0.035 |
Madd | -0.033 |
Token | was |
Token ID | 373 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Chick | +0.394 |
burn | +0.383 |
Bunny | +0.331 |
pt | +0.325 |
seed | +0.315 |
Neg logit contributions | |
2 | -0.268 |
dice | -0.265 |
2 | -0.251 |
seven | -0.239 |
equation | -0.238 |
Token | at |
Token ID | 379 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
Chick | +0.086 |
burn | +0.084 |
Bunny | +0.072 |
pt | +0.071 |
seed | +0.069 |
Neg logit contributions | |
2 | -0.066 |
dice | -0.066 |
2 | -0.062 |
seven | -0.060 |
equation | -0.059 |
Token | the |
Token ID | 262 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
dice | +0.095 |
2 | +0.094 |
2 | +0.085 |
ars | +0.085 |
seven | +0.084 |
Neg logit contributions | |
Chick | -0.119 |
burn | -0.112 |
Bunny | -0.099 |
D | -0.092 |
M | -0.092 |
Token | store |
Token ID | 3650 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
dice | +0.026 |
2 | +0.026 |
2 | +0.024 |
equation | +0.022 |
3 | +0.022 |
Neg logit contributions | |
Chick | -0.038 |
burn | -0.037 |
Bunny | -0.031 |
lull | -0.030 |
seed | -0.030 |
Token | with |
Token ID | 351 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
dice | +0.192 |
2 | +0.179 |
2 | +0.173 |
seven | +0.169 |
equation | +0.168 |
Neg logit contributions | |
Chick | -0.167 |
burn | -0.166 |
Bunny | -0.139 |
D | -0.132 |
Betsy | -0.129 |
Token | side |
Token ID | 1735 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
dice | +0.047 |
2 | +0.044 |
equation | +0.043 |
Kyle | +0.042 |
2 | +0.042 |
Neg logit contributions | |
Chick | -0.052 |
burn | -0.051 |
Bunny | -0.044 |
light | -0.042 |
D | -0.041 |
Token | safely |
Token ID | 11512 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
dice | +0.047 |
2 | +0.047 |
2 | +0.044 |
equation | +0.043 |
seven | +0.042 |
Neg logit contributions | |
Chick | -0.054 |
burn | -0.052 |
Bunny | -0.045 |
pt | -0.043 |
seed | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
dice | +0.083 |
2 | +0.081 |
2 | +0.076 |
equation | +0.075 |
seven | +0.074 |
Neg logit contributions | |
Chick | -0.091 |
burn | -0.090 |
Bunny | -0.077 |
pt | -0.076 |
seed | -0.071 |
Token | |
Token ID | 220 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
2 | +0.010 |
dice | +0.009 |
2 | +0.009 |
3 | +0.008 |
equation | +0.008 |
Neg logit contributions | |
Chick | -0.015 |
burn | -0.015 |
pt | -0.013 |
Bunny | -0.013 |
seed | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
Chick | +0.010 |
burn | +0.010 |
Bunny | +0.009 |
pt | +0.008 |
seed | +0.008 |
Neg logit contributions | |
dice | -0.007 |
2 | -0.007 |
2 | -0.007 |
seven | -0.007 |
equation | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Chick | +0.023 |
burn | +0.021 |
Bunny | +0.019 |
pt | +0.018 |
seed | +0.018 |
Neg logit contributions | |
dice | -0.017 |
2 | -0.016 |
2 | -0.015 |
seven | -0.015 |
equation | -0.015 |
Token | Since |
Token ID | 6385 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Chick | +0.021 |
burn | +0.020 |
Bunny | +0.017 |
lull | +0.017 |
lor | +0.017 |
Neg logit contributions | |
dice | -0.015 |
2 | -0.015 |
2 | -0.014 |
seven | -0.014 |
equation | -0.014 |
Token | then |
Token ID | 788 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
Chick | +0.088 |
burn | +0.085 |
Bunny | +0.076 |
pt | +0.074 |
seed | +0.073 |
Neg logit contributions | |
dice | -0.043 |
2 | -0.043 |
2 | -0.039 |
equation | -0.037 |
seven | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +6.62e-02 |
Pos logit contributions | |
2 | +0.087 |
dice | +0.083 |
2 | +0.082 |
1 | +0.076 |
seven | +0.076 |
Neg logit contributions | |
Chick | -0.166 |
burn | -0.163 |
Bunny | -0.142 |
pt | -0.141 |
seed | -0.140 |
Token | the |
Token ID | 262 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
burn | +0.005 |
Chick | +0.005 |
pt | +0.005 |
seed | +0.004 |
lor | +0.004 |
Neg logit contributions | |
2 | -0.003 |
dice | -0.003 |
2 | -0.003 |
seven | -0.003 |
1 | -0.003 |
Token | little |
Token ID | 1310 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
dice | +0.050 |
2 | +0.048 |
equation | +0.047 |
five | +0.045 |
Kyle | +0.044 |
Neg logit contributions | |
Chick | -0.045 |
burn | -0.042 |
Bunny | -0.037 |
Pig | -0.035 |
lull | -0.033 |
Token | spotted |
Token ID | 13489 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Chick | +0.106 |
burn | +0.099 |
Bunny | +0.086 |
pt | +0.085 |
seed | +0.081 |
Neg logit contributions | |
dice | -0.104 |
2 | -0.103 |
2 | -0.097 |
equation | -0.095 |
seven | -0.093 |
Token | a |
Token ID | 257 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
burn | +0.096 |
Chick | +0.095 |
lull | +0.081 |
pt | +0.080 |
lor | +0.079 |
Neg logit contributions | |
dice | -0.047 |
2 | -0.046 |
2 | -0.045 |
1 | -0.042 |
seven | -0.042 |
Token | small |
Token ID | 1402 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
dice | +0.042 |
2 | +0.042 |
2 | +0.039 |
equation | +0.038 |
seven | +0.037 |
Neg logit contributions | |
Chick | -0.055 |
burn | -0.052 |
Bunny | -0.047 |
pt | -0.043 |
seed | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | +9.98e-02 |
Pos logit contributions | |
2 | +0.055 |
dice | +0.054 |
2 | +0.049 |
equation | +0.049 |
five | +0.049 |
Neg logit contributions | |
Chick | -0.058 |
burn | -0.053 |
Bunny | -0.050 |
chick | -0.046 |
Madd | -0.045 |
Token | black |
Token ID | 2042 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
Chick | +0.007 |
burn | +0.007 |
Bunny | +0.006 |
seed | +0.006 |
D | +0.006 |
Neg logit contributions | |
2 | -0.006 |
dice | -0.006 |
equation | -0.005 |
2 | -0.005 |
five | -0.005 |
Token | spider |
Token ID | 19230 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
dice | +0.015 |
2 | +0.015 |
2 | +0.014 |
equation | +0.013 |
3 | +0.013 |
Neg logit contributions | |
Chick | -0.014 |
burn | -0.013 |
Bunny | -0.011 |
pt | -0.011 |
seed | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
Chick | +0.143 |
burn | +0.137 |
Bunny | +0.118 |
pt | +0.115 |
seed | +0.112 |
Neg logit contributions | |
dice | -0.120 |
2 | -0.120 |
2 | -0.113 |
equation | -0.108 |
seven | -0.108 |
Token | The |
Token ID | 383 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
2 | +0.027 |
dice | +0.026 |
2 | +0.026 |
seven | +0.024 |
1 | +0.024 |
Neg logit contributions | |
burn | -0.031 |
Chick | -0.030 |
pt | -0.026 |
Bunny | -0.024 |
seed | -0.024 |
Token | bird |
Token ID | 6512 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
Chick | +0.043 |
burn | +0.039 |
Bunny | +0.034 |
seed | +0.030 |
chick | +0.030 |
Neg logit contributions | |
dice | -0.059 |
2 | -0.059 |
2 | -0.056 |
equation | -0.054 |
3 | -0.053 |
Token | picked |
Token ID | 6497 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
Chick | +0.214 |
burn | +0.206 |
Bunny | +0.179 |
pt | +0.175 |
seed | +0.171 |
Neg logit contributions | |
dice | -0.153 |
2 | -0.153 |
2 | -0.143 |
equation | -0.136 |
seven | -0.136 |
Token | it |
Token ID | 340 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
dice | +0.010 |
2 | +0.010 |
2 | +0.009 |
seven | +0.009 |
1 | +0.009 |
Neg logit contributions | |
Chick | -0.013 |
burn | -0.013 |
pt | -0.011 |
Bunny | -0.011 |
seed | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
2 | +0.136 |
dice | +0.134 |
equation | +0.123 |
2 | +0.123 |
3 | +0.120 |
Neg logit contributions | |
Chick | -0.151 |
burn | -0.141 |
Bunny | -0.126 |
pt | -0.123 |
Madd | -0.117 |
Token | a |
Token ID | 257 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
Chick | +0.010 |
burn | +0.010 |
Bunny | +0.008 |
pt | +0.008 |
seed | +0.008 |
Neg logit contributions | |
dice | -0.009 |
2 | -0.009 |
2 | -0.009 |
seven | -0.008 |
equation | -0.008 |
Token | little |
Token ID | 1310 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
dice | +0.043 |
2 | +0.043 |
2 | +0.039 |
seven | +0.038 |
1 | +0.038 |
Neg logit contributions | |
Chick | -0.057 |
burn | -0.052 |
Bunny | -0.048 |
lull | -0.045 |
pt | -0.044 |
Token | dog |
Token ID | 3290 |
Feature activation | +9.17e-01 |
Pos logit contributions | |
Chick | +0.091 |
burn | +0.085 |
Bunny | +0.080 |
chick | +0.074 |
Madd | +0.073 |
Neg logit contributions | |
dice | -0.073 |
2 | -0.073 |
equation | -0.066 |
2 | -0.065 |
1 | -0.065 |
Token | named |
Token ID | 3706 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
Chick | +0.064 |
burn | +0.063 |
Bunny | +0.052 |
pt | +0.051 |
ectar | +0.050 |
Neg logit contributions | |
dice | -0.054 |
2 | -0.054 |
2 | -0.051 |
seven | -0.049 |
equation | -0.048 |
Token | Spot |
Token ID | 15899 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
Chick | +0.202 |
burn | +0.199 |
pt | +0.169 |
seed | +0.164 |
Bunny | +0.162 |
Neg logit contributions | |
dice | -0.169 |
2 | -0.168 |
2 | -0.160 |
seven | -0.151 |
1 | -0.150 |
Token | came |
Token ID | 1625 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
Chick | +0.106 |
burn | +0.102 |
Bunny | +0.087 |
pt | +0.085 |
seed | +0.083 |
Neg logit contributions | |
2 | -0.088 |
dice | -0.088 |
2 | -0.083 |
seven | -0.079 |
equation | -0.079 |
Token | by |
Token ID | 416 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
Chick | +0.118 |
burn | +0.114 |
Bunny | +0.099 |
pt | +0.096 |
seed | +0.093 |
Neg logit contributions | |
dice | -0.095 |
2 | -0.094 |
2 | -0.088 |
equation | -0.085 |
seven | -0.084 |
Token | . |
Token ID | 13 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
dice | +0.212 |
2 | +0.206 |
2 | +0.188 |
seven | +0.187 |
4 | +0.184 |
Neg logit contributions | |
Chick | -0.243 |
burn | -0.226 |
Bunny | -0.211 |
pt | -0.201 |
D | -0.195 |
Token | Spot |
Token ID | 15899 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
dice | +0.008 |
2 | +0.008 |
2 | +0.007 |
equation | +0.007 |
seven | +0.007 |
Neg logit contributions | |
Chick | -0.008 |
burn | -0.008 |
Bunny | -0.007 |
pt | -0.006 |
seed | -0.006 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
Chick | +0.086 |
Bunny | +0.074 |
burn | +0.072 |
D | +0.065 |
pt | +0.063 |
Neg logit contributions | |
dice | -0.100 |
2 | -0.095 |
equation | -0.091 |
2 | -0.089 |
seven | -0.088 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
dice | +0.003 |
2 | +0.003 |
equation | +0.003 |
2 | +0.003 |
3 | +0.002 |
Neg logit contributions | |
Chick | -0.005 |
burn | -0.005 |
Bunny | -0.004 |
pt | -0.004 |
seed | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
2 | +0.050 |
2 | +0.050 |
seven | +0.047 |
1 | +0.047 |
dice | +0.045 |
Neg logit contributions | |
Chick | -0.105 |
burn | -0.103 |
lor | -0.088 |
seed | -0.087 |
Bunny | -0.086 |
Token | " |
Token ID | 366 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
Chick | +0.003 |
burn | +0.003 |
Bunny | +0.002 |
pt | +0.002 |
seed | +0.002 |
Neg logit contributions | |
dice | -0.002 |
2 | -0.002 |
2 | -0.002 |
equation | -0.001 |
seven | -0.001 |
Token | Yes |
Token ID | 5297 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
dice | +0.043 |
2 | +0.043 |
2 | +0.040 |
equation | +0.038 |
seven | +0.038 |
Neg logit contributions | |
Chick | -0.063 |
burn | -0.061 |
Bunny | -0.053 |
pt | -0.052 |
seed | -0.051 |
Token | , |
Token ID | 11 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
2 | +0.020 |
2 | +0.020 |
dice | +0.020 |
seven | +0.020 |
1 | +0.019 |
Neg logit contributions | |
Chick | -0.041 |
burn | -0.041 |
seed | -0.036 |
ectar | -0.035 |
pt | -0.034 |
Token | I |
Token ID | 314 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
2 | +0.020 |
dice | +0.019 |
2 | +0.019 |
seven | +0.018 |
1 | +0.018 |
Neg logit contributions | |
Chick | -0.025 |
burn | -0.024 |
pt | -0.021 |
seed | -0.021 |
lor | -0.020 |
Token | want |
Token ID | 765 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
Chick | +0.031 |
burn | +0.029 |
Bunny | +0.026 |
pt | +0.026 |
seed | +0.024 |
Neg logit contributions | |
dice | -0.027 |
2 | -0.026 |
2 | -0.025 |
equation | -0.024 |
seven | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
dice | +0.124 |
2 | +0.117 |
2 | +0.117 |
seven | +0.112 |
1 | +0.108 |
Neg logit contributions | |
Chick | -0.212 |
burn | -0.210 |
pt | -0.175 |
lor | -0.175 |
seed | -0.173 |
Token | play |
Token ID | 711 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Chick | +0.016 |
burn | +0.015 |
Bunny | +0.014 |
seed | +0.014 |
pt | +0.013 |
Neg logit contributions | |
dice | -0.009 |
2 | -0.009 |
2 | -0.008 |
seven | -0.008 |
3 | -0.008 |
Token | too |
Token ID | 1165 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
Chick | +0.094 |
burn | +0.091 |
Bunny | +0.078 |
pt | +0.077 |
seed | +0.075 |
Neg logit contributions | |
dice | -0.065 |
2 | -0.064 |
2 | -0.060 |
seven | -0.057 |
equation | -0.057 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
dice | +0.190 |
2 | +0.189 |
2 | +0.178 |
equation | +0.171 |
seven | +0.170 |
Neg logit contributions | |
Chick | -0.218 |
burn | -0.210 |
Bunny | -0.180 |
pt | -0.175 |
seed | -0.170 |
Token | Sorry |
Token ID | 14385 |
Feature activation | +9.61e-01 |
Pos logit contributions | |
dice | +0.153 |
2 | +0.152 |
2 | +0.146 |
equation | +0.143 |
1 | +0.140 |
Neg logit contributions | |
Chick | -0.181 |
burn | -0.179 |
Bunny | -0.150 |
pt | -0.141 |
D | -0.140 |
Token | , |
Token ID | 11 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
Chick | +0.078 |
burn | +0.076 |
Bunny | +0.066 |
pt | +0.065 |
seed | +0.064 |
Neg logit contributions | |
2 | -0.047 |
dice | -0.046 |
2 | -0.043 |
seven | -0.041 |
equation | -0.041 |
Token | m |
Token ID | 285 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
dice | +0.015 |
2 | +0.015 |
2 | +0.014 |
equation | +0.014 |
seven | +0.013 |
Neg logit contributions | |
Chick | -0.020 |
burn | -0.019 |
Bunny | -0.017 |
pt | -0.016 |
D | -0.016 |
Token | ister |
Token ID | 1694 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
Chick | +0.026 |
burn | +0.025 |
Bunny | +0.021 |
pt | +0.020 |
seed | +0.020 |
Neg logit contributions | |
2 | -0.029 |
dice | -0.028 |
2 | -0.027 |
equation | -0.026 |
seven | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
dice | +0.036 |
2 | +0.036 |
equation | +0.034 |
2 | +0.033 |
3 | +0.033 |
Neg logit contributions | |
Chick | -0.035 |
burn | -0.033 |
Bunny | -0.029 |
pt | -0.027 |
seed | -0.027 |
Token | we |
Token ID | 356 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
dice | +0.021 |
2 | +0.021 |
2 | +0.020 |
seven | +0.019 |
equation | +0.019 |
Neg logit contributions | |
Chick | -0.019 |
burn | -0.018 |
Bunny | -0.015 |
pt | -0.015 |
seed | -0.014 |
Token | did |
Token ID | 750 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Chick | +0.081 |
burn | +0.078 |
Bunny | +0.068 |
pt | +0.065 |
seed | +0.064 |
Neg logit contributions | |
dice | -0.053 |
2 | -0.053 |
2 | -0.049 |
seven | -0.047 |
equation | -0.047 |
Token | not |
Token ID | 407 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
2 | +0.086 |
dice | +0.084 |
2 | +0.081 |
equation | +0.076 |
3 | +0.076 |
Neg logit contributions | |
Chick | -0.098 |
burn | -0.094 |
Bunny | -0.080 |
pt | -0.078 |
seed | -0.077 |
Token | know |
Token ID | 760 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
dice | +0.065 |
2 | +0.065 |
2 | +0.059 |
1 | +0.057 |
equation | +0.056 |
Neg logit contributions | |
Chick | -0.107 |
burn | -0.106 |
pt | -0.094 |
Bunny | -0.094 |
seed | -0.090 |
Token | ," |
Token ID | 553 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
dice | +0.130 |
2 | +0.127 |
2 | +0.122 |
seven | +0.118 |
1 | +0.117 |
Neg logit contributions | |
burn | -0.223 |
Chick | -0.222 |
Bunny | -0.188 |
lor | -0.184 |
lull | -0.182 |
Token | Lily |
Token ID | 20037 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
Chick | +0.066 |
D | +0.056 |
Bunny | +0.055 |
M | +0.053 |
burn | +0.051 |
Neg logit contributions | |
2 | -0.070 |
dice | -0.070 |
equation | -0.069 |
seven | -0.065 |
3 | -0.065 |
Token | and |
Token ID | 290 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
dice | +0.016 |
2 | +0.016 |
2 | +0.015 |
seven | +0.014 |
equation | +0.014 |
Neg logit contributions | |
Chick | -0.027 |
burn | -0.026 |
Bunny | -0.023 |
pt | -0.022 |
seed | -0.022 |
Token | amazed |
Token ID | 24562 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
2 | +0.006 |
dice | +0.006 |
2 | +0.005 |
seven | +0.005 |
equation | +0.005 |
Neg logit contributions | |
Chick | -0.010 |
burn | -0.010 |
pt | -0.008 |
Bunny | -0.008 |
seed | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
2 | +0.041 |
dice | +0.041 |
2 | +0.038 |
seven | +0.037 |
1 | +0.036 |
Neg logit contributions | |
Chick | -0.064 |
burn | -0.062 |
Bunny | -0.053 |
pt | -0.052 |
seed | -0.051 |
Token | be |
Token ID | 307 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
Chick | +0.029 |
burn | +0.028 |
Bunny | +0.025 |
pt | +0.025 |
D | +0.024 |
Neg logit contributions | |
dice | -0.017 |
2 | -0.016 |
2 | -0.015 |
equation | -0.014 |
3 | -0.014 |
Token | flying |
Token ID | 7348 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
2 | +0.110 |
dice | +0.107 |
2 | +0.106 |
seven | +0.105 |
3 | +0.099 |
Neg logit contributions | |
Chick | -0.170 |
burn | -0.162 |
pt | -0.142 |
Bunny | -0.139 |
lull | -0.135 |
Token | in |
Token ID | 287 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Chick | +0.041 |
burn | +0.039 |
Bunny | +0.034 |
pt | +0.033 |
seed | +0.033 |
Neg logit contributions | |
dice | -0.027 |
2 | -0.027 |
2 | -0.025 |
seven | -0.024 |
equation | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
dice | +0.086 |
2 | +0.085 |
2 | +0.080 |
seven | +0.076 |
equation | +0.076 |
Neg logit contributions | |
Chick | -0.133 |
burn | -0.129 |
Bunny | -0.112 |
pt | -0.110 |
seed | -0.108 |
Token | machine |
Token ID | 4572 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
dice | +0.032 |
2 | +0.031 |
2 | +0.028 |
equation | +0.028 |
1 | +0.026 |
Neg logit contributions | |
Chick | -0.054 |
burn | -0.053 |
Bunny | -0.047 |
pt | -0.045 |
seed | -0.045 |
Token | ! |
Token ID | 0 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
dice | +0.063 |
2 | +0.062 |
2 | +0.058 |
equation | +0.056 |
seven | +0.056 |
Neg logit contributions | |
Chick | -0.078 |
burn | -0.076 |
Bunny | -0.066 |
pt | -0.064 |
seed | -0.062 |
Token | |
Token ID | 220 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
dice | +0.028 |
2 | +0.028 |
2 | +0.026 |
equation | +0.025 |
seven | +0.025 |
Neg logit contributions | |
Chick | -0.042 |
burn | -0.040 |
Bunny | -0.036 |
pt | -0.035 |
seed | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
Chick | +0.002 |
burn | +0.002 |
Bunny | +0.002 |
pt | +0.002 |
seed | +0.002 |
Neg logit contributions | |
dice | -0.002 |
2 | -0.002 |
2 | -0.001 |
equation | -0.001 |
seven | -0.001 |
Token | He |
Token ID | 679 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
dice | +0.004 |
2 | +0.004 |
2 | +0.003 |
seven | +0.003 |
equation | +0.003 |
Neg logit contributions | |
Chick | -0.006 |
burn | -0.005 |
Bunny | -0.005 |
D | -0.004 |
pt | -0.004 |
Token | got |
Token ID | 1392 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
dice | +0.063 |
2 | +0.062 |
2 | +0.056 |
equation | +0.056 |
seven | +0.054 |
Neg logit contributions | |
Chick | -0.073 |
burn | -0.068 |
Bunny | -0.061 |
pt | -0.060 |
seed | -0.057 |
Token | some |
Token ID | 617 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
Chick | +0.011 |
burn | +0.010 |
Bunny | +0.009 |
pt | +0.009 |
seed | +0.009 |
Neg logit contributions | |
2 | -0.008 |
dice | -0.008 |
2 | -0.008 |
equation | -0.008 |
seven | -0.007 |
Token | sticky |
Token ID | 23408 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
Chick | +0.206 |
burn | +0.195 |
Bunny | +0.176 |
pt | +0.174 |
seed | +0.171 |
Neg logit contributions | |
2 | -0.153 |
dice | -0.149 |
2 | -0.140 |
seven | -0.137 |
3 | -0.135 |
Token | tape |
Token ID | 9154 |
Feature activation | -4.74e+00 |
Pos logit contributions | |
Chick | +0.054 |
burn | +0.051 |
Bunny | +0.044 |
pt | +0.043 |
seed | +0.042 |
Neg logit contributions | |
2 | -0.051 |
dice | -0.050 |
2 | -0.048 |
3 | -0.046 |
seven | -0.046 |
Token | and |
Token ID | 290 |
Feature activation | -6.53e-02 |
Pos logit contributions | |
2 | +0.213 |
dice | +0.210 |
2 | +0.192 |
equation | +0.184 |
3 | +0.183 |
Neg logit contributions | |
Chick | -0.402 |
burn | -0.395 |
Bunny | -0.349 |
pt | -0.344 |
seed | -0.333 |
Token | carefully |
Token ID | 7773 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
dice | +0.003 |
2 | +0.003 |
2 | +0.003 |
equation | +0.003 |
seven | +0.003 |
Neg logit contributions | |
Chick | -0.005 |
burn | -0.005 |
Bunny | -0.004 |
pt | -0.004 |
seed | -0.004 |
Token | put |
Token ID | 1234 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
dice | +0.212 |
2 | +0.207 |
2 | +0.192 |
seven | +0.189 |
equation | +0.188 |
Neg logit contributions | |
Chick | -0.290 |
burn | -0.273 |
pt | -0.241 |
Bunny | -0.241 |
seed | -0.231 |
Token | the |
Token ID | 262 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
2 | +0.021 |
dice | +0.021 |
equation | +0.020 |
2 | +0.019 |
4 | +0.019 |
Neg logit contributions | |
Chick | -0.020 |
burn | -0.018 |
Bunny | -0.016 |
pt | -0.015 |
seed | -0.015 |
Token | paint |
Token ID | 7521 |
Feature activation | -7.66e-01 |
Pos logit contributions | |
2 | +0.042 |
dice | +0.041 |
2 | +0.038 |
equation | +0.038 |
4 | +0.037 |
Neg logit contributions | |
Chick | -0.051 |
burn | -0.050 |
seed | -0.043 |
Bunny | -0.042 |
pt | -0.041 |
Token | back |
Token ID | 736 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
2 | +0.049 |
dice | +0.048 |
2 | +0.045 |
equation | +0.045 |
3 | +0.043 |
Neg logit contributions | |
Chick | -0.049 |
burn | -0.049 |
pt | -0.040 |
Bunny | -0.040 |
seed | -0.039 |
Token | ?" |
Token ID | 1701 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
Chick | +0.084 |
burn | +0.082 |
Bunny | +0.070 |
pt | +0.070 |
seed | +0.069 |
Neg logit contributions | |
dice | -0.068 |
2 | -0.067 |
2 | -0.064 |
seven | -0.061 |
1 | -0.060 |
Token | she |
Token ID | 673 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Chick | +0.210 |
burn | +0.204 |
Bunny | +0.173 |
pt | +0.169 |
seed | +0.164 |
Neg logit contributions | |
dice | -0.185 |
2 | -0.185 |
2 | -0.175 |
seven | -0.168 |
equation | -0.167 |
Token | asked |
Token ID | 1965 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
Chick | +0.078 |
burn | +0.070 |
Bunny | +0.065 |
pt | +0.061 |
Pig | +0.060 |
Neg logit contributions | |
dice | -0.067 |
2 | -0.062 |
equation | -0.057 |
five | -0.056 |
scoreboard | -0.055 |
Token | her |
Token ID | 607 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
2 | +0.035 |
dice | +0.034 |
2 | +0.034 |
1 | +0.032 |
seven | +0.031 |
Neg logit contributions | |
Chick | -0.048 |
burn | -0.048 |
lor | -0.040 |
Bunny | -0.039 |
pt | -0.039 |
Token | mom |
Token ID | 1995 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
Chick | +0.070 |
burn | +0.067 |
Bunny | +0.055 |
pt | +0.054 |
seed | +0.053 |
Neg logit contributions | |
dice | -0.082 |
2 | -0.082 |
2 | -0.078 |
seven | -0.075 |
equation | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
Chick | +0.041 |
burn | +0.040 |
Bunny | +0.035 |
pt | +0.034 |
seed | +0.033 |
Neg logit contributions | |
dice | -0.036 |
2 | -0.035 |
2 | -0.032 |
equation | -0.032 |
seven | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
dice | +0.002 |
2 | +0.002 |
2 | +0.002 |
equation | +0.001 |
seven | +0.001 |
Neg logit contributions | |
Chick | -0.002 |
burn | -0.002 |
Bunny | -0.002 |
pt | -0.002 |
seed | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
Chick | +0.029 |
burn | +0.028 |
Bunny | +0.025 |
pt | +0.024 |
seed | +0.023 |
Neg logit contributions | |
dice | -0.020 |
2 | -0.020 |
2 | -0.018 |
equation | -0.018 |
seven | -0.017 |
Token | " |
Token ID | 1 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
Chick | +0.026 |
burn | +0.025 |
Bunny | +0.022 |
lull | +0.021 |
lor | +0.021 |
Neg logit contributions | |
dice | -0.020 |
2 | -0.019 |
2 | -0.018 |
equation | -0.018 |
seven | -0.017 |
Token | Yes |
Token ID | 5297 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
dice | +0.139 |
2 | +0.133 |
equation | +0.131 |
2 | +0.127 |
1 | +0.123 |
Neg logit contributions | |
Chick | -0.142 |
burn | -0.140 |
Bunny | -0.118 |
lull | -0.113 |
D | -0.112 |
Token | , |
Token ID | 11 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
2 | +0.012 |
2 | +0.012 |
dice | +0.012 |
seven | +0.012 |
1 | +0.011 |
Neg logit contributions | |
Chick | -0.025 |
burn | -0.025 |
seed | -0.022 |
Bunny | -0.022 |
pt | -0.021 |
Token | your |
Token ID | 534 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
Chick | +0.023 |
burn | +0.021 |
Bunny | +0.019 |
pt | +0.018 |
D | +0.017 |
Neg logit contributions | |
2 | -0.022 |
dice | -0.021 |
equation | -0.020 |
2 | -0.020 |
4 | -0.019 |
Token | key |
Token ID | 1994 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
Chick | +0.040 |
burn | +0.040 |
Bunny | +0.034 |
pt | +0.034 |
unic | +0.033 |
Neg logit contributions | |
2 | -0.035 |
2 | -0.033 |
4 | -0.032 |
dice | -0.032 |
3 | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
2 | +0.240 |
dice | +0.238 |
2 | +0.225 |
equation | +0.219 |
3 | +0.215 |
Neg logit contributions | |
Chick | -0.250 |
burn | -0.242 |
Bunny | -0.205 |
pt | -0.202 |
seed | -0.193 |
Token | You |
Token ID | 921 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
dice | +0.066 |
2 | +0.066 |
2 | +0.062 |
seven | +0.060 |
equation | +0.059 |
Neg logit contributions | |
Chick | -0.084 |
burn | -0.082 |
Bunny | -0.070 |
pt | -0.069 |
seed | -0.067 |
Token | lost |
Token ID | 2626 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
2 | +0.090 |
dice | +0.087 |
2 | +0.084 |
equation | +0.084 |
seven | +0.080 |
Neg logit contributions | |
Chick | -0.107 |
burn | -0.101 |
pt | -0.090 |
Bunny | -0.089 |
seed | -0.082 |
Token | the |
Token ID | 262 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Chick | +0.020 |
burn | +0.018 |
Bunny | +0.016 |
pt | +0.015 |
D | +0.015 |
Neg logit contributions | |
2 | -0.022 |
dice | -0.021 |
equation | -0.020 |
2 | -0.020 |
3 | -0.020 |
Token | game |
Token ID | 983 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
2 | +0.073 |
4 | +0.067 |
2 | +0.066 |
dice | +0.066 |
3 | +0.064 |
Neg logit contributions | |
burn | -0.082 |
Chick | -0.078 |
Bunny | -0.068 |
unic | -0.067 |
pt | -0.065 |
Token | ." |
Token ID | 526 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
2 | +0.056 |
dice | +0.054 |
2 | +0.052 |
equation | +0.051 |
3 | +0.050 |
Neg logit contributions | |
Chick | -0.049 |
burn | -0.046 |
pt | -0.040 |
Bunny | -0.040 |
seed | -0.036 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
Chick | +0.091 |
Bunny | +0.079 |
burn | +0.075 |
D | +0.074 |
M | +0.070 |
Neg logit contributions | |
dice | -0.102 |
2 | -0.097 |
2 | -0.095 |
seven | -0.095 |
equation | -0.094 |
Token | L |
Token ID | 43 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
Chick | +0.054 |
burn | +0.051 |
Bunny | +0.046 |
pt | +0.044 |
seed | +0.043 |
Neg logit contributions | |
dice | -0.039 |
2 | -0.039 |
2 | -0.036 |
equation | -0.035 |
seven | -0.035 |
Token | ily |
Token ID | 813 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
Chick | +0.032 |
burn | +0.030 |
Bunny | +0.027 |
pt | +0.027 |
D | +0.026 |
Neg logit contributions | |
2 | -0.026 |
dice | -0.026 |
equation | -0.025 |
3 | -0.024 |
2 | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
Chick | +0.216 |
burn | +0.208 |
Bunny | +0.184 |
lull | +0.179 |
ie | +0.175 |
Neg logit contributions | |
dice | -0.208 |
2 | -0.188 |
equation | -0.180 |
3 | -0.172 |
seven | -0.169 |
Token | so |
Token ID | 523 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
Chick | +0.021 |
burn | +0.020 |
Bunny | +0.018 |
pt | +0.017 |
D | +0.017 |
Neg logit contributions | |
dice | -0.012 |
2 | -0.012 |
equation | -0.011 |
2 | -0.011 |
seven | -0.010 |
Token | off |
Token ID | 572 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
burn | +0.044 |
Chick | +0.042 |
pt | +0.036 |
seed | +0.036 |
ulp | +0.035 |
Neg logit contributions | |
2 | -0.046 |
2 | -0.046 |
dice | -0.046 |
seven | -0.045 |
1 | -0.044 |
Token | Amanda |
Token ID | 23040 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
Chick | +0.211 |
burn | +0.204 |
Bunny | +0.172 |
pt | +0.168 |
seed | +0.164 |
Neg logit contributions | |
dice | -0.207 |
2 | -0.207 |
2 | -0.197 |
seven | -0.190 |
equation | -0.188 |
Token | went |
Token ID | 1816 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
Chick | +0.055 |
burn | +0.054 |
Bunny | +0.046 |
pt | +0.046 |
seed | +0.044 |
Neg logit contributions | |
dice | -0.047 |
2 | -0.046 |
2 | -0.043 |
equation | -0.042 |
seven | -0.041 |
Token | ! |
Token ID | 0 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
burn | +0.040 |
Chick | +0.040 |
Bunny | +0.037 |
Beth | +0.034 |
Betsy | +0.033 |
Neg logit contributions | |
dice | -0.058 |
2 | -0.057 |
equation | -0.052 |
ars | -0.051 |
thirteen | -0.050 |
Token |
|
Token ID | 198 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
dice | +0.014 |
2 | +0.014 |
2 | +0.013 |
equation | +0.013 |
seven | +0.012 |
Neg logit contributions | |
Chick | -0.018 |
burn | -0.017 |
Bunny | -0.015 |
pt | -0.014 |
Madd | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
Chick | +0.029 |
burn | +0.027 |
Bunny | +0.024 |
pt | +0.023 |
lor | +0.022 |
Neg logit contributions | |
dice | -0.025 |
2 | -0.024 |
equation | -0.023 |
2 | -0.022 |
seven | -0.022 |
Token | She |
Token ID | 3347 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
Chick | +0.025 |
burn | +0.023 |
Bunny | +0.020 |
lor | +0.019 |
lull | +0.019 |
Neg logit contributions | |
dice | -0.021 |
2 | -0.020 |
equation | -0.020 |
scoreboard | -0.019 |
2 | -0.018 |
Token | ran |
Token ID | 4966 |
Feature activation | +9.59e-01 |
Pos logit contributions | |
dice | +0.043 |
2 | +0.042 |
equation | +0.041 |
2 | +0.038 |
ensive | +0.037 |
Neg logit contributions | |
Chick | -0.039 |
burn | -0.038 |
Bunny | -0.034 |
D | -0.032 |
pt | -0.031 |
Token | around |
Token ID | 1088 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
Chick | +0.044 |
Bunny | +0.042 |
burn | +0.041 |
Madd | +0.040 |
Beth | +0.040 |
Neg logit contributions | |
2 | -0.073 |
equation | -0.070 |
dice | -0.066 |
Twenty | -0.064 |
irteen | -0.064 |
Token | , |
Token ID | 11 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
dice | +0.201 |
2 | +0.199 |
2 | +0.185 |
equation | +0.179 |
seven | +0.176 |
Neg logit contributions | |
Chick | -0.284 |
burn | -0.276 |
Bunny | -0.242 |
pt | -0.234 |
seed | -0.229 |
Token | you |
Token ID | 345 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
dice | +0.012 |
2 | +0.012 |
2 | +0.011 |
seven | +0.011 |
equation | +0.010 |
Neg logit contributions | |
Chick | -0.016 |
burn | -0.016 |
Bunny | -0.013 |
pt | -0.013 |
seed | -0.013 |
Token | cannot |
Token ID | 2314 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
dice | +0.054 |
2 | +0.053 |
2 | +0.050 |
seven | +0.047 |
3 | +0.046 |
Neg logit contributions | |
Chick | -0.085 |
burn | -0.082 |
Bunny | -0.071 |
seed | -0.069 |
lull | -0.068 |
Token | use |
Token ID | 779 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
2 | +0.086 |
dice | +0.085 |
2 | +0.081 |
seven | +0.077 |
equation | +0.076 |
Neg logit contributions | |
Chick | -0.123 |
burn | -0.119 |
Bunny | -0.104 |
pt | -0.103 |
seed | -0.097 |
Token | my |
Token ID | 616 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
2 | +0.224 |
dice | +0.220 |
2 | +0.207 |
equation | +0.206 |
3 | +0.202 |
Neg logit contributions | |
Chick | -0.223 |
burn | -0.207 |
Bunny | -0.181 |
pt | -0.174 |
D | -0.167 |
Token | papers |
Token ID | 9473 |
Feature activation | -4.83e+00 |
Pos logit contributions | |
Chick | +0.045 |
burn | +0.043 |
Bunny | +0.038 |
pt | +0.036 |
seed | +0.036 |
Neg logit contributions | |
2 | -0.037 |
dice | -0.037 |
2 | -0.035 |
3 | -0.035 |
4 | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
2 | +0.293 |
dice | +0.287 |
2 | +0.273 |
3 | +0.264 |
equation | +0.264 |
Neg logit contributions | |
Chick | -0.325 |
burn | -0.320 |
pt | -0.272 |
Bunny | -0.269 |
seed | -0.253 |
Token | They |
Token ID | 1119 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
dice | +0.044 |
2 | +0.044 |
2 | +0.041 |
equation | +0.039 |
seven | +0.039 |
Neg logit contributions | |
Chick | -0.057 |
burn | -0.055 |
Bunny | -0.047 |
pt | -0.046 |
seed | -0.045 |
Token | are |
Token ID | 389 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
Chick | +0.007 |
burn | +0.007 |
pt | +0.006 |
Bunny | +0.006 |
seed | +0.005 |
Neg logit contributions | |
2 | -0.007 |
dice | -0.007 |
2 | -0.007 |
equation | -0.007 |
1 | -0.007 |
Token | mine |
Token ID | 6164 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
Chick | +0.018 |
burn | +0.016 |
Bunny | +0.015 |
pt | +0.014 |
D | +0.014 |
Neg logit contributions | |
2 | -0.016 |
dice | -0.015 |
five | -0.014 |
equation | -0.014 |
4 | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
dice | +0.128 |
2 | +0.127 |
2 | +0.119 |
equation | +0.114 |
seven | +0.113 |
Neg logit contributions | |
Chick | -0.180 |
burn | -0.174 |
Bunny | -0.151 |
pt | -0.148 |
seed | -0.143 |
Token | it |
Token ID | 340 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
burn | +0.173 |
Chick | +0.172 |
pt | +0.141 |
Bunny | +0.140 |
seed | +0.138 |
Neg logit contributions | |
dice | -0.130 |
2 | -0.130 |
2 | -0.123 |
1 | -0.117 |
seven | -0.115 |
Token | . |
Token ID | 13 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
Chick | +0.067 |
burn | +0.065 |
Bunny | +0.056 |
pt | +0.055 |
seed | +0.053 |
Neg logit contributions | |
dice | -0.047 |
2 | -0.047 |
2 | -0.044 |
seven | -0.042 |
equation | -0.042 |
Token |
|
Token ID | 198 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
dice | +0.025 |
2 | +0.025 |
2 | +0.023 |
equation | +0.022 |
seven | +0.022 |
Neg logit contributions | |
Chick | -0.034 |
burn | -0.032 |
Bunny | -0.029 |
pt | -0.028 |
seed | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
Chick | +0.001 |
burn | +0.001 |
Bunny | +0.001 |
pt | +0.001 |
seed | +0.001 |
Neg logit contributions | |
dice | -0.001 |
2 | -0.001 |
2 | -0.001 |
equation | -0.001 |
seven | -0.001 |
Token | The |
Token ID | 464 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
dice | +0.001 |
2 | +0.001 |
2 | +0.001 |
equation | +0.001 |
seven | +0.001 |
Neg logit contributions | |
Chick | -0.001 |
burn | -0.001 |
Bunny | -0.001 |
lull | -0.001 |
lor | -0.001 |
Token | End |
Token ID | 5268 |
Feature activation | -4.82e+00 |
Pos logit contributions | |
Chick | +0.038 |
burn | +0.037 |
Bunny | +0.033 |
chick | +0.031 |
pt | +0.031 |
Neg logit contributions | |
dice | -0.030 |
2 | -0.029 |
2 | -0.027 |
equation | -0.026 |
4 | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
2 | +0.253 |
dice | +0.252 |
2 | +0.235 |
equation | +0.225 |
seven | +0.224 |
Neg logit contributions | |
Chick | -0.371 |
burn | -0.364 |
Bunny | -0.312 |
pt | -0.305 |
seed | -0.299 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
2 | +0.019 |
dice | +0.018 |
2 | +0.017 |
seven | +0.016 |
3 | +0.016 |
Neg logit contributions | |
Chick | -0.038 |
burn | -0.037 |
pt | -0.033 |
Bunny | -0.032 |
seed | -0.032 |
Token | Once |
Token ID | 7454 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
Chick | +0.067 |
burn | +0.065 |
pt | +0.056 |
Bunny | +0.055 |
lull | +0.055 |
Neg logit contributions | |
2 | -0.035 |
dice | -0.035 |
2 | -0.033 |
seven | -0.030 |
equation | -0.030 |
Token | upon |
Token ID | 2402 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Chick | +0.164 |
burn | +0.161 |
Bunny | +0.137 |
seed | +0.134 |
pt | +0.132 |
Neg logit contributions | |
dice | -0.100 |
2 | -0.099 |
2 | -0.094 |
1 | -0.088 |
seven | -0.088 |
Token | a |
Token ID | 257 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
dice | +0.039 |
2 | +0.037 |
2 | +0.034 |
seven | +0.033 |
3 | +0.032 |
Neg logit contributions | |
Chick | -0.094 |
burn | -0.092 |
Bunny | -0.081 |
pt | -0.080 |
seed | -0.079 |
Token | books |
Token ID | 3835 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
2 | +0.225 |
3 | +0.210 |
Kyle | +0.208 |
4 | +0.207 |
five | +0.206 |
Neg logit contributions | |
Chick | -0.200 |
unic | -0.171 |
lull | -0.165 |
burn | -0.163 |
pt | -0.161 |
Token | . |
Token ID | 13 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
2 | +0.107 |
dice | +0.105 |
2 | +0.096 |
equation | +0.096 |
3 | +0.094 |
Neg logit contributions | |
Chick | -0.127 |
burn | -0.123 |
pt | -0.109 |
Bunny | -0.107 |
light | -0.102 |
Token | She |
Token ID | 1375 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
Chick | +0.048 |
burn | +0.045 |
Bunny | +0.040 |
seed | +0.038 |
pt | +0.037 |
Neg logit contributions | |
dice | -0.038 |
2 | -0.037 |
2 | -0.035 |
seven | -0.034 |
equation | -0.034 |
Token | would |
Token ID | 561 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
Chick | +0.016 |
burn | +0.013 |
pt | +0.012 |
unic | +0.011 |
Bunny | +0.010 |
Neg logit contributions | |
dice | -0.029 |
2 | -0.029 |
booth | -0.028 |
scoreboard | -0.027 |
2 | -0.027 |
Token | add |
Token ID | 751 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
Chick | +0.164 |
burn | +0.149 |
lull | +0.142 |
unic | +0.141 |
M | +0.126 |
Neg logit contributions | |
2 | -0.161 |
dice | -0.150 |
ars | -0.146 |
2 | -0.146 |
booth | -0.142 |
Token | numbers |
Token ID | 3146 |
Feature activation | -6.34e+00 |
Pos logit contributions | |
2 | +0.085 |
dice | +0.079 |
agree | +0.079 |
equation | +0.078 |
4 | +0.076 |
Neg logit contributions | |
Chick | -0.092 |
burn | -0.084 |
Bunny | -0.077 |
M | -0.073 |
pt | -0.071 |
Token | and |
Token ID | 290 |
Feature activation | -6.26e-02 |
Pos logit contributions | |
2 | +0.409 |
dice | +0.396 |
equation | +0.395 |
scoreboard | +0.374 |
agree | +0.374 |
Neg logit contributions | |
Chick | -0.357 |
burn | -0.328 |
Bunny | -0.278 |
ectar | -0.266 |
M | -0.265 |
Token | subtract |
Token ID | 34128 |
Feature activation | -7.02e+00 |
Pos logit contributions | |
2 | +0.003 |
booth | +0.003 |
dice | +0.003 |
seven | +0.002 |
adamant | +0.002 |
Neg logit contributions | |
Chick | -0.004 |
unic | -0.004 |
burn | -0.004 |
light | -0.004 |
M | -0.004 |
Token | them |
Token ID | 606 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
dice | +0.451 |
2 | +0.436 |
equation | +0.427 |
seven | +0.423 |
agree | +0.416 |
Neg logit contributions | |
Chick | -0.419 |
burn | -0.379 |
light | -0.313 |
Bunny | -0.311 |
pt | -0.310 |
Token | too |
Token ID | 1165 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
Chick | +0.064 |
burn | +0.058 |
pt | +0.051 |
Bunny | +0.050 |
streaming | +0.048 |
Neg logit contributions | |
2 | -0.068 |
dice | -0.068 |
seven | -0.062 |
2 | -0.062 |
equation | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
dice | +0.187 |
2 | +0.175 |
booth | +0.173 |
seven | +0.170 |
five | +0.166 |
Neg logit contributions | |
Chick | -0.149 |
burn | -0.122 |
Bunny | -0.107 |
pt | -0.107 |
M | -0.106 |
Token | never |
Token ID | 1239 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
dice | +0.062 |
2 | +0.062 |
2 | +0.057 |
equation | +0.057 |
3 | +0.054 |
Neg logit contributions | |
Chick | -0.065 |
burn | -0.063 |
Bunny | -0.055 |
pt | -0.054 |
D | -0.051 |
Token | expected |
Token ID | 2938 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
Chick | +0.071 |
burn | +0.069 |
Bunny | +0.059 |
pt | +0.058 |
seed | +0.056 |
Neg logit contributions | |
dice | -0.058 |
2 | -0.057 |
2 | -0.054 |
seven | -0.052 |
equation | -0.052 |
Token | the |
Token ID | 262 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
2 | +0.096 |
dice | +0.095 |
2 | +0.092 |
seven | +0.087 |
1 | +0.087 |
Neg logit contributions | |
Chick | -0.129 |
burn | -0.124 |
Bunny | -0.104 |
pt | -0.103 |
seed | -0.103 |
Token | turtle |
Token ID | 28699 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
dice | +0.048 |
2 | +0.048 |
2 | +0.044 |
seven | +0.043 |
1 | +0.043 |
Neg logit contributions | |
Chick | -0.054 |
burn | -0.053 |
Bunny | -0.049 |
D | -0.044 |
Madd | -0.043 |
Token | to |
Token ID | 284 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
dice | +0.072 |
2 | +0.072 |
2 | +0.068 |
equation | +0.065 |
seven | +0.065 |
Neg logit contributions | |
Chick | -0.094 |
burn | -0.091 |
Bunny | -0.079 |
pt | -0.077 |
seed | -0.075 |
Token | win |
Token ID | 1592 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
Chick | +0.023 |
burn | +0.022 |
Bunny | +0.020 |
pt | +0.019 |
seed | +0.018 |
Neg logit contributions | |
dice | -0.015 |
2 | -0.015 |
2 | -0.014 |
equation | -0.013 |
seven | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
dice | +0.295 |
2 | +0.295 |
2 | +0.275 |
equation | +0.267 |
3 | +0.265 |
Neg logit contributions | |
Chick | -0.320 |
burn | -0.305 |
Bunny | -0.269 |
pt | -0.266 |
D | -0.251 |
Token | but |
Token ID | 475 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
dice | +0.005 |
2 | +0.005 |
2 | +0.005 |
equation | +0.005 |
3 | +0.005 |
Neg logit contributions | |
Chick | -0.008 |
burn | -0.008 |
Bunny | -0.007 |
pt | -0.007 |
D | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
Chick | +0.010 |
burn | +0.009 |
Bunny | +0.008 |
pt | +0.008 |
D | +0.007 |
Neg logit contributions | |
dice | -0.009 |
2 | -0.009 |
2 | -0.008 |
equation | -0.008 |
seven | -0.008 |
Token | turtle |
Token ID | 28699 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
dice | +0.059 |
2 | +0.058 |
4 | +0.053 |
2 | +0.053 |
3 | +0.053 |
Neg logit contributions | |
Chick | -0.047 |
burn | -0.045 |
Bunny | -0.044 |
D | -0.040 |
Pig | -0.038 |
Token | was |
Token ID | 373 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
dice | +0.088 |
2 | +0.087 |
2 | +0.081 |
equation | +0.080 |
3 | +0.078 |
Neg logit contributions | |
Chick | -0.083 |
burn | -0.079 |
Bunny | -0.071 |
pt | -0.069 |
seed | -0.065 |
Token | elevator |
Token ID | 20932 |
Feature activation | -4.79e+00 |
Pos logit contributions | |
2 | +0.020 |
dice | +0.020 |
2 | +0.019 |
equation | +0.018 |
3 | +0.017 |
Neg logit contributions | |
Chick | -0.033 |
burn | -0.032 |
Bunny | -0.029 |
pt | -0.028 |
seed | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
2 | +0.297 |
dice | +0.296 |
2 | +0.279 |
equation | +0.269 |
3 | +0.265 |
Neg logit contributions | |
burn | -0.312 |
Chick | -0.307 |
pt | -0.256 |
Bunny | -0.254 |
seed | -0.250 |
Token | Tim |
Token ID | 5045 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
Chick | +0.019 |
burn | +0.019 |
Bunny | +0.016 |
pt | +0.016 |
seed | +0.016 |
Neg logit contributions | |
2 | -0.013 |
dice | -0.013 |
2 | -0.012 |
seven | -0.012 |
equation | -0.012 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
dice | +0.026 |
2 | +0.026 |
2 | +0.024 |
equation | +0.024 |
seven | +0.023 |
Neg logit contributions | |
Chick | -0.032 |
burn | -0.031 |
Bunny | -0.027 |
pt | -0.026 |
seed | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
Chick | +0.107 |
burn | +0.104 |
Bunny | +0.090 |
pt | +0.088 |
seed | +0.086 |
Neg logit contributions | |
dice | -0.082 |
2 | -0.082 |
2 | -0.077 |
equation | -0.073 |
seven | -0.073 |
Token | elevator |
Token ID | 20932 |
Feature activation | -4.94e+00 |
Pos logit contributions | |
2 | +0.032 |
dice | +0.032 |
2 | +0.029 |
equation | +0.029 |
4 | +0.028 |
Neg logit contributions | |
burn | -0.040 |
Chick | -0.039 |
Bunny | -0.034 |
lull | -0.033 |
pt | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
2 | +0.261 |
dice | +0.260 |
2 | +0.241 |
equation | +0.231 |
3 | +0.227 |
Neg logit contributions | |
burn | -0.371 |
Chick | -0.370 |
Bunny | -0.316 |
pt | -0.308 |
seed | -0.304 |
Token | felt |
Token ID | 2936 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
dice | +0.007 |
2 | +0.007 |
2 | +0.006 |
seven | +0.006 |
equation | +0.006 |
Neg logit contributions | |
Chick | -0.009 |
burn | -0.009 |
Bunny | -0.007 |
pt | -0.007 |
seed | -0.007 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
Chick | +0.172 |
burn | +0.168 |
Bunny | +0.147 |
pt | +0.144 |
seed | +0.143 |
Neg logit contributions | |
dice | -0.078 |
2 | -0.077 |
2 | -0.073 |
seven | -0.069 |
3 | -0.066 |
Token | to |
Token ID | 284 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
dice | +0.007 |
2 | +0.007 |
equation | +0.006 |
man | +0.006 |
2 | +0.006 |
Neg logit contributions | |
Chick | -0.015 |
burn | -0.014 |
Bunny | -0.012 |
seed | -0.012 |
lor | -0.012 |
Token | be |
Token ID | 307 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
Chick | +0.032 |
burn | +0.031 |
Bunny | +0.028 |
seed | +0.028 |
lor | +0.027 |
Neg logit contributions | |
dice | -0.013 |
2 | -0.013 |
2 | -0.012 |
seven | -0.012 |
equation | -0.011 |