Token | , |
Token ID | 11 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
Suz | +0.083 |
Bee | +0.082 |
M | +0.079 |
Andy | +0.075 |
Mia | +0.073 |
Neg logit contributions | |
aces | -0.202 |
ooter | -0.167 |
uries | -0.164 |
ival | -0.160 |
ests | -0.159 |
Token | a |
Token ID | 257 |
Feature activation | +6.90e-02 |
Pos logit contributions | |
Suz | +0.047 |
Bee | +0.045 |
M | +0.045 |
Andy | +0.042 |
Joe | +0.042 |
Neg logit contributions | |
aces | -0.120 |
ooter | -0.101 |
uries | -0.100 |
ests | -0.097 |
ival | -0.096 |
Token | storm |
Token ID | 6388 |
Feature activation | +7.01e-02 |
Pos logit contributions | |
Suz | +0.094 |
M | +0.088 |
Bee | +0.087 |
Joe | +0.086 |
Andy | +0.086 |
Neg logit contributions | |
aces | -0.165 |
ooter | -0.143 |
ival | -0.140 |
uries | -0.135 |
sweets | -0.132 |
Token | cloud |
Token ID | 6279 |
Feature activation | +9.07e-02 |
Pos logit contributions | |
Suz | +0.100 |
M | +0.098 |
Bee | +0.097 |
Mia | +0.093 |
Joe | +0.093 |
Neg logit contributions | |
aces | -0.166 |
ooter | -0.136 |
ival | -0.134 |
rides | -0.131 |
seek | -0.129 |
Token | came |
Token ID | 1625 |
Feature activation | +8.92e-02 |
Pos logit contributions | |
Suz | +0.127 |
M | +0.122 |
Bee | +0.122 |
Andy | +0.118 |
Joe | +0.116 |
Neg logit contributions | |
aces | -0.219 |
ooter | -0.180 |
ival | -0.173 |
rides | -0.168 |
uries | -0.167 |
Token | over |
Token ID | 625 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Suz | +0.137 |
Mia | +0.134 |
Ali | +0.133 |
Liz | +0.133 |
Bee | +0.129 |
Neg logit contributions | |
aces | -0.184 |
ooter | -0.143 |
ance | -0.137 |
rides | -0.135 |
uries | -0.134 |
Token | the |
Token ID | 262 |
Feature activation | +5.64e-02 |
Pos logit contributions | |
Bee | +0.186 |
Ali | +0.183 |
Suz | +0.180 |
Liz | +0.175 |
Doug | +0.164 |
Neg logit contributions | |
aces | -0.287 |
rides | -0.252 |
sweets | -0.246 |
parties | -0.233 |
cand | -0.230 |
Token | sky |
Token ID | 6766 |
Feature activation | +8.42e-02 |
Pos logit contributions | |
Bee | +0.091 |
Suz | +0.091 |
M | +0.090 |
Andy | +0.086 |
Mia | +0.086 |
Neg logit contributions | |
aces | -0.133 |
uries | -0.105 |
ooter | -0.105 |
ests | -0.104 |
oll | -0.101 |
Token | and |
Token ID | 290 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
Suz | +0.118 |
Bee | +0.116 |
M | +0.112 |
Andy | +0.110 |
Liz | +0.107 |
Neg logit contributions | |
aces | -0.205 |
ooter | -0.168 |
uries | -0.165 |
ival | -0.158 |
seek | -0.157 |
Token | it |
Token ID | 340 |
Feature activation | +5.04e-02 |
Pos logit contributions | |
Suz | +0.046 |
Bee | +0.043 |
Liz | +0.042 |
Ali | +0.041 |
M | +0.041 |
Neg logit contributions | |
aces | -0.091 |
rides | -0.078 |
ival | -0.076 |
sweets | -0.076 |
ooter | -0.074 |
Token | started |
Token ID | 2067 |
Feature activation | +5.40e-02 |
Pos logit contributions | |
Suz | +0.078 |
Bee | +0.072 |
Andy | +0.071 |
M | +0.071 |
Joe | +0.071 |
Neg logit contributions | |
aces | -0.111 |
case | -0.087 |
rides | -0.087 |
ooter | -0.086 |
ival | -0.086 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
Suz | +0.037 |
Bee | +0.036 |
M | +0.036 |
Mia | +0.035 |
Andy | +0.034 |
Neg logit contributions | |
aces | -0.067 |
ooter | -0.055 |
uries | -0.054 |
ests | -0.053 |
ival | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
Suz | +0.058 |
Bee | +0.056 |
M | +0.055 |
Andy | +0.053 |
Joe | +0.052 |
Neg logit contributions | |
aces | -0.154 |
ooter | -0.128 |
uries | -0.126 |
ival | -0.124 |
ests | -0.123 |
Token | a |
Token ID | 257 |
Feature activation | +5.99e-02 |
Pos logit contributions | |
Suz | +0.036 |
Bee | +0.035 |
M | +0.034 |
Andy | +0.033 |
Joe | +0.033 |
Neg logit contributions | |
aces | -0.088 |
ooter | -0.074 |
uries | -0.073 |
ests | -0.071 |
ival | -0.071 |
Token | voice |
Token ID | 3809 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
Suz | +0.081 |
M | +0.075 |
Joe | +0.074 |
Bee | +0.074 |
Andy | +0.073 |
Neg logit contributions | |
aces | -0.140 |
ooter | -0.122 |
ival | -0.121 |
sweets | -0.115 |
bracelet | -0.115 |
Token | shouted |
Token ID | 17293 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
Bee | +0.143 |
Suz | +0.137 |
M | +0.137 |
Mia | +0.131 |
Andy | +0.129 |
Neg logit contributions | |
aces | -0.245 |
ooter | -0.204 |
ival | -0.198 |
rides | -0.196 |
oll | -0.188 |
Token | out |
Token ID | 503 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
Suz | +0.055 |
Bee | +0.054 |
Andy | +0.052 |
M | +0.050 |
Joe | +0.049 |
Neg logit contributions | |
aces | -0.091 |
ooter | -0.074 |
uries | -0.072 |
oll | -0.069 |
ival | -0.069 |
Token | : |
Token ID | 25 |
Feature activation | +6.28e-02 |
Pos logit contributions | |
boiling | +0.224 |
shallow | +0.223 |
etchup | +0.217 |
Suz | +0.213 |
Miles | +0.207 |
Neg logit contributions | |
aces | -0.230 |
sweets | -0.172 |
case | -0.167 |
oll | -0.167 |
bracelet | -0.163 |
Token | " |
Token ID | 366 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
Suz | +0.073 |
Bee | +0.066 |
Andy | +0.065 |
Liz | +0.064 |
boiling | +0.063 |
Neg logit contributions | |
aces | -0.148 |
ooter | -0.124 |
uries | -0.122 |
ival | -0.120 |
lor | -0.119 |
Token | Hey |
Token ID | 10814 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
Suz | +0.033 |
Bee | +0.032 |
M | +0.031 |
Mia | +0.030 |
Joe | +0.030 |
Neg logit contributions | |
aces | -0.054 |
ooter | -0.044 |
uries | -0.043 |
ests | -0.042 |
oll | -0.041 |
Token | ! |
Token ID | 0 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
Suz | +0.043 |
Bee | +0.042 |
M | +0.041 |
Andy | +0.039 |
Mia | +0.037 |
Neg logit contributions | |
aces | -0.113 |
ooter | -0.096 |
uries | -0.095 |
ival | -0.093 |
ests | -0.090 |
Token | Those |
Token ID | 5845 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
Suz | +0.045 |
Bee | +0.044 |
M | +0.044 |
Andy | +0.042 |
Joe | +0.042 |
Neg logit contributions | |
aces | -0.077 |
ooter | -0.062 |
uries | -0.061 |
ests | -0.060 |
ival | -0.059 |
Token | But |
Token ID | 1537 |
Feature activation | +3.49e-02 |
Pos logit contributions | |
Suz | +0.040 |
Bee | +0.039 |
M | +0.039 |
Mia | +0.037 |
Andy | +0.037 |
Neg logit contributions | |
aces | -0.071 |
ooter | -0.058 |
uries | -0.056 |
ests | -0.055 |
oll | -0.054 |
Token | then |
Token ID | 788 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
Suz | +0.042 |
Bee | +0.041 |
M | +0.040 |
Andy | +0.038 |
Joe | +0.038 |
Neg logit contributions | |
aces | -0.094 |
ooter | -0.078 |
uries | -0.078 |
ests | -0.076 |
ival | -0.075 |
Token | a |
Token ID | 257 |
Feature activation | +5.34e-02 |
Pos logit contributions | |
Suz | +0.013 |
Bee | +0.013 |
M | +0.013 |
Andy | +0.012 |
Joe | +0.012 |
Neg logit contributions | |
aces | -0.039 |
ooter | -0.033 |
uries | -0.032 |
ests | -0.032 |
ival | -0.031 |
Token | voice |
Token ID | 3809 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
Suz | +0.072 |
M | +0.068 |
Bee | +0.067 |
Joe | +0.066 |
Andy | +0.066 |
Neg logit contributions | |
aces | -0.130 |
ooter | -0.111 |
ival | -0.109 |
uries | -0.106 |
ests | -0.103 |
Token | spoke |
Token ID | 5158 |
Feature activation | +7.26e-02 |
Pos logit contributions | |
Suz | +0.146 |
M | +0.144 |
Bee | +0.141 |
Joe | +0.134 |
Andy | +0.133 |
Neg logit contributions | |
aces | -0.256 |
ooter | -0.207 |
rides | -0.205 |
ival | -0.201 |
oll | -0.191 |
Token | out |
Token ID | 503 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Suz | +0.099 |
Bee | +0.096 |
M | +0.092 |
Andy | +0.091 |
Mia | +0.090 |
Neg logit contributions | |
aces | -0.180 |
ooter | -0.145 |
uries | -0.141 |
ests | -0.137 |
ival | -0.136 |
Token | from |
Token ID | 422 |
Feature activation | +8.70e-02 |
Pos logit contributions | |
Suz | +0.195 |
boiling | +0.182 |
Liz | +0.169 |
shallow | +0.168 |
M | +0.167 |
Neg logit contributions | |
aces | -0.295 |
case | -0.225 |
novels | -0.223 |
sweets | -0.223 |
rides | -0.222 |
Token | the |
Token ID | 262 |
Feature activation | +4.86e-02 |
Pos logit contributions | |
Suz | +0.094 |
Bee | +0.089 |
M | +0.086 |
Liz | +0.077 |
Ali | +0.075 |
Neg logit contributions | |
aces | -0.227 |
rides | -0.189 |
uries | -0.185 |
sweets | -0.181 |
magazines | -0.177 |
Token | other |
Token ID | 584 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
Suz | +0.072 |
Bee | +0.072 |
M | +0.071 |
Mia | +0.068 |
Andy | +0.068 |
Neg logit contributions | |
aces | -0.119 |
uries | -0.095 |
ooter | -0.095 |
ests | -0.093 |
ival | -0.091 |
Token | room |
Token ID | 2119 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
Suz | +0.045 |
Bee | +0.044 |
M | +0.044 |
Mia | +0.043 |
Joe | +0.042 |
Neg logit contributions | |
aces | -0.066 |
ooter | -0.053 |
uries | -0.052 |
ests | -0.051 |
ival | -0.050 |
Token | : |
Token ID | 25 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
Suz | +0.060 |
Bee | +0.058 |
M | +0.057 |
Andy | +0.055 |
Mia | +0.054 |
Neg logit contributions | |
aces | -0.135 |
ooter | -0.113 |
uries | -0.111 |
ests | -0.109 |
ival | -0.108 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | +5.20e-02 |
Pos logit contributions | |
Suz | +0.029 |
Bee | +0.029 |
M | +0.028 |
Andy | +0.028 |
Joe | +0.027 |
Neg logit contributions | |
aces | -0.045 |
ooter | -0.037 |
uries | -0.036 |
ests | -0.035 |
ival | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
Suz | +0.061 |
Bee | +0.060 |
M | +0.056 |
Mia | +0.053 |
Andy | +0.053 |
Neg logit contributions | |
aces | -0.136 |
ooter | -0.110 |
ival | -0.110 |
uries | -0.108 |
ests | -0.107 |
Token | a |
Token ID | 257 |
Feature activation | +6.20e-02 |
Pos logit contributions | |
Suz | +0.036 |
Bee | +0.036 |
M | +0.033 |
Mia | +0.031 |
Andy | +0.031 |
Neg logit contributions | |
aces | -0.083 |
ival | -0.068 |
ooter | -0.068 |
uries | -0.068 |
sweets | -0.067 |
Token | voice |
Token ID | 3809 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Suz | +0.083 |
M | +0.078 |
Bee | +0.077 |
Andy | +0.077 |
Mia | +0.077 |
Neg logit contributions | |
aces | -0.145 |
ival | -0.127 |
ooter | -0.127 |
bracelet | -0.119 |
sweets | -0.118 |
Token | shouted |
Token ID | 17293 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
Bee | +0.141 |
M | +0.136 |
Suz | +0.134 |
Mia | +0.133 |
Andy | +0.127 |
Neg logit contributions | |
aces | -0.237 |
ooter | -0.196 |
ival | -0.193 |
rides | -0.189 |
oll | -0.178 |
Token | out |
Token ID | 503 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Suz | +0.045 |
Bee | +0.043 |
Andy | +0.041 |
M | +0.041 |
Mia | +0.040 |
Neg logit contributions | |
aces | -0.080 |
ooter | -0.065 |
uries | -0.064 |
ival | -0.062 |
oll | -0.061 |
Token | - |
Token ID | 532 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
etchup | +0.206 |
boiling | +0.203 |
shallow | +0.201 |
Suz | +0.196 |
swollen | +0.191 |
Neg logit contributions | |
aces | -0.228 |
sweets | -0.170 |
case | -0.166 |
oll | -0.166 |
bracelet | -0.164 |
Token | it |
Token ID | 340 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
Suz | +0.049 |
Bee | +0.048 |
Liz | +0.044 |
Andy | +0.043 |
Mia | +0.043 |
Neg logit contributions | |
aces | -0.105 |
ooter | -0.087 |
uries | -0.087 |
ival | -0.086 |
sweets | -0.083 |
Token | was |
Token ID | 373 |
Feature activation | +4.39e-02 |
Pos logit contributions | |
Suz | +0.060 |
Bee | +0.060 |
Mia | +0.055 |
Jen | +0.055 |
Liz | +0.055 |
Neg logit contributions | |
aces | -0.101 |
ival | -0.082 |
case | -0.082 |
ooter | -0.081 |
lor | -0.081 |
Token | Jack |
Token ID | 3619 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
Bee | +0.056 |
Suz | +0.054 |
Ali | +0.051 |
Liz | +0.049 |
Andy | +0.049 |
Neg logit contributions | |
aces | -0.101 |
uries | -0.084 |
ooter | -0.079 |
sweets | -0.078 |
bracelet | -0.078 |
Token | 's |
Token ID | 338 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
Suz | +0.024 |
M | +0.023 |
Bee | +0.023 |
Joe | +0.022 |
Andy | +0.022 |
Neg logit contributions | |
aces | -0.052 |
ooter | -0.043 |
uries | -0.043 |
ests | -0.043 |
ival | -0.042 |
Token | suddenly |
Token ID | 6451 |
Feature activation | +4.34e-02 |
Pos logit contributions | |
Suz | +0.031 |
Bee | +0.031 |
M | +0.029 |
Andy | +0.028 |
Mia | +0.027 |
Neg logit contributions | |
aces | -0.067 |
uries | -0.056 |
ooter | -0.055 |
ival | -0.053 |
ests | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
Suz | +0.046 |
Bee | +0.045 |
M | +0.043 |
Andy | +0.041 |
Mia | +0.040 |
Neg logit contributions | |
aces | -0.120 |
uries | -0.099 |
ooter | -0.099 |
ival | -0.097 |
ests | -0.096 |
Token | a |
Token ID | 257 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
Suz | +0.023 |
Bee | +0.023 |
M | +0.022 |
Andy | +0.021 |
Mia | +0.021 |
Neg logit contributions | |
aces | -0.072 |
ooter | -0.061 |
uries | -0.061 |
ests | -0.059 |
ival | -0.059 |
Token | voice |
Token ID | 3809 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
Suz | +0.074 |
M | +0.070 |
Bee | +0.070 |
Andy | +0.068 |
Joe | +0.067 |
Neg logit contributions | |
aces | -0.137 |
ooter | -0.121 |
ival | -0.118 |
sweets | -0.112 |
bracelet | -0.112 |
Token | shouted |
Token ID | 17293 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
Bee | +0.136 |
M | +0.131 |
Suz | +0.129 |
Mia | +0.124 |
Andy | +0.122 |
Neg logit contributions | |
aces | -0.234 |
ooter | -0.197 |
ival | -0.190 |
rides | -0.188 |
uries | -0.177 |
Token | out |
Token ID | 503 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
Suz | +0.049 |
Bee | +0.048 |
Andy | +0.046 |
M | +0.044 |
Mia | +0.044 |
Neg logit contributions | |
aces | -0.084 |
ooter | -0.069 |
uries | -0.068 |
ival | -0.065 |
oll | -0.065 |
Token | from |
Token ID | 422 |
Feature activation | +7.94e-02 |
Pos logit contributions | |
boiling | +0.211 |
Suz | +0.207 |
shallow | +0.207 |
etchup | +0.207 |
swollen | +0.195 |
Neg logit contributions | |
aces | -0.221 |
sweets | -0.168 |
case | -0.163 |
rides | -0.162 |
oll | -0.159 |
Token | the |
Token ID | 262 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
Bee | +0.104 |
Suz | +0.104 |
M | +0.100 |
swarm | +0.093 |
apy | +0.089 |
Neg logit contributions | |
aces | -0.175 |
rides | -0.148 |
uries | -0.141 |
sweets | -0.139 |
magazines | -0.136 |
Token | tree |
Token ID | 5509 |
Feature activation | +6.20e-02 |
Pos logit contributions | |
Suz | +0.060 |
Bee | +0.059 |
M | +0.058 |
Andy | +0.056 |
Joe | +0.056 |
Neg logit contributions | |
aces | -0.090 |
ooter | -0.073 |
uries | -0.072 |
ests | -0.070 |
ival | -0.069 |
Token | - |
Token ID | 532 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
Suz | +0.081 |
Bee | +0.078 |
M | +0.077 |
Andy | +0.073 |
Mia | +0.073 |
Neg logit contributions | |
aces | -0.160 |
ooter | -0.133 |
uries | -0.130 |
ival | -0.126 |
ests | -0.125 |
Token | it |
Token ID | 340 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
Bee | +0.040 |
Suz | +0.040 |
M | +0.036 |
Andy | +0.035 |
boiling | +0.035 |
Neg logit contributions | |
aces | -0.101 |
ooter | -0.086 |
uries | -0.085 |
ival | -0.085 |
sweets | -0.082 |
Token | you |
Token ID | 345 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
Suz | +0.001 |
Bee | +0.001 |
M | +0.001 |
Andy | +0.001 |
Joe | +0.001 |
Neg logit contributions | |
aces | -0.001 |
ooter | -0.001 |
uries | -0.001 |
ival | -0.001 |
oll | -0.000 |
Token | doing |
Token ID | 1804 |
Feature activation | -5.90e-02 |
Pos logit contributions | |
aces | +0.056 |
ooter | +0.044 |
uries | +0.041 |
oll | +0.041 |
ival | +0.040 |
Neg logit contributions | |
Suz | -0.051 |
Bee | -0.050 |
M | -0.049 |
Andy | -0.047 |
Mia | -0.047 |
Token | ?" |
Token ID | 1701 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
aces | +0.156 |
ooter | +0.128 |
uries | +0.127 |
ests | +0.124 |
ival | +0.124 |
Neg logit contributions | |
Suz | -0.074 |
Bee | -0.072 |
M | -0.070 |
Andy | -0.066 |
Mia | -0.065 |
Token | Mom |
Token ID | 11254 |
Feature activation | +4.99e-02 |
Pos logit contributions | |
rou | +0.036 |
oc | +0.032 |
preventing | +0.031 |
Suz | +0.031 |
swarm | +0.031 |
Neg logit contributions | |
aces | -0.046 |
rides | -0.039 |
case | -0.034 |
oll | -0.034 |
nes | -0.033 |
Token | came |
Token ID | 1625 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
Suz | +0.075 |
crocod | +0.070 |
tad | +0.068 |
Bee | +0.068 |
its | +0.068 |
Neg logit contributions | |
aces | -0.109 |
oll | -0.086 |
ooter | -0.084 |
rides | -0.079 |
ode | -0.078 |
Token | out |
Token ID | 503 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
Suz | +0.102 |
apy | +0.099 |
crocod | +0.097 |
swarm | +0.096 |
oc | +0.096 |
Neg logit contributions | |
aces | -0.106 |
ooter | -0.078 |
rides | -0.074 |
nes | -0.074 |
uries | -0.071 |
Token | of |
Token ID | 286 |
Feature activation | +9.54e-02 |
Pos logit contributions | |
Suz | +0.273 |
Joe | +0.261 |
Andy | +0.258 |
Doug | +0.252 |
Judy | +0.242 |
Neg logit contributions | |
aces | -0.155 |
parties | -0.107 |
cand | -0.106 |
oll | -0.103 |
magazines | -0.102 |
Token | the |
Token ID | 262 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
oc | +0.114 |
Suz | +0.112 |
Bee | +0.105 |
hh | +0.102 |
Andy | +0.100 |
Neg logit contributions | |
aces | -0.194 |
parties | -0.183 |
magazines | -0.181 |
rides | -0.170 |
cand | -0.170 |
Token | house |
Token ID | 2156 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
Suz | +0.063 |
Joe | +0.058 |
M | +0.057 |
Bee | +0.057 |
Andy | +0.056 |
Neg logit contributions | |
aces | -0.048 |
ooter | -0.038 |
rides | -0.038 |
case | -0.037 |
magazines | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
Suz | +0.039 |
Bee | +0.037 |
M | +0.036 |
Andy | +0.036 |
Joe | +0.035 |
Neg logit contributions | |
aces | -0.062 |
ooter | -0.051 |
uries | -0.049 |
seek | -0.047 |
rides | -0.047 |
Token | She |
Token ID | 1375 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
Suz | +0.097 |
Andy | +0.094 |
crocod | +0.090 |
oc | +0.089 |
rim | +0.087 |
Neg logit contributions | |
aces | -0.062 |
case | -0.041 |
ives | -0.035 |
oll | -0.035 |
robe | -0.034 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | +5.97e-02 |
Pos logit contributions | |
Suz | +0.046 |
Bee | +0.044 |
M | +0.044 |
Andy | +0.042 |
Joe | +0.042 |
Neg logit contributions | |
aces | -0.092 |
ooter | -0.076 |
uries | -0.075 |
ests | -0.073 |
ival | -0.073 |
Token | , |
Token ID | 11 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
Suz | +0.063 |
Bee | +0.060 |
M | +0.059 |
Andy | +0.056 |
Joe | +0.055 |
Neg logit contributions | |
aces | -0.169 |
ooter | -0.141 |
uries | -0.139 |
ests | -0.137 |
ival | -0.136 |
Token | a |
Token ID | 257 |
Feature activation | +6.29e-02 |
Pos logit contributions | |
Suz | +0.036 |
Bee | +0.034 |
M | +0.034 |
Andy | +0.032 |
Mia | +0.032 |
Neg logit contributions | |
aces | -0.103 |
ooter | -0.087 |
uries | -0.086 |
ests | -0.085 |
ival | -0.083 |
Token | fox |
Token ID | 21831 |
Feature activation | +5.31e-02 |
Pos logit contributions | |
Suz | +0.083 |
M | +0.077 |
Joe | +0.076 |
Bee | +0.076 |
Andy | +0.075 |
Neg logit contributions | |
aces | -0.153 |
ooter | -0.132 |
ival | -0.130 |
bracelet | -0.123 |
uries | -0.123 |
Token | came |
Token ID | 1625 |
Feature activation | +7.59e-02 |
Pos logit contributions | |
Suz | +0.071 |
M | +0.067 |
Bee | +0.066 |
Andy | +0.064 |
Mia | +0.063 |
Neg logit contributions | |
aces | -0.135 |
ooter | -0.110 |
ival | -0.106 |
uries | -0.105 |
rides | -0.105 |
Token | out |
Token ID | 503 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
Suz | +0.123 |
Liz | +0.117 |
Mia | +0.113 |
M | +0.113 |
boiling | +0.111 |
Neg logit contributions | |
aces | -0.161 |
ooter | -0.127 |
ance | -0.117 |
seek | -0.116 |
rides | -0.115 |
Token | wearing |
Token ID | 5762 |
Feature activation | +4.72e-03 |
Pos logit contributions | |
Suz | +0.233 |
Liz | +0.221 |
M | +0.207 |
boiling | +0.203 |
swollen | +0.202 |
Neg logit contributions | |
aces | -0.229 |
rides | -0.164 |
seek | -0.152 |
ives | -0.147 |
sweets | -0.146 |
Token | a |
Token ID | 257 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
Suz | +0.005 |
M | +0.005 |
Bee | +0.005 |
Andy | +0.005 |
Joe | +0.005 |
Neg logit contributions | |
aces | -0.013 |
ooter | -0.012 |
uries | -0.011 |
ests | -0.011 |
ival | -0.011 |
Token | beautiful |
Token ID | 4950 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
Suz | +0.043 |
Bee | +0.041 |
M | +0.041 |
Andy | +0.040 |
Joe | +0.040 |
Neg logit contributions | |
aces | -0.059 |
ooter | -0.048 |
uries | -0.046 |
ests | -0.045 |
ival | -0.045 |
Token | fur |
Token ID | 9230 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
Suz | +0.032 |
Bee | +0.032 |
M | +0.031 |
Andy | +0.030 |
Mia | +0.030 |
Neg logit contributions | |
aces | -0.041 |
ooter | -0.033 |
uries | -0.032 |
ests | -0.031 |
ival | -0.030 |
Token | coat |
Token ID | 13209 |
Feature activation | +4.62e-03 |
Pos logit contributions | |
M | +0.023 |
Bee | +0.023 |
Suz | +0.022 |
its | +0.021 |
Joe | +0.021 |
Neg logit contributions | |
aces | -0.074 |
uries | -0.067 |
ival | -0.064 |
ests | -0.064 |
ooter | -0.063 |
Token | Mom |
Token ID | 29252 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
Suz | +0.046 |
Bee | +0.045 |
M | +0.044 |
Andy | +0.043 |
Joe | +0.042 |
Neg logit contributions | |
aces | -0.076 |
ooter | -0.062 |
uries | -0.062 |
ests | -0.060 |
ival | -0.059 |
Token | heard |
Token ID | 2982 |
Feature activation | +9.90e-02 |
Pos logit contributions | |
Suz | +0.049 |
Bee | +0.048 |
M | +0.046 |
Andy | +0.045 |
Joe | +0.044 |
Neg logit contributions | |
aces | -0.093 |
ooter | -0.077 |
uries | -0.074 |
ival | -0.074 |
ests | -0.073 |
Token | Lily |
Token ID | 20037 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
Suz | +0.107 |
Bee | +0.103 |
M | +0.099 |
Andy | +0.095 |
Joe | +0.092 |
Neg logit contributions | |
aces | -0.267 |
ooter | -0.220 |
uries | -0.218 |
ival | -0.214 |
rides | -0.214 |
Token | and |
Token ID | 290 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
Suz | +0.025 |
Bee | +0.025 |
M | +0.024 |
Andy | +0.023 |
Joe | +0.023 |
Neg logit contributions | |
aces | -0.054 |
ooter | -0.045 |
uries | -0.045 |
ests | -0.044 |
ival | -0.043 |
Token | came |
Token ID | 1625 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
arter | +0.041 |
Suz | +0.040 |
oc | +0.040 |
boiling | +0.040 |
Farmer | +0.039 |
Neg logit contributions | |
aces | -0.050 |
rides | -0.040 |
cand | -0.039 |
sweets | -0.039 |
ooter | -0.037 |
Token | out |
Token ID | 503 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
apy | +0.114 |
crocod | +0.114 |
boiling | +0.114 |
Suz | +0.113 |
swarm | +0.112 |
Neg logit contributions | |
aces | -0.118 |
ooter | -0.102 |
uries | -0.093 |
rides | -0.092 |
seek | -0.092 |
Token | of |
Token ID | 286 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
Suz | +0.238 |
boiling | +0.229 |
apy | +0.222 |
Doug | +0.221 |
shallow | +0.220 |
Neg logit contributions | |
aces | -0.179 |
rides | -0.141 |
parties | -0.134 |
seek | -0.127 |
sweets | -0.124 |
Token | the |
Token ID | 262 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
Bee | +0.109 |
Suz | +0.107 |
ry | +0.096 |
Ali | +0.095 |
M | +0.094 |
Neg logit contributions | |
aces | -0.260 |
rides | -0.225 |
sweets | -0.224 |
parties | -0.222 |
magazines | -0.220 |
Token | house |
Token ID | 2156 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
Suz | +0.047 |
Bee | +0.046 |
M | +0.046 |
Mia | +0.045 |
Andy | +0.044 |
Neg logit contributions | |
aces | -0.081 |
uries | -0.066 |
ooter | -0.064 |
ests | -0.063 |
ival | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | +3.98e-02 |
Pos logit contributions | |
Suz | +0.048 |
Bee | +0.048 |
M | +0.046 |
Andy | +0.044 |
Joe | +0.043 |
Neg logit contributions | |
aces | -0.083 |
ooter | -0.068 |
uries | -0.067 |
seek | -0.064 |
rides | -0.063 |
Token | She |
Token ID | 1375 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
boiling | +0.079 |
Suz | +0.078 |
Bee | +0.078 |
roaring | +0.076 |
swarm | +0.076 |
Neg logit contributions | |
aces | -0.056 |
case | -0.045 |
ooter | -0.043 |
uries | -0.038 |
rides | -0.038 |
Token | help |
Token ID | 1037 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
Suz | +0.041 |
Bee | +0.040 |
M | +0.037 |
Ali | +0.037 |
Joe | +0.037 |
Neg logit contributions | |
aces | -0.046 |
sweets | -0.037 |
uries | -0.036 |
rides | -0.035 |
ooter | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
Suz | +0.042 |
Bee | +0.041 |
M | +0.039 |
Joe | +0.037 |
Andy | +0.037 |
Neg logit contributions | |
aces | -0.082 |
ooter | -0.067 |
uries | -0.067 |
ests | -0.064 |
seek | -0.063 |
Token | His |
Token ID | 2399 |
Feature activation | -2.10e-03 |
Pos logit contributions | |
Suz | +0.015 |
Bee | +0.015 |
boiling | +0.015 |
swarm | +0.014 |
buzzing | +0.014 |
Neg logit contributions | |
aces | -0.032 |
ooter | -0.027 |
uries | -0.026 |
seek | -0.026 |
rides | -0.025 |
Token | mom |
Token ID | 1995 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
aces | +0.006 |
uries | +0.005 |
ooter | +0.005 |
ests | +0.005 |
ival | +0.005 |
Neg logit contributions | |
Suz | -0.002 |
Bee | -0.002 |
M | -0.002 |
Andy | -0.002 |
Joe | -0.002 |
Token | came |
Token ID | 1625 |
Feature activation | +7.09e-02 |
Pos logit contributions | |
Suz | +0.080 |
Bee | +0.078 |
M | +0.076 |
Joe | +0.075 |
Andy | +0.073 |
Neg logit contributions | |
aces | -0.114 |
ooter | -0.094 |
rides | -0.090 |
ival | -0.090 |
oll | -0.089 |
Token | out |
Token ID | 503 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
Suz | +0.121 |
Bee | +0.114 |
crocod | +0.112 |
M | +0.111 |
swarm | +0.111 |
Neg logit contributions | |
aces | -0.135 |
ooter | -0.114 |
uries | -0.106 |
rides | -0.104 |
ests | -0.099 |
Token | and |
Token ID | 290 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
Suz | +0.255 |
Joe | +0.234 |
Ali | +0.232 |
Bee | +0.232 |
Andy | +0.229 |
Neg logit contributions | |
aces | -0.190 |
rides | -0.146 |
cand | -0.141 |
ooter | -0.137 |
oll | -0.137 |
Token | saw |
Token ID | 2497 |
Feature activation | +8.94e-02 |
Pos logit contributions | |
arter | +0.041 |
Suz | +0.035 |
swarm | +0.034 |
crocod | +0.034 |
Ali | +0.034 |
Neg logit contributions | |
cand | -0.035 |
mie | -0.035 |
sweets | -0.035 |
rides | -0.035 |
ival | -0.034 |
Token | what |
Token ID | 644 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
Bee | +0.116 |
Suz | +0.110 |
swarm | +0.109 |
Ali | +0.108 |
booming | +0.107 |
Neg logit contributions | |
aces | -0.199 |
rides | -0.172 |
sweets | -0.167 |
cand | -0.166 |
ests | -0.160 |
Token | happened |
Token ID | 3022 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
Bee | +0.074 |
Suz | +0.074 |
M | +0.070 |
Ali | +0.067 |
boiling | +0.065 |
Neg logit contributions | |
aces | -0.095 |
ests | -0.075 |
ival | -0.073 |
rides | -0.073 |
ooter | -0.073 |
Token | . |
Token ID | 13 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
Suz | +0.051 |
Bee | +0.050 |
M | +0.048 |
Andy | +0.047 |
Mia | +0.046 |
Neg logit contributions | |
aces | -0.092 |
ooter | -0.075 |
uries | -0.074 |
ests | -0.071 |
seek | -0.071 |
Token | loud |
Token ID | 7812 |
Feature activation | +6.54e-02 |
Pos logit contributions | |
Suz | +0.046 |
Andy | +0.043 |
Joe | +0.042 |
Maria | +0.041 |
Jan | +0.038 |
Neg logit contributions | |
aces | -0.057 |
medal | -0.051 |
ooter | -0.051 |
cand | -0.050 |
bracelet | -0.050 |
Token | noise |
Token ID | 7838 |
Feature activation | +7.78e-02 |
Pos logit contributions | |
Suz | +0.116 |
M | +0.107 |
Joe | +0.106 |
Andy | +0.104 |
Maria | +0.102 |
Neg logit contributions | |
aces | -0.130 |
ooter | -0.099 |
rides | -0.098 |
hell | -0.098 |
cand | -0.096 |
Token | and |
Token ID | 290 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
Suz | +0.128 |
M | +0.119 |
Bee | +0.119 |
Andy | +0.116 |
Joe | +0.115 |
Neg logit contributions | |
aces | -0.177 |
ooter | -0.135 |
uries | -0.135 |
rides | -0.132 |
oll | -0.127 |
Token | smoke |
Token ID | 7523 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
Suz | +0.032 |
Andy | +0.029 |
Joe | +0.028 |
Maria | +0.028 |
Bee | +0.027 |
Neg logit contributions | |
aces | -0.052 |
rides | -0.042 |
cand | -0.038 |
medals | -0.038 |
sweets | -0.038 |
Token | comes |
Token ID | 2058 |
Feature activation | +7.89e-02 |
Pos logit contributions | |
Suz | +0.103 |
Bee | +0.097 |
M | +0.097 |
Andy | +0.094 |
Joe | +0.092 |
Neg logit contributions | |
aces | -0.196 |
ooter | -0.157 |
uries | -0.155 |
ests | -0.152 |
ival | -0.149 |
Token | out |
Token ID | 503 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
Suz | +0.139 |
Bee | +0.128 |
M | +0.127 |
Maria | +0.126 |
Joe | +0.126 |
Neg logit contributions | |
aces | -0.160 |
ooter | -0.123 |
uries | -0.119 |
rides | -0.114 |
ode | -0.108 |
Token | of |
Token ID | 286 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
Suz | +0.254 |
Andy | +0.231 |
Doug | +0.226 |
Bee | +0.225 |
Joe | +0.222 |
Neg logit contributions | |
aces | -0.224 |
rides | -0.162 |
parties | -0.145 |
company | -0.144 |
cand | -0.143 |
Token | the |
Token ID | 262 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
Suz | +0.122 |
Bee | +0.113 |
Ali | +0.104 |
M | +0.101 |
Andy | +0.100 |
Neg logit contributions | |
aces | -0.271 |
rides | -0.224 |
bons | -0.220 |
sweets | -0.219 |
magazines | -0.214 |
Token | pot |
Token ID | 1787 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
M | +0.046 |
Bee | +0.046 |
Suz | +0.045 |
Mia | +0.044 |
Joe | +0.043 |
Neg logit contributions | |
aces | -0.079 |
uries | -0.065 |
ooter | -0.064 |
ests | -0.062 |
ival | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
Suz | +0.054 |
Bee | +0.053 |
M | +0.052 |
Andy | +0.050 |
Joe | +0.049 |
Neg logit contributions | |
aces | -0.120 |
ooter | -0.100 |
uries | -0.099 |
ests | -0.097 |
ival | -0.095 |
Token | Tom |
Token ID | 4186 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
Suz | +0.037 |
Bee | +0.035 |
Andy | +0.034 |
boiling | +0.033 |
M | +0.033 |
Neg logit contributions | |
aces | -0.062 |
ooter | -0.048 |
ests | -0.048 |
uries | -0.048 |
ival | -0.047 |
Token | his |
Token ID | 465 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
Suz | +0.050 |
Bee | +0.044 |
M | +0.040 |
Maria | +0.039 |
Joe | +0.039 |
Neg logit contributions | |
aces | -0.130 |
rides | -0.104 |
sweets | -0.103 |
uries | -0.102 |
ooter | -0.102 |
Token | hand |
Token ID | 1021 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
aces | +0.101 |
uries | +0.082 |
ival | +0.082 |
ooter | +0.081 |
ests | +0.080 |
Neg logit contributions | |
Bee | -0.066 |
M | -0.065 |
Suz | -0.065 |
Andy | -0.062 |
Mia | -0.062 |
Token | and |
Token ID | 290 |
Feature activation | +8.06e-03 |
Pos logit contributions | |
M | +0.039 |
Suz | +0.039 |
Bee | +0.037 |
Joe | +0.036 |
Mia | +0.036 |
Neg logit contributions | |
aces | -0.116 |
uries | -0.100 |
ival | -0.099 |
ooter | -0.099 |
ests | -0.098 |
Token | smoke |
Token ID | 7523 |
Feature activation | +6.96e-02 |
Pos logit contributions | |
Suz | +0.011 |
Bee | +0.010 |
M | +0.010 |
Andy | +0.010 |
Joe | +0.010 |
Neg logit contributions | |
aces | -0.020 |
ooter | -0.016 |
rides | -0.016 |
cand | -0.016 |
oll | -0.016 |
Token | came |
Token ID | 1625 |
Feature activation | +7.73e-02 |
Pos logit contributions | |
Suz | +0.076 |
Bee | +0.075 |
M | +0.075 |
Mia | +0.071 |
Joe | +0.071 |
Neg logit contributions | |
aces | -0.194 |
ooter | -0.165 |
uries | -0.164 |
ests | -0.159 |
ival | -0.159 |
Token | out |
Token ID | 503 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
Suz | +0.132 |
M | +0.125 |
Bee | +0.124 |
Mia | +0.124 |
Joe | +0.124 |
Neg logit contributions | |
aces | -0.163 |
ooter | -0.129 |
uries | -0.119 |
ests | -0.114 |
ode | -0.113 |
Token | of |
Token ID | 286 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
Suz | +0.239 |
Bee | +0.226 |
Ali | +0.219 |
Andy | +0.215 |
Joe | +0.214 |
Neg logit contributions | |
aces | -0.242 |
rides | -0.174 |
ooter | -0.172 |
oll | -0.166 |
sweets | -0.165 |
Token | the |
Token ID | 262 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
Suz | +0.119 |
Bee | +0.116 |
Ali | +0.112 |
Maria | +0.100 |
M | +0.099 |
Neg logit contributions | |
aces | -0.270 |
sweets | -0.226 |
rides | -0.222 |
cand | -0.218 |
bons | -0.217 |
Token | drill |
Token ID | 16007 |
Feature activation | +5.53e-02 |
Pos logit contributions | |
Suz | +0.053 |
Bee | +0.049 |
M | +0.048 |
Joe | +0.048 |
Andy | +0.047 |
Neg logit contributions | |
aces | -0.073 |
ooter | -0.060 |
uries | -0.056 |
ests | -0.056 |
rides | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
Suz | +0.055 |
Bee | +0.055 |
M | +0.054 |
Andy | +0.052 |
Joe | +0.052 |
Neg logit contributions | |
aces | -0.157 |
uries | -0.133 |
ooter | -0.132 |
ests | -0.132 |
ival | -0.130 |
Token | He |
Token ID | 679 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
buzzing | +0.038 |
boiling | +0.038 |
Suz | +0.037 |
swarm | +0.037 |
burning | +0.037 |
Neg logit contributions | |
aces | -0.042 |
ooter | -0.032 |
ests | -0.031 |
oll | -0.029 |
uries | -0.028 |
Token | black |
Token ID | 2042 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
Suz | +0.058 |
Joe | +0.053 |
Andy | +0.052 |
Bee | +0.052 |
Maria | +0.050 |
Neg logit contributions | |
aces | -0.068 |
ival | -0.063 |
sweets | -0.062 |
cand | -0.062 |
ooter | -0.060 |
Token | mess |
Token ID | 2085 |
Feature activation | +4.44e-02 |
Pos logit contributions | |
Suz | +0.029 |
Bee | +0.028 |
M | +0.028 |
Andy | +0.027 |
Joe | +0.027 |
Neg logit contributions | |
aces | -0.040 |
ooter | -0.032 |
uries | -0.032 |
ests | -0.031 |
ival | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
Suz | +0.059 |
M | +0.058 |
Bee | +0.057 |
Mia | +0.055 |
Andy | +0.055 |
Neg logit contributions | |
aces | -0.114 |
ooter | -0.095 |
uries | -0.094 |
ests | -0.091 |
ival | -0.091 |
Token | Smoke |
Token ID | 25416 |
Feature activation | +6.42e-02 |
Pos logit contributions | |
Suz | +0.020 |
Andy | +0.019 |
Bee | +0.018 |
Joe | +0.018 |
Maria | +0.017 |
Neg logit contributions | |
aces | -0.033 |
ests | -0.026 |
oll | -0.025 |
ooter | -0.025 |
uries | -0.025 |
Token | came |
Token ID | 1625 |
Feature activation | +7.52e-02 |
Pos logit contributions | |
Suz | +0.082 |
Bee | +0.078 |
M | +0.077 |
Andy | +0.075 |
Joe | +0.073 |
Neg logit contributions | |
aces | -0.169 |
ooter | -0.136 |
uries | -0.134 |
ests | -0.133 |
ival | -0.130 |
Token | out |
Token ID | 503 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
Suz | +0.118 |
Bee | +0.114 |
M | +0.112 |
Andy | +0.111 |
Joe | +0.110 |
Neg logit contributions | |
aces | -0.171 |
ooter | -0.136 |
uries | -0.131 |
ests | -0.126 |
oll | -0.125 |
Token | . |
Token ID | 13 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
Suz | +0.237 |
Andy | +0.221 |
Doug | +0.217 |
Bee | +0.216 |
Ali | +0.216 |
Neg logit contributions | |
aces | -0.230 |
oll | -0.162 |
cand | -0.162 |
rides | -0.159 |
sweets | -0.156 |
Token | The |
Token ID | 383 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
Suz | +0.039 |
Andy | +0.036 |
Bee | +0.034 |
Joe | +0.034 |
Maria | +0.033 |
Neg logit contributions | |
aces | -0.067 |
ests | -0.052 |
uries | -0.051 |
oll | -0.051 |
ooter | -0.050 |
Token | fire |
Token ID | 2046 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
Suz | +0.061 |
Bee | +0.059 |
M | +0.058 |
Andy | +0.057 |
Joe | +0.056 |
Neg logit contributions | |
aces | -0.100 |
ooter | -0.081 |
uries | -0.080 |
ests | -0.078 |
ival | -0.077 |
Token | alarm |
Token ID | 10436 |
Feature activation | +5.68e-02 |
Pos logit contributions | |
Suz | +0.061 |
Bee | +0.057 |
M | +0.057 |
Andy | +0.054 |
Joe | +0.053 |
Neg logit contributions | |
aces | -0.124 |
ooter | -0.101 |
ests | -0.099 |
uries | -0.098 |
ival | -0.095 |
Token | be |
Token ID | 307 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
Suz | +0.068 |
Bee | +0.066 |
M | +0.066 |
Andy | +0.063 |
Mia | +0.062 |
Neg logit contributions | |
aces | -0.154 |
ooter | -0.128 |
uries | -0.127 |
ests | -0.124 |
ival | -0.122 |
Token |
|
Token ID | 198 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
Suz | +0.031 |
Bee | +0.030 |
boiling | +0.029 |
Andy | +0.028 |
M | +0.028 |
Neg logit contributions | |
aces | -0.053 |
ooter | -0.043 |
uries | -0.042 |
ival | -0.040 |
ests | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
Suz | +0.045 |
Bee | +0.044 |
boiling | +0.042 |
M | +0.042 |
crocod | +0.042 |
Neg logit contributions | |
aces | -0.072 |
ooter | -0.061 |
ival | -0.059 |
uries | -0.058 |
ests | -0.058 |
Token | Her |
Token ID | 9360 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
Suz | +0.055 |
Bee | +0.053 |
M | +0.053 |
Joe | +0.050 |
Andy | +0.050 |
Neg logit contributions | |
aces | -0.081 |
ooter | -0.067 |
uries | -0.066 |
ival | -0.064 |
ests | -0.063 |
Token | mom |
Token ID | 1995 |
Feature activation | +4.67e-02 |
Pos logit contributions | |
Suz | +0.011 |
M | +0.011 |
Bee | +0.011 |
Andy | +0.011 |
Mia | +0.011 |
Neg logit contributions | |
aces | -0.031 |
uries | -0.026 |
ooter | -0.026 |
ests | -0.026 |
ival | -0.025 |
Token | came |
Token ID | 1625 |
Feature activation | +7.65e-02 |
Pos logit contributions | |
Suz | +0.065 |
Bee | +0.064 |
M | +0.060 |
Andy | +0.059 |
Joe | +0.058 |
Neg logit contributions | |
aces | -0.109 |
ooter | -0.091 |
ival | -0.087 |
rides | -0.087 |
oll | -0.085 |
Token | over |
Token ID | 625 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
Suz | +0.135 |
crocod | +0.131 |
Bee | +0.131 |
Joe | +0.125 |
Andy | +0.124 |
Neg logit contributions | |
aces | -0.138 |
ooter | -0.114 |
uries | -0.108 |
rides | -0.104 |
parties | -0.099 |
Token | and |
Token ID | 290 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
Suz | +0.245 |
Bee | +0.240 |
Andy | +0.226 |
Ali | +0.222 |
crocod | +0.219 |
Neg logit contributions | |
aces | -0.224 |
sweets | -0.180 |
rides | -0.180 |
cand | -0.173 |
parties | -0.173 |
Token | asked |
Token ID | 1965 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
arter | +0.067 |
crocod | +0.058 |
Suz | +0.057 |
Bee | +0.056 |
swarm | +0.055 |
Neg logit contributions | |
mie | -0.059 |
aces | -0.058 |
ival | -0.057 |
cand | -0.057 |
sweets | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | +5.90e-02 |
Pos logit contributions | |
Suz | +0.038 |
Bee | +0.038 |
Andy | +0.036 |
Joe | +0.034 |
boiling | +0.034 |
Neg logit contributions | |
aces | -0.077 |
uries | -0.062 |
sweets | -0.061 |
ooter | -0.061 |
cand | -0.061 |
Token | " |
Token ID | 366 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
Suz | +0.078 |
Ali | +0.072 |
crocod | +0.072 |
Bee | +0.071 |
Andy | +0.069 |
Neg logit contributions | |
aces | -0.121 |
ooter | -0.103 |
uries | -0.100 |
sweets | -0.099 |
ival | -0.097 |
Token | What |
Token ID | 2061 |
Feature activation | -9.79e-03 |
Pos logit contributions | |
Suz | +0.025 |
M | +0.024 |
Bee | +0.023 |
Joe | +0.023 |
Andy | +0.023 |
Neg logit contributions | |
aces | -0.039 |
uries | -0.032 |
ooter | -0.032 |
ival | -0.032 |
ests | -0.031 |
Token | opens |
Token ID | 9808 |
Feature activation | +8.31e-02 |
Pos logit contributions | |
Suz | +0.112 |
Bee | +0.112 |
M | +0.108 |
Andy | +0.105 |
Joe | +0.103 |
Neg logit contributions | |
aces | -0.216 |
ooter | -0.176 |
uries | -0.171 |
ival | -0.169 |
ests | -0.166 |
Token | and |
Token ID | 290 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
Suz | +0.098 |
Bee | +0.094 |
M | +0.089 |
Andy | +0.087 |
Joe | +0.084 |
Neg logit contributions | |
aces | -0.226 |
uries | -0.183 |
ooter | -0.181 |
ival | -0.177 |
rides | -0.177 |
Token | a |
Token ID | 257 |
Feature activation | +4.73e-02 |
Pos logit contributions | |
Suz | +0.048 |
Bee | +0.047 |
Andy | +0.044 |
M | +0.043 |
Joe | +0.042 |
Neg logit contributions | |
aces | -0.105 |
ooter | -0.085 |
rides | -0.084 |
uries | -0.084 |
ival | -0.084 |
Token | man |
Token ID | 582 |
Feature activation | +5.09e-02 |
Pos logit contributions | |
Suz | +0.072 |
Bee | +0.068 |
M | +0.067 |
Andy | +0.066 |
Joe | +0.066 |
Neg logit contributions | |
aces | -0.110 |
ooter | -0.092 |
ival | -0.091 |
uries | -0.090 |
sweets | -0.086 |
Token | comes |
Token ID | 2058 |
Feature activation | +7.41e-02 |
Pos logit contributions | |
Suz | +0.066 |
Bee | +0.065 |
M | +0.063 |
Andy | +0.060 |
Mia | +0.059 |
Neg logit contributions | |
aces | -0.130 |
ooter | -0.108 |
uries | -0.105 |
ival | -0.105 |
rides | -0.104 |
Token | out |
Token ID | 503 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
Suz | +0.109 |
Bee | +0.108 |
M | +0.102 |
Mia | +0.099 |
Andy | +0.098 |
Neg logit contributions | |
aces | -0.167 |
uries | -0.136 |
ooter | -0.135 |
ival | -0.127 |
rides | -0.126 |
Token | . |
Token ID | 13 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
Suz | +0.213 |
Bee | +0.203 |
Andy | +0.191 |
M | +0.190 |
Liz | +0.189 |
Neg logit contributions | |
aces | -0.277 |
rides | -0.215 |
sweets | -0.202 |
uries | -0.201 |
ooter | -0.200 |
Token | He |
Token ID | 679 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
Suz | +0.057 |
Bee | +0.055 |
Andy | +0.052 |
M | +0.051 |
boiling | +0.051 |
Neg logit contributions | |
aces | -0.092 |
ooter | -0.076 |
uries | -0.072 |
ival | -0.072 |
rides | -0.071 |
Token | is |
Token ID | 318 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
Suz | +0.041 |
Bee | +0.038 |
M | +0.037 |
Andy | +0.036 |
Joe | +0.035 |
Neg logit contributions | |
aces | -0.070 |
rides | -0.057 |
ooter | -0.057 |
ival | -0.055 |
uries | -0.055 |
Token | wearing |
Token ID | 5762 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
Suz | +0.022 |
Bee | +0.021 |
M | +0.020 |
Andy | +0.019 |
Joe | +0.019 |
Neg logit contributions | |
aces | -0.037 |
uries | -0.030 |
ooter | -0.030 |
oll | -0.029 |
rides | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
aces | +0.036 |
ooter | +0.032 |
uries | +0.031 |
ests | +0.030 |
seek | +0.029 |
Neg logit contributions | |
M | -0.012 |
Suz | -0.011 |
Mia | -0.011 |
Andy | -0.011 |
Joe | -0.011 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
aces | +0.003 |
ooter | +0.002 |
uries | +0.002 |
ests | +0.002 |
ival | +0.002 |
Neg logit contributions | |
Suz | -0.001 |
M | -0.001 |
Bee | -0.001 |
Joe | -0.001 |
Mia | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +4.99e-02 |
Pos logit contributions | |
Suz | +0.054 |
Bee | +0.052 |
M | +0.050 |
Andy | +0.048 |
Mia | +0.047 |
Neg logit contributions | |
aces | -0.148 |
ooter | -0.123 |
uries | -0.122 |
ival | -0.120 |
ests | -0.120 |
Token | giant |
Token ID | 6175 |
Feature activation | +6.70e-02 |
Pos logit contributions | |
Suz | +0.072 |
M | +0.066 |
Liz | +0.065 |
Andy | +0.065 |
Mia | +0.064 |
Neg logit contributions | |
aces | -0.112 |
ival | -0.102 |
ooter | -0.097 |
medal | -0.096 |
bracelet | -0.093 |
Token | fish |
Token ID | 5916 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
Suz | +0.086 |
Bee | +0.082 |
M | +0.082 |
Andy | +0.078 |
Mia | +0.078 |
Neg logit contributions | |
aces | -0.174 |
ooter | -0.144 |
uries | -0.141 |
ival | -0.139 |
ests | -0.138 |
Token | came |
Token ID | 1625 |
Feature activation | +7.42e-02 |
Pos logit contributions | |
Suz | +0.032 |
M | +0.030 |
Bee | +0.030 |
Liz | +0.029 |
Mia | +0.029 |
Neg logit contributions | |
aces | -0.054 |
ooter | -0.045 |
ival | -0.043 |
rides | -0.042 |
uries | -0.042 |
Token | out |
Token ID | 503 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
Suz | +0.118 |
Liz | +0.116 |
Mia | +0.111 |
M | +0.111 |
Ali | +0.110 |
Neg logit contributions | |
aces | -0.158 |
ooter | -0.125 |
uries | -0.116 |
ance | -0.114 |
ode | -0.113 |
Token | of |
Token ID | 286 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
Liz | +0.231 |
Suz | +0.225 |
Ali | +0.217 |
Bee | +0.207 |
Sp | +0.207 |
Neg logit contributions | |
aces | -0.216 |
rides | -0.151 |
sweets | -0.147 |
tie | -0.143 |
medals | -0.142 |
Token | the |
Token ID | 262 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
Suz | +0.116 |
Liz | +0.114 |
Ali | +0.113 |
Bee | +0.110 |
M | +0.100 |
Neg logit contributions | |
aces | -0.255 |
sweets | -0.224 |
rides | -0.211 |
medals | -0.209 |
cand | -0.208 |
Token | reef |
Token ID | 25088 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
M | +0.057 |
Bee | +0.056 |
Suz | +0.056 |
Joe | +0.054 |
Andy | +0.053 |
Neg logit contributions | |
aces | -0.101 |
uries | -0.081 |
ooter | -0.080 |
ests | -0.079 |
seek | -0.078 |
Token | . |
Token ID | 13 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
Suz | +0.037 |
Bee | +0.035 |
M | +0.034 |
Andy | +0.033 |
Mia | +0.033 |
Neg logit contributions | |
aces | -0.072 |
ooter | -0.059 |
uries | -0.058 |
ival | -0.057 |
ests | -0.056 |
Token | It |
Token ID | 632 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
Suz | +0.035 |
Bee | +0.033 |
M | +0.032 |
Andy | +0.032 |
Mia | +0.030 |
Neg logit contributions | |
aces | -0.072 |
ooter | -0.060 |
uries | -0.059 |
ival | -0.058 |
ests | -0.057 |
Token | giant |
Token ID | 6175 |
Feature activation | +7.45e-02 |
Pos logit contributions | |
Suz | +0.079 |
Joe | +0.072 |
M | +0.072 |
Andy | +0.071 |
Bee | +0.071 |
Neg logit contributions | |
aces | -0.132 |
ooter | -0.117 |
ival | -0.116 |
bracelet | -0.112 |
medal | -0.111 |
Token | , |
Token ID | 11 |
Feature activation | +4.39e-02 |
Pos logit contributions | |
Suz | +0.094 |
Bee | +0.090 |
M | +0.089 |
Andy | +0.085 |
Joe | +0.084 |
Neg logit contributions | |
aces | -0.197 |
ooter | -0.163 |
uries | -0.159 |
ival | -0.157 |
ests | -0.156 |
Token | scary |
Token ID | 14343 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
Suz | +0.054 |
Bee | +0.052 |
M | +0.051 |
Andy | +0.048 |
Joe | +0.046 |
Neg logit contributions | |
aces | -0.111 |
ooter | -0.090 |
rides | -0.089 |
sweets | -0.088 |
ival | -0.087 |
Token | bear |
Token ID | 6842 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
Suz | +0.074 |
M | +0.070 |
Bee | +0.069 |
Andy | +0.066 |
Mia | +0.065 |
Neg logit contributions | |
aces | -0.113 |
ooter | -0.092 |
rides | -0.087 |
ests | -0.086 |
cand | -0.085 |
Token | came |
Token ID | 1625 |
Feature activation | +7.88e-02 |
Pos logit contributions | |
Suz | +0.060 |
M | +0.056 |
Bee | +0.056 |
Andy | +0.053 |
Mia | +0.053 |
Neg logit contributions | |
aces | -0.117 |
ooter | -0.097 |
uries | -0.094 |
ival | -0.093 |
rides | -0.092 |
Token | out |
Token ID | 503 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
Suz | +0.122 |
M | +0.114 |
Bee | +0.113 |
boiling | +0.113 |
Farmer | +0.112 |
Neg logit contributions | |
aces | -0.166 |
ooter | -0.133 |
uries | -0.122 |
rides | -0.121 |
ance | -0.121 |
Token | from |
Token ID | 422 |
Feature activation | +7.97e-02 |
Pos logit contributions | |
Suz | +0.238 |
Bee | +0.217 |
Andy | +0.215 |
Liz | +0.212 |
swollen | +0.211 |
Neg logit contributions | |
aces | -0.211 |
rides | -0.160 |
parties | -0.150 |
medals | -0.143 |
sweets | -0.141 |
Token | the |
Token ID | 262 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
Suz | +0.106 |
Bee | +0.101 |
M | +0.100 |
Ali | +0.089 |
Liz | +0.088 |
Neg logit contributions | |
aces | -0.184 |
rides | -0.156 |
sweets | -0.144 |
uries | -0.143 |
magazines | -0.142 |
Token | forest |
Token ID | 8222 |
Feature activation | +5.07e-02 |
Pos logit contributions | |
Suz | +0.055 |
Bee | +0.053 |
M | +0.053 |
Andy | +0.051 |
Joe | +0.051 |
Neg logit contributions | |
aces | -0.080 |
ooter | -0.065 |
uries | -0.064 |
ests | -0.062 |
ival | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
Suz | +0.076 |
Bee | +0.072 |
M | +0.071 |
Andy | +0.068 |
Liz | +0.066 |
Neg logit contributions | |
aces | -0.121 |
ooter | -0.099 |
uries | -0.097 |
seek | -0.094 |
rides | -0.094 |
Token | Peggy |
Token ID | 40910 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
Suz | +0.042 |
Bee | +0.040 |
Andy | +0.038 |
M | +0.037 |
boiling | +0.036 |
Neg logit contributions | |
aces | -0.081 |
ooter | -0.067 |
uries | -0.066 |
ival | -0.065 |
ests | -0.064 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | +5.27e-02 |
Pos logit contributions | |
Suz | +0.036 |
Bee | +0.035 |
M | +0.034 |
Andy | +0.033 |
Joe | +0.033 |
Neg logit contributions | |
aces | -0.061 |
ooter | -0.050 |
uries | -0.050 |
ests | -0.048 |
ival | -0.048 |
Token | , |
Token ID | 11 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
Suz | +0.058 |
Bee | +0.056 |
M | +0.054 |
Andy | +0.052 |
Joe | +0.051 |
Neg logit contributions | |
aces | -0.142 |
ooter | -0.116 |
ival | -0.114 |
uries | -0.114 |
ests | -0.112 |
Token | her |
Token ID | 607 |
Feature activation | -3.61e-03 |
Pos logit contributions | |
Suz | +0.030 |
Bee | +0.029 |
M | +0.028 |
Andy | +0.027 |
Joe | +0.027 |
Neg logit contributions | |
aces | -0.085 |
ooter | -0.071 |
uries | -0.070 |
ival | -0.069 |
ests | -0.069 |
Token | mom |
Token ID | 1995 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
aces | +0.010 |
ooter | +0.008 |
uries | +0.008 |
ests | +0.008 |
ival | +0.008 |
Neg logit contributions | |
Suz | -0.004 |
Bee | -0.004 |
M | -0.004 |
Andy | -0.004 |
Mia | -0.004 |
Token | yelled |
Token ID | 22760 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
Suz | +0.058 |
Bee | +0.057 |
M | +0.054 |
its | +0.054 |
Andy | +0.053 |
Neg logit contributions | |
aces | -0.110 |
ooter | -0.091 |
oll | -0.088 |
ival | -0.088 |
uries | -0.087 |
Token | out |
Token ID | 503 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
Suz | +0.035 |
Bee | +0.034 |
Andy | +0.033 |
M | +0.032 |
Joe | +0.032 |
Neg logit contributions | |
aces | -0.064 |
ooter | -0.052 |
uries | -0.052 |
ival | -0.049 |
oll | -0.049 |
Token | and |
Token ID | 290 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
Suz | +0.206 |
shallow | +0.194 |
boiling | +0.188 |
Miles | +0.184 |
swollen | +0.181 |
Neg logit contributions | |
aces | -0.233 |
sweets | -0.184 |
oll | -0.178 |
parties | -0.176 |
novels | -0.174 |
Token | warned |
Token ID | 7728 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
arter | +0.037 |
Bee | +0.036 |
Suz | +0.035 |
oc | +0.034 |
crocod | +0.034 |
Neg logit contributions | |
aces | -0.050 |
ival | -0.043 |
sweets | -0.041 |
cand | -0.041 |
ooter | -0.040 |
Token | her |
Token ID | 607 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
Suz | +0.031 |
Bee | +0.030 |
M | +0.029 |
Andy | +0.028 |
Joe | +0.028 |
Neg logit contributions | |
aces | -0.072 |
ooter | -0.060 |
uries | -0.059 |
ests | -0.057 |
ival | -0.057 |
Token | not |
Token ID | 407 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
aces | +0.035 |
ests | +0.029 |
uries | +0.029 |
ooter | +0.029 |
ival | +0.028 |
Neg logit contributions | |
Suz | -0.012 |
M | -0.012 |
Bee | -0.012 |
Mia | -0.012 |
Joe | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
Suz | +0.052 |
Bee | +0.050 |
M | +0.050 |
Andy | +0.047 |
Joe | +0.047 |
Neg logit contributions | |
aces | -0.123 |
ooter | -0.103 |
uries | -0.102 |
ests | -0.100 |
ival | -0.099 |
Token | late |
Token ID | 2739 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
Suz | +0.060 |
Bee | +0.058 |
M | +0.056 |
Maria | +0.053 |
Andy | +0.053 |
Neg logit contributions | |
aces | -0.099 |
ooter | -0.084 |
ival | -0.081 |
case | -0.080 |
rides | -0.079 |
Token | . |
Token ID | 13 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
Suz | +0.033 |
M | +0.032 |
Bee | +0.031 |
Joe | +0.031 |
Andy | +0.031 |
Neg logit contributions | |
aces | -0.094 |
ooter | -0.080 |
uries | -0.079 |
ests | -0.078 |
ival | -0.077 |
Token | A |
Token ID | 317 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
M | +0.015 |
Suz | +0.015 |
Bee | +0.015 |
Mia | +0.015 |
Joe | +0.014 |
Neg logit contributions | |
aces | -0.039 |
ooter | -0.032 |
uries | -0.032 |
ests | -0.032 |
ival | -0.031 |
Token | man |
Token ID | 582 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
Suz | +0.067 |
Bee | +0.065 |
M | +0.064 |
Andy | +0.062 |
Joe | +0.062 |
Neg logit contributions | |
aces | -0.110 |
ooter | -0.094 |
ival | -0.091 |
uries | -0.090 |
ests | -0.088 |
Token | came |
Token ID | 1625 |
Feature activation | +7.28e-02 |
Pos logit contributions | |
Suz | +0.062 |
Bee | +0.060 |
M | +0.059 |
Andy | +0.056 |
Mia | +0.055 |
Neg logit contributions | |
aces | -0.144 |
ooter | -0.121 |
uries | -0.119 |
ival | -0.116 |
ests | -0.115 |
Token | out |
Token ID | 503 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
Suz | +0.105 |
Bee | +0.101 |
M | +0.099 |
Mia | +0.095 |
Andy | +0.095 |
Neg logit contributions | |
aces | -0.176 |
ooter | -0.147 |
uries | -0.141 |
ests | -0.136 |
ival | -0.135 |
Token | of |
Token ID | 286 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
Suz | +0.223 |
Bee | +0.208 |
Andy | +0.199 |
M | +0.197 |
Ali | +0.195 |
Neg logit contributions | |
aces | -0.251 |
rides | -0.193 |
ooter | -0.186 |
sweets | -0.182 |
oll | -0.180 |
Token | the |
Token ID | 262 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
Suz | +0.101 |
Bee | +0.100 |
M | +0.086 |
Ali | +0.086 |
Andy | +0.082 |
Neg logit contributions | |
aces | -0.291 |
sweets | -0.249 |
rides | -0.246 |
cand | -0.242 |
magazines | -0.241 |
Token | house |
Token ID | 2156 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
M | +0.052 |
Mia | +0.050 |
Suz | +0.050 |
Bee | +0.049 |
boiling | +0.048 |
Neg logit contributions | |
aces | -0.085 |
uries | -0.067 |
oll | -0.064 |
seek | -0.064 |
ests | -0.063 |
Token | and |
Token ID | 290 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
Suz | +0.047 |
Bee | +0.046 |
M | +0.045 |
Andy | +0.043 |
Joe | +0.042 |
Neg logit contributions | |
aces | -0.101 |
ooter | -0.084 |
uries | -0.083 |
ests | -0.080 |
ival | -0.080 |
Token | saw |
Token ID | 2497 |
Feature activation | +8.58e-02 |
Pos logit contributions | |
Suz | +0.028 |
Bee | +0.028 |
M | +0.026 |
Andy | +0.025 |
Joe | +0.025 |
Neg logit contributions | |
aces | -0.052 |
ooter | -0.043 |
uries | -0.043 |
rides | -0.042 |
ival | -0.042 |
Token | very |
Token ID | 845 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
Bee | +0.054 |
Suz | +0.053 |
M | +0.051 |
Andy | +0.050 |
Ali | +0.050 |
Neg logit contributions | |
aces | -0.096 |
ooter | -0.079 |
uries | -0.076 |
ival | -0.074 |
rides | -0.074 |
Token | angry |
Token ID | 7954 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
Bee | +0.046 |
Suz | +0.045 |
Andy | +0.043 |
Ali | +0.041 |
Joe | +0.041 |
Neg logit contributions | |
aces | -0.100 |
ooter | -0.084 |
oll | -0.081 |
rides | -0.080 |
cand | -0.079 |
Token | . |
Token ID | 13 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
Suz | +0.056 |
Bee | +0.055 |
M | +0.054 |
Andy | +0.052 |
Joe | +0.051 |
Neg logit contributions | |
aces | -0.126 |
ooter | -0.105 |
uries | -0.104 |
ests | -0.101 |
ival | -0.100 |
Token | He |
Token ID | 679 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
Suz | +0.027 |
Bee | +0.027 |
M | +0.025 |
Andy | +0.025 |
boiling | +0.024 |
Neg logit contributions | |
aces | -0.055 |
ooter | -0.045 |
uries | -0.044 |
ests | -0.043 |
ival | -0.042 |
Token | came |
Token ID | 1625 |
Feature activation | +6.12e-02 |
Pos logit contributions | |
Suz | +0.035 |
Bee | +0.034 |
M | +0.032 |
Maria | +0.031 |
Andy | +0.031 |
Neg logit contributions | |
aces | -0.054 |
ooter | -0.044 |
rides | -0.043 |
uries | -0.042 |
ival | -0.040 |
Token | out |
Token ID | 503 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
Suz | +0.105 |
Bee | +0.105 |
boiling | +0.102 |
M | +0.100 |
swarm | +0.100 |
Neg logit contributions | |
aces | -0.117 |
ooter | -0.101 |
uries | -0.089 |
ests | -0.085 |
rides | -0.084 |
Token | and |
Token ID | 290 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
Suz | +0.237 |
Bee | +0.215 |
Ali | +0.213 |
M | +0.213 |
Andy | +0.212 |
Neg logit contributions | |
aces | -0.209 |
rides | -0.162 |
ooter | -0.149 |
cand | -0.148 |
sweets | -0.143 |
Token | yelled |
Token ID | 22760 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
Suz | +0.035 |
Bee | +0.034 |
arter | +0.033 |
M | +0.031 |
Farmer | +0.031 |
Neg logit contributions | |
aces | -0.044 |
rides | -0.043 |
ooter | -0.039 |
sweets | -0.039 |
cand | -0.038 |
Token | at |
Token ID | 379 |
Feature activation | +6.26e-02 |
Pos logit contributions | |
Suz | +0.029 |
Bee | +0.028 |
Andy | +0.027 |
M | +0.026 |
Maria | +0.026 |
Neg logit contributions | |
aces | -0.050 |
ooter | -0.040 |
uries | -0.039 |
oll | -0.038 |
ival | -0.037 |
Token | Bob |
Token ID | 5811 |
Feature activation | +3.49e-02 |
Pos logit contributions | |
Suz | +0.061 |
Bee | +0.060 |
M | +0.056 |
Andy | +0.052 |
Ali | +0.051 |
Neg logit contributions | |
aces | -0.176 |
ooter | -0.146 |
uries | -0.145 |
ests | -0.143 |
rides | -0.141 |
Token | . |
Token ID | 13 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
Suz | +0.045 |
Bee | +0.043 |
M | +0.042 |
Andy | +0.040 |
Mia | +0.039 |
Neg logit contributions | |
aces | -0.092 |
ooter | -0.076 |
uries | -0.075 |
ests | -0.072 |
ival | -0.071 |
Token | to |
Token ID | 284 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
Suz | +0.026 |
Bee | +0.025 |
M | +0.024 |
Andy | +0.023 |
Joe | +0.023 |
Neg logit contributions | |
aces | -0.044 |
ooter | -0.037 |
uries | -0.035 |
sweets | -0.035 |
seek | -0.034 |
Token | scream |
Token ID | 8196 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
Suz | +0.018 |
Bee | +0.018 |
M | +0.017 |
Joe | +0.017 |
Mia | +0.017 |
Neg logit contributions | |
aces | -0.027 |
ooter | -0.022 |
uries | -0.022 |
ests | -0.020 |
ival | -0.020 |
Token | but |
Token ID | 475 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
Suz | +0.055 |
Bee | +0.052 |
M | +0.050 |
Joe | +0.049 |
Andy | +0.049 |
Neg logit contributions | |
aces | -0.112 |
ooter | -0.091 |
uries | -0.090 |
ests | -0.086 |
oll | -0.086 |
Token | nothing |
Token ID | 2147 |
Feature activation | +5.52e-02 |
Pos logit contributions | |
Suz | +0.016 |
Bee | +0.015 |
M | +0.014 |
Andy | +0.014 |
Joe | +0.014 |
Neg logit contributions | |
aces | -0.035 |
ooter | -0.028 |
uries | -0.028 |
oll | -0.027 |
sweets | -0.026 |
Token | came |
Token ID | 1625 |
Feature activation | +6.77e-02 |
Pos logit contributions | |
Suz | +0.078 |
Bee | +0.077 |
M | +0.076 |
Andy | +0.073 |
Joe | +0.073 |
Neg logit contributions | |
aces | -0.138 |
ooter | -0.111 |
uries | -0.109 |
ests | -0.107 |
ival | -0.106 |
Token | out |
Token ID | 503 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
Suz | +0.108 |
Bee | +0.105 |
M | +0.103 |
Mia | +0.100 |
Joe | +0.099 |
Neg logit contributions | |
aces | -0.150 |
ooter | -0.122 |
uries | -0.116 |
ests | -0.108 |
seek | -0.108 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
Suz | +0.227 |
Bee | +0.221 |
Andy | +0.211 |
Ali | +0.206 |
M | +0.206 |
Neg logit contributions | |
aces | -0.252 |
ooter | -0.175 |
uries | -0.174 |
oll | -0.173 |
sweets | -0.172 |
Token | The |
Token ID | 383 |
Feature activation | +3.98e-02 |
Pos logit contributions | |
Suz | +0.015 |
Bee | +0.014 |
M | +0.014 |
Andy | +0.013 |
Joe | +0.013 |
Neg logit contributions | |
aces | -0.028 |
ooter | -0.023 |
uries | -0.023 |
ests | -0.022 |
ival | -0.022 |
Token | animal |
Token ID | 5044 |
Feature activation | +5.08e-02 |
Pos logit contributions | |
Bee | +0.054 |
Suz | +0.053 |
M | +0.053 |
Mia | +0.051 |
Andy | +0.050 |
Neg logit contributions | |
aces | -0.103 |
uries | -0.086 |
ooter | -0.083 |
ests | -0.082 |
seek | -0.081 |
Token | suddenly |
Token ID | 6451 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
Suz | +0.061 |
M | +0.058 |
Bee | +0.057 |
Andy | +0.054 |
Joe | +0.054 |
Neg logit contributions | |
aces | -0.137 |
ooter | -0.113 |
uries | -0.111 |
ests | -0.109 |
ival | -0.109 |
Token | stopped |
Token ID | 5025 |
Feature activation | +8.71e-02 |
Pos logit contributions | |
Suz | +0.085 |
Bee | +0.082 |
M | +0.081 |
Andy | +0.079 |
Joe | +0.077 |
Neg logit contributions | |
aces | -0.162 |
ooter | -0.129 |
uries | -0.127 |
ival | -0.125 |
ests | -0.124 |
Token | ate |
Token ID | 378 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
aces | +0.132 |
ooter | +0.105 |
uries | +0.104 |
ests | +0.097 |
ival | +0.097 |
Neg logit contributions | |
Suz | -0.123 |
M | -0.122 |
Bee | -0.120 |
Mia | -0.117 |
Andy | -0.116 |
Token | her |
Token ID | 607 |
Feature activation | -7.20e-02 |
Pos logit contributions | |
aces | +0.047 |
ooter | +0.040 |
uries | +0.040 |
ests | +0.039 |
ival | +0.039 |
Neg logit contributions | |
Suz | -0.019 |
M | -0.018 |
Bee | -0.018 |
Mia | -0.017 |
Andy | -0.017 |
Token | house |
Token ID | 2156 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
aces | +0.181 |
uries | +0.149 |
ooter | +0.148 |
seek | +0.145 |
ests | +0.143 |
Neg logit contributions | |
M | -0.107 |
Suz | -0.103 |
Bee | -0.100 |
Mia | -0.097 |
Andy | -0.093 |
Token | for |
Token ID | 329 |
Feature activation | -5.09e-02 |
Pos logit contributions | |
aces | +0.145 |
ooter | +0.124 |
uries | +0.122 |
ests | +0.122 |
ival | +0.121 |
Neg logit contributions | |
M | -0.048 |
Suz | -0.047 |
Mia | -0.045 |
Bee | -0.044 |
Andy | -0.041 |
Token | special |
Token ID | 2041 |
Feature activation | -5.45e-02 |
Pos logit contributions | |
aces | +0.137 |
ooter | +0.117 |
uries | +0.113 |
ests | +0.111 |
ival | +0.110 |
Neg logit contributions | |
M | -0.064 |
Suz | -0.064 |
Bee | -0.061 |
Mia | -0.060 |
Andy | -0.058 |
Token | occasions |
Token ID | 12432 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
aces | +0.112 |
uries | +0.091 |
ooter | +0.089 |
ival | +0.087 |
oll | +0.087 |
Neg logit contributions | |
M | -0.102 |
Suz | -0.100 |
Mia | -0.094 |
Bee | -0.093 |
Maria | -0.091 |
Token | . |
Token ID | 13 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
aces | +0.379 |
ooter | +0.324 |
uries | +0.315 |
ival | +0.315 |
ests | +0.313 |
Neg logit contributions | |
Suz | -0.139 |
M | -0.137 |
Bee | -0.133 |
Mia | -0.128 |
Andy | -0.126 |
Token | Today |
Token ID | 6288 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
aces | +0.056 |
ooter | +0.045 |
uries | +0.044 |
ests | +0.043 |
ival | +0.042 |
Neg logit contributions | |
Suz | -0.039 |
Bee | -0.038 |
M | -0.037 |
Andy | -0.036 |
Joe | -0.036 |
Token | was |
Token ID | 373 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
aces | +0.093 |
ooter | +0.077 |
case | +0.075 |
ival | +0.075 |
rides | +0.074 |
Neg logit contributions | |
Bee | -0.049 |
Suz | -0.048 |
Andy | -0.044 |
M | -0.044 |
Doug | -0.044 |
Token | no |
Token ID | 645 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
Suz | +0.013 |
M | +0.012 |
Bee | +0.012 |
Mia | +0.011 |
Andy | +0.011 |
Neg logit contributions | |
aces | -0.029 |
ooter | -0.024 |
uries | -0.024 |
ests | -0.023 |
ival | -0.023 |
Token | exception |
Token ID | 6631 |
Feature activation | -4.37e-03 |
Pos logit contributions | |
Suz | +0.064 |
Bee | +0.062 |
M | +0.062 |
Andy | +0.060 |
Mia | +0.060 |
Neg logit contributions | |
aces | -0.097 |
ooter | -0.078 |
uries | -0.077 |
ests | -0.075 |
ival | -0.074 |
Token | . |
Token ID | 13 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
aces | +0.001 |
ooter | +0.000 |
uries | +0.000 |
ests | +0.000 |
rides | +0.000 |
Neg logit contributions | |
Suz | -0.000 |
Bee | -0.000 |
M | -0.000 |
Andy | -0.000 |
Joe | -0.000 |
Token | She |
Token ID | 1375 |
Feature activation | +1.18e-03 |
Pos logit contributions | |
aces | +0.062 |
ooter | +0.051 |
uries | +0.051 |
ival | +0.049 |
ests | +0.049 |
Neg logit contributions | |
Suz | -0.033 |
M | -0.032 |
Bee | -0.032 |
Mia | -0.031 |
Andy | -0.030 |
Token | loved |
Token ID | 6151 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
Suz | +0.002 |
M | +0.002 |
Bee | +0.002 |
Andy | +0.002 |
Mia | +0.002 |
Neg logit contributions | |
aces | -0.003 |
ooter | -0.002 |
uries | -0.002 |
ests | -0.002 |
ival | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
aces | +0.059 |
uries | +0.049 |
ooter | +0.049 |
ests | +0.047 |
ival | +0.047 |
Neg logit contributions | |
Suz | -0.022 |
M | -0.022 |
Bee | -0.022 |
Andy | -0.021 |
Mia | -0.020 |
Token | have |
Token ID | 423 |
Feature activation | -5.61e-02 |
Pos logit contributions | |
aces | +0.064 |
uries | +0.052 |
ival | +0.052 |
ooter | +0.051 |
ests | +0.051 |
Neg logit contributions | |
M | -0.040 |
Suz | -0.040 |
Bee | -0.039 |
Mia | -0.038 |
Andy | -0.037 |
Token | pic |
Token ID | 8301 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
aces | +0.138 |
ooter | +0.121 |
uries | +0.120 |
ests | +0.109 |
lor | +0.108 |
Neg logit contributions | |
M | -0.089 |
Mia | -0.084 |
Suz | -0.082 |
Bee | -0.082 |
its | -0.080 |
Token | n |
Token ID | 77 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
aces | +0.227 |
ooter | +0.163 |
ests | +0.163 |
oll | +0.159 |
uries | +0.152 |
Neg logit contributions | |
Suz | -0.291 |
Andy | -0.288 |
M | -0.285 |
Bee | -0.283 |
Joe | -0.281 |
Token | ics |
Token ID | 873 |
Feature activation | -5.32e-02 |
Pos logit contributions | |
aces | +0.107 |
uries | +0.079 |
ooter | +0.075 |
ests | +0.073 |
ival | +0.071 |
Neg logit contributions | |
Suz | -0.173 |
Bee | -0.168 |
Andy | -0.168 |
M | -0.166 |
Joe | -0.165 |
Token | with |
Token ID | 351 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
aces | +0.160 |
ooter | +0.143 |
uries | +0.138 |
ival | +0.136 |
lor | +0.131 |
Neg logit contributions | |
its | -0.047 |
M | -0.047 |
Mia | -0.046 |
Bee | -0.045 |
Suz | -0.044 |
Token | her |
Token ID | 607 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
aces | +0.036 |
ooter | +0.031 |
uries | +0.031 |
ival | +0.030 |
ests | +0.029 |
Neg logit contributions | |
M | -0.014 |
Suz | -0.014 |
Bee | -0.014 |
Mia | -0.013 |
Andy | -0.013 |
Token | family |
Token ID | 1641 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
aces | +0.171 |
uries | +0.144 |
ooter | +0.142 |
ival | +0.137 |
seek | +0.135 |
Neg logit contributions | |
M | -0.092 |
Bee | -0.091 |
Suz | -0.088 |
Andy | -0.085 |
Mia | -0.084 |
Token | liked |
Token ID | 8288 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
aces | +0.077 |
ooter | +0.065 |
uries | +0.064 |
lor | +0.063 |
ests | +0.062 |
Neg logit contributions | |
Suz | -0.046 |
M | -0.045 |
Bee | -0.044 |
Joe | -0.042 |
Andy | -0.042 |
Token | to |
Token ID | 284 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
aces | +0.063 |
ooter | +0.052 |
uries | +0.052 |
ests | +0.051 |
ival | +0.050 |
Neg logit contributions | |
Suz | -0.029 |
Bee | -0.028 |
M | -0.027 |
Andy | -0.026 |
Mia | -0.026 |
Token | play |
Token ID | 711 |
Feature activation | -8.35e-02 |
Pos logit contributions | |
aces | +0.063 |
ooter | +0.051 |
ival | +0.051 |
uries | +0.051 |
oll | +0.050 |
Neg logit contributions | |
Suz | -0.042 |
Bee | -0.041 |
M | -0.041 |
Mia | -0.040 |
Andy | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
aces | +0.218 |
ooter | +0.178 |
uries | +0.176 |
ests | +0.175 |
ival | +0.171 |
Neg logit contributions | |
Suz | -0.111 |
Bee | -0.106 |
M | -0.106 |
Andy | -0.101 |
Joe | -0.101 |
Token | have |
Token ID | 423 |
Feature activation | -5.29e-02 |
Pos logit contributions | |
aces | +0.076 |
uries | +0.061 |
ooter | +0.061 |
rides | +0.057 |
seek | +0.056 |
Neg logit contributions | |
Suz | -0.064 |
Bee | -0.064 |
M | -0.062 |
Andy | -0.059 |
Joe | -0.059 |
Token | pic |
Token ID | 8301 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
aces | +0.140 |
ooter | +0.122 |
uries | +0.118 |
oll | +0.115 |
lor | +0.114 |
Neg logit contributions | |
Mia | -0.069 |
M | -0.068 |
Suz | -0.068 |
Bee | -0.067 |
Joe | -0.067 |
Token | n |
Token ID | 77 |
Feature activation | -7.07e-02 |
Pos logit contributions | |
aces | +0.223 |
oll | +0.160 |
ests | +0.159 |
ooter | +0.159 |
uries | +0.148 |
Neg logit contributions | |
Suz | -0.293 |
Andy | -0.288 |
Joe | -0.282 |
M | -0.281 |
Bee | -0.281 |
Token | ics |
Token ID | 873 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
aces | +0.096 |
uries | +0.070 |
ooter | +0.067 |
ests | +0.062 |
oll | +0.062 |
Neg logit contributions | |
Suz | -0.174 |
Andy | -0.170 |
Bee | -0.169 |
Joe | -0.168 |
M | -0.168 |
Token | . |
Token ID | 13 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
aces | +0.156 |
ooter | +0.138 |
uries | +0.133 |
lor | +0.129 |
ival | +0.129 |
Neg logit contributions | |
Mia | -0.049 |
M | -0.048 |
Bee | -0.048 |
Suz | -0.047 |
its | -0.046 |
Token | One |
Token ID | 1881 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
aces | +0.059 |
uries | +0.048 |
ooter | +0.047 |
ests | +0.046 |
ival | +0.045 |
Neg logit contributions | |
Bee | -0.040 |
Suz | -0.040 |
M | -0.037 |
Andy | -0.037 |
Ali | -0.036 |
Token | day |
Token ID | 1110 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
aces | +0.022 |
ooter | +0.016 |
oll | +0.015 |
ests | +0.015 |
uries | +0.015 |
Neg logit contributions | |
Suz | -0.033 |
Bee | -0.031 |
Andy | -0.031 |
M | -0.031 |
Liz | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
aces | +0.070 |
uries | +0.058 |
ooter | +0.058 |
ests | +0.057 |
ival | +0.057 |
Neg logit contributions | |
M | -0.024 |
Suz | -0.024 |
Joe | -0.023 |
Bee | -0.022 |
Andy | -0.022 |
Token | They |
Token ID | 1119 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
aces | +0.066 |
ooter | +0.055 |
uries | +0.054 |
ests | +0.053 |
ival | +0.053 |
Neg logit contributions | |
Suz | -0.029 |
M | -0.029 |
Bee | -0.028 |
Joe | -0.027 |
Mia | -0.027 |
Token | loved |
Token ID | 6151 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
aces | +0.068 |
ooter | +0.058 |
lor | +0.057 |
ests | +0.057 |
uries | +0.057 |
Neg logit contributions | |
M | -0.032 |
Suz | -0.032 |
Joe | -0.030 |
Bee | -0.030 |
Andy | -0.029 |
Token | celebrating |
Token ID | 17499 |
Feature activation | -4.58e-02 |
Pos logit contributions | |
aces | +0.061 |
ooter | +0.051 |
uries | +0.050 |
ests | +0.049 |
ival | +0.049 |
Neg logit contributions | |
Suz | -0.025 |
Bee | -0.024 |
M | -0.024 |
Andy | -0.023 |
Joe | -0.023 |
Token | special |
Token ID | 2041 |
Feature activation | -5.03e-02 |
Pos logit contributions | |
aces | +0.120 |
uries | +0.099 |
sweets | +0.098 |
rides | +0.098 |
ests | +0.098 |
Neg logit contributions | |
Suz | -0.056 |
Bee | -0.054 |
M | -0.049 |
Andy | -0.049 |
Joe | -0.048 |
Token | occasions |
Token ID | 12432 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
aces | +0.101 |
ooter | +0.079 |
uries | +0.078 |
oll | +0.075 |
ode | +0.069 |
Neg logit contributions | |
M | -0.100 |
Suz | -0.097 |
Bee | -0.097 |
Mia | -0.095 |
Andy | -0.095 |
Token | . |
Token ID | 13 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
aces | +0.344 |
uries | +0.283 |
ooter | +0.283 |
ests | +0.275 |
ival | +0.271 |
Neg logit contributions | |
Suz | -0.166 |
Bee | -0.163 |
M | -0.158 |
Andy | -0.153 |
Joe | -0.151 |
Token | They |
Token ID | 1119 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
aces | +0.064 |
ooter | +0.053 |
uries | +0.052 |
ests | +0.051 |
ival | +0.050 |
Neg logit contributions | |
Suz | -0.033 |
M | -0.032 |
Bee | -0.032 |
Andy | -0.031 |
Joe | -0.031 |
Token | had |
Token ID | 550 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
aces | +0.072 |
ooter | +0.061 |
lor | +0.060 |
uries | +0.059 |
ests | +0.059 |
Neg logit contributions | |
M | -0.040 |
Suz | -0.038 |
Bee | -0.037 |
Joe | -0.036 |
Mia | -0.036 |
Token | plans |
Token ID | 3352 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
aces | +0.135 |
ooter | +0.123 |
ests | +0.116 |
uries | +0.115 |
oll | +0.112 |
Neg logit contributions | |
M | -0.044 |
Mia | -0.042 |
Joe | -0.039 |
its | -0.038 |
Suz | -0.038 |
Token | to |
Token ID | 284 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
aces | +0.188 |
ooter | +0.160 |
uries | +0.158 |
ests | +0.157 |
oll | +0.154 |
Neg logit contributions | |
Suz | -0.052 |
M | -0.052 |
Joe | -0.050 |
Mia | -0.049 |
Andy | -0.048 |
Token | Jimmy |
Token ID | 40335 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
aces | +0.215 |
uries | +0.187 |
ooter | +0.186 |
ival | +0.175 |
ests | +0.175 |
Neg logit contributions | |
M | -0.067 |
Suz | -0.066 |
Bee | -0.065 |
Mia | -0.061 |
Joe | -0.061 |
Token | was |
Token ID | 373 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
aces | +0.040 |
ooter | +0.033 |
uries | +0.033 |
ests | +0.032 |
ival | +0.032 |
Neg logit contributions | |
Suz | -0.018 |
M | -0.018 |
Bee | -0.018 |
Joe | -0.017 |
Andy | -0.017 |
Token | always |
Token ID | 1464 |
Feature activation | +3.59e-03 |
Pos logit contributions | |
aces | +0.028 |
ooter | +0.023 |
uries | +0.023 |
oll | +0.022 |
ests | +0.022 |
Neg logit contributions | |
Suz | -0.017 |
Bee | -0.017 |
M | -0.017 |
Andy | -0.016 |
Mia | -0.016 |
Token | excited |
Token ID | 6568 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
Suz | +0.005 |
Bee | +0.005 |
Andy | +0.005 |
M | +0.005 |
Mia | +0.005 |
Neg logit contributions | |
aces | -0.008 |
ooter | -0.007 |
uries | -0.007 |
oll | -0.006 |
ival | -0.006 |
Token | for |
Token ID | 329 |
Feature activation | -5.09e-02 |
Pos logit contributions | |
aces | +0.070 |
ooter | +0.059 |
uries | +0.059 |
ests | +0.059 |
ival | +0.057 |
Neg logit contributions | |
M | -0.021 |
Joe | -0.021 |
Suz | -0.021 |
Andy | -0.020 |
Mia | -0.019 |
Token | Wed |
Token ID | 3300 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
aces | +0.154 |
ooter | +0.132 |
uries | +0.128 |
ests | +0.127 |
oll | +0.124 |
Neg logit contributions | |
M | -0.052 |
Suz | -0.051 |
Joe | -0.049 |
Mia | -0.047 |
Andy | -0.046 |
Token | nes |
Token ID | 2516 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
aces | +0.144 |
ests | +0.089 |
ooter | +0.080 |
cand | +0.073 |
sweets | +0.069 |
Neg logit contributions | |
Suz | -0.359 |
Bee | -0.343 |
M | -0.343 |
Joe | -0.341 |
Andy | -0.341 |
Token | days |
Token ID | 12545 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
aces | +0.093 |
ooter | +0.072 |
uries | +0.072 |
ests | +0.066 |
ival | +0.065 |
Neg logit contributions | |
Bee | -0.098 |
Suz | -0.097 |
M | -0.096 |
Andy | -0.094 |
Mia | -0.093 |
Token | because |
Token ID | 780 |
Feature activation | -6.85e-03 |
Pos logit contributions | |
aces | +0.227 |
ooter | +0.190 |
ests | +0.190 |
uries | +0.189 |
ode | +0.188 |
Neg logit contributions | |
M | -0.063 |
Joe | -0.060 |
Suz | -0.058 |
Andy | -0.053 |
Mia | -0.050 |
Token | it |
Token ID | 340 |
Feature activation | -7.45e-04 |
Pos logit contributions | |
aces | +0.020 |
ooter | +0.017 |
uries | +0.017 |
ests | +0.016 |
ival | +0.016 |
Neg logit contributions | |
Suz | -0.007 |
M | -0.007 |
Bee | -0.007 |
Andy | -0.007 |
Joe | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | -5.44e-04 |
Pos logit contributions | |
aces | +0.002 |
ooter | +0.002 |
uries | +0.002 |
ests | +0.002 |
ival | +0.002 |
Neg logit contributions | |
Suz | -0.001 |
Bee | -0.001 |
M | -0.001 |
Andy | -0.001 |
Mia | -0.001 |
Token | shapes |
Token ID | 15268 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
aces | +0.064 |
ooter | +0.049 |
uries | +0.049 |
ests | +0.047 |
ival | +0.046 |
Neg logit contributions | |
Suz | -0.058 |
Bee | -0.057 |
M | -0.056 |
Andy | -0.055 |
Joe | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
aces | +0.068 |
ooter | +0.057 |
uries | +0.057 |
ests | +0.055 |
ival | +0.055 |
Neg logit contributions | |
Suz | -0.027 |
Bee | -0.027 |
M | -0.026 |
Mia | -0.025 |
Joe | -0.025 |
Token | They |
Token ID | 1119 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
aces | +0.028 |
uries | +0.022 |
ests | +0.022 |
ooter | +0.022 |
ival | +0.021 |
Neg logit contributions | |
Suz | -0.016 |
Bee | -0.015 |
Andy | -0.015 |
M | -0.014 |
Joe | -0.014 |
Token | make |
Token ID | 787 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
aces | +0.084 |
ooter | +0.070 |
uries | +0.069 |
ests | +0.068 |
ival | +0.067 |
Neg logit contributions | |
Suz | -0.043 |
Bee | -0.042 |
M | -0.042 |
Mia | -0.040 |
Joe | -0.039 |
Token | a |
Token ID | 257 |
Feature activation | -2.77e-04 |
Pos logit contributions | |
aces | +0.039 |
uries | +0.031 |
ooter | +0.030 |
ests | +0.030 |
ival | +0.030 |
Neg logit contributions | |
Suz | -0.024 |
Bee | -0.023 |
M | -0.023 |
Andy | -0.022 |
Joe | -0.022 |
Token | coll |
Token ID | 2927 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
aces | +0.001 |
ooter | +0.000 |
bracelet | +0.000 |
uries | +0.000 |
cand | +0.000 |
Neg logit contributions | |
Suz | -0.000 |
Joe | -0.000 |
Andy | -0.000 |
Bee | -0.000 |
M | -0.000 |
Token | age |
Token ID | 496 |
Feature activation | -6.35e-03 |
Pos logit contributions | |
aces | +0.163 |
ooter | +0.112 |
uries | +0.108 |
ests | +0.103 |
oll | +0.099 |
Neg logit contributions | |
Suz | -0.325 |
Bee | -0.322 |
M | -0.313 |
Andy | -0.312 |
Mia | -0.311 |
Token | of |
Token ID | 286 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
aces | +0.018 |
ooter | +0.015 |
uries | +0.015 |
ests | +0.014 |
ival | +0.014 |
Neg logit contributions | |
Suz | -0.007 |
Bee | -0.007 |
M | -0.007 |
Mia | -0.007 |
Andy | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -4.99e-03 |
Pos logit contributions | |
Suz | +0.069 |
Bee | +0.068 |
M | +0.067 |
Andy | +0.066 |
Joe | +0.065 |
Neg logit contributions | |
aces | -0.086 |
ooter | -0.066 |
uries | -0.064 |
ests | -0.063 |
cand | -0.063 |
Token | farm |
Token ID | 5318 |
Feature activation | -4.94e-02 |
Pos logit contributions | |
aces | +0.010 |
ooter | +0.008 |
uries | +0.008 |
bracelet | +0.008 |
ival | +0.008 |
Neg logit contributions | |
Suz | -0.009 |
Joe | -0.008 |
Andy | -0.008 |
Bee | -0.008 |
M | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -8.28e-03 |
Pos logit contributions | |
aces | +0.136 |
ooter | +0.114 |
uries | +0.113 |
ests | +0.111 |
ival | +0.109 |
Neg logit contributions | |
Suz | -0.058 |
Bee | -0.056 |
M | -0.055 |
Mia | -0.053 |
Andy | -0.053 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
Suz | +0.052 |
M | +0.049 |
Bee | +0.049 |
Joe | +0.049 |
Andy | +0.049 |
Neg logit contributions | |
aces | -0.068 |
ooter | -0.056 |
ests | -0.053 |
oll | -0.052 |
uries | -0.052 |
Token | named |
Token ID | 3706 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
Suz | +0.022 |
Joe | +0.022 |
Andy | +0.021 |
Bee | +0.021 |
Doug | +0.021 |
Neg logit contributions | |
aces | -0.029 |
ooter | -0.024 |
uries | -0.023 |
oll | -0.023 |
rides | -0.022 |
Token | Lily |
Token ID | 20037 |
Feature activation | -5.44e-03 |
Pos logit contributions | |
aces | +0.074 |
uries | +0.061 |
ooter | +0.061 |
oll | +0.058 |
sweets | +0.058 |
Neg logit contributions | |
Bee | -0.036 |
Suz | -0.035 |
Joe | -0.035 |
Andy | -0.035 |
Farmer | -0.034 |
Token | who |
Token ID | 508 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
aces | +0.012 |
ooter | +0.010 |
uries | +0.010 |
rides | +0.009 |
ests | +0.009 |
Neg logit contributions | |
Suz | -0.009 |
Bee | -0.009 |
M | -0.008 |
Joe | -0.008 |
Andy | -0.008 |
Token | loved |
Token ID | 6151 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
Suz | +0.018 |
Bee | +0.017 |
M | +0.017 |
Andy | +0.016 |
Joe | +0.016 |
Neg logit contributions | |
aces | -0.027 |
ooter | -0.022 |
uries | -0.021 |
ests | -0.021 |
ival | -0.020 |
Token | pic |
Token ID | 8301 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
aces | +0.074 |
uries | +0.062 |
ooter | +0.062 |
ival | +0.060 |
ests | +0.060 |
Neg logit contributions | |
Suz | -0.027 |
M | -0.027 |
Bee | -0.027 |
Andy | -0.025 |
Mia | -0.025 |
Token | n |
Token ID | 77 |
Feature activation | -7.61e-02 |
Pos logit contributions | |
aces | +0.218 |
ests | +0.157 |
ooter | +0.156 |
uries | +0.148 |
oll | +0.145 |
Neg logit contributions | |
Suz | -0.291 |
Andy | -0.284 |
M | -0.283 |
Bee | -0.281 |
Joe | -0.278 |
Token | ics |
Token ID | 873 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
aces | +0.105 |
uries | +0.073 |
ooter | +0.071 |
ival | +0.068 |
ests | +0.068 |
Neg logit contributions | |
Suz | -0.190 |
Bee | -0.186 |
M | -0.185 |
Andy | -0.183 |
Joe | -0.182 |
Token | . |
Token ID | 13 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
aces | +0.167 |
ooter | +0.151 |
uries | +0.149 |
ival | +0.147 |
lor | +0.141 |
Neg logit contributions | |
M | -0.039 |
Mia | -0.036 |
Bee | -0.035 |
its | -0.035 |
Suz | -0.033 |
Token | She |
Token ID | 1375 |
Feature activation | -8.91e-03 |
Pos logit contributions | |
aces | +0.081 |
ival | +0.069 |
ooter | +0.068 |
uries | +0.068 |
lor | +0.066 |
Neg logit contributions | |
M | -0.040 |
Suz | -0.038 |
Mia | -0.038 |
Bee | -0.036 |
Liz | -0.034 |
Token | would |
Token ID | 561 |
Feature activation | -5.96e-02 |
Pos logit contributions | |
aces | +0.022 |
ooter | +0.018 |
uries | +0.018 |
ests | +0.017 |
ival | +0.017 |
Neg logit contributions | |
Suz | -0.013 |
M | -0.013 |
Bee | -0.013 |
Mia | -0.012 |
Andy | -0.012 |
Token | plan |
Token ID | 1410 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
M | +0.003 |
Mia | +0.002 |
Bee | +0.002 |
Suz | +0.002 |
Joe | +0.002 |
Neg logit contributions | |
aces | -0.004 |
uries | -0.004 |
ooter | -0.004 |
ests | -0.003 |
ival | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | +2.47e-03 |
Pos logit contributions | |
aces | +0.111 |
uries | +0.096 |
ooter | +0.096 |
ode | +0.092 |
ests | +0.092 |
Neg logit contributions | |
Suz | -0.035 |
M | -0.033 |
Joe | -0.032 |
Andy | -0.032 |
Mia | -0.032 |
Token | to |
Token ID | 284 |
Feature activation | +5.10e-03 |
Pos logit contributions | |
Suz | +0.003 |
Bee | +0.003 |
M | +0.003 |
Andy | +0.003 |
Joe | +0.003 |
Neg logit contributions | |
aces | -0.006 |
ooter | -0.005 |
uries | -0.005 |
ests | -0.005 |
ival | -0.005 |
Token | make |
Token ID | 787 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
Suz | +0.008 |
M | +0.007 |
Joe | +0.007 |
Bee | +0.007 |
Andy | +0.007 |
Neg logit contributions | |
aces | -0.013 |
ooter | -0.010 |
ests | -0.010 |
oll | -0.010 |
uries | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +3.74e-03 |
Pos logit contributions | |
aces | +0.056 |
ooter | +0.046 |
uries | +0.046 |
ests | +0.045 |
ival | +0.044 |
Neg logit contributions | |
Suz | -0.028 |
Bee | -0.027 |
M | -0.027 |
Andy | -0.026 |
Joe | -0.026 |
Token | coll |
Token ID | 2927 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
Suz | +0.006 |
Bee | +0.006 |
M | +0.006 |
Andy | +0.005 |
Joe | +0.005 |
Neg logit contributions | |
aces | -0.008 |
ooter | -0.007 |
uries | -0.007 |
ival | -0.007 |
ests | -0.007 |
Token | age |
Token ID | 496 |
Feature activation | -6.72e-03 |
Pos logit contributions | |
aces | +0.166 |
ooter | +0.108 |
uries | +0.108 |
ests | +0.105 |
oll | +0.104 |
Neg logit contributions | |
Suz | -0.315 |
Bee | -0.311 |
Andy | -0.307 |
Maria | -0.301 |
its | -0.299 |
Token | with |
Token ID | 351 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
aces | +0.019 |
uries | +0.016 |
ooter | +0.016 |
ests | +0.016 |
ival | +0.016 |
Neg logit contributions | |
Suz | -0.007 |
M | -0.007 |
Bee | -0.007 |
Joe | -0.007 |
Andy | -0.007 |
Token | pictures |
Token ID | 5986 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
Suz | +0.026 |
Bee | +0.025 |
M | +0.025 |
Andy | +0.024 |
Joe | +0.024 |
Neg logit contributions | |
aces | -0.047 |
ooter | -0.038 |
uries | -0.038 |
ests | -0.037 |
ival | -0.036 |
Token | from |
Token ID | 422 |
Feature activation | +7.06e-03 |
Pos logit contributions | |
aces | +0.122 |
uries | +0.109 |
ooter | +0.107 |
ests | +0.106 |
ival | +0.103 |
Neg logit contributions | |
Suz | -0.036 |
Mia | -0.035 |
M | -0.035 |
Joe | -0.034 |
Andy | -0.032 |
Token | a |
Token ID | 257 |
Feature activation | -4.70e-03 |
Pos logit contributions | |
Suz | +0.007 |
Bee | +0.007 |
M | +0.007 |
Andy | +0.006 |
Mia | +0.006 |
Neg logit contributions | |
aces | -0.021 |
ooter | -0.017 |
uries | -0.017 |
ests | -0.017 |
ival | -0.017 |
Token | ate |
Token ID | 378 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
aces | +0.122 |
ooter | +0.098 |
uries | +0.097 |
ests | +0.090 |
ival | +0.090 |
Neg logit contributions | |
Suz | -0.111 |
M | -0.109 |
Bee | -0.108 |
Mia | -0.105 |
Andy | -0.104 |
Token | her |
Token ID | 607 |
Feature activation | -6.81e-02 |
Pos logit contributions | |
aces | +0.035 |
ooter | +0.030 |
uries | +0.029 |
ests | +0.028 |
ival | +0.028 |
Neg logit contributions | |
Suz | -0.014 |
M | -0.013 |
Bee | -0.013 |
Mia | -0.013 |
Andy | -0.012 |
Token | home |
Token ID | 1363 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
aces | +0.169 |
uries | +0.138 |
ooter | +0.137 |
seek | +0.135 |
ests | +0.133 |
Neg logit contributions | |
M | -0.103 |
Suz | -0.100 |
Bee | -0.096 |
Mia | -0.093 |
Andy | -0.090 |
Token | for |
Token ID | 329 |
Feature activation | -4.54e-02 |
Pos logit contributions | |
aces | +0.091 |
ooter | +0.078 |
uries | +0.076 |
ests | +0.076 |
ival | +0.075 |
Neg logit contributions | |
M | -0.034 |
Suz | -0.034 |
Bee | -0.032 |
Mia | -0.032 |
Andy | -0.030 |
Token | special |
Token ID | 2041 |
Feature activation | -5.23e-02 |
Pos logit contributions | |
aces | +0.122 |
ooter | +0.104 |
uries | +0.100 |
ests | +0.099 |
ival | +0.098 |
Neg logit contributions | |
Suz | -0.057 |
M | -0.057 |
Bee | -0.055 |
Mia | -0.053 |
Andy | -0.052 |
Token | occasions |
Token ID | 12432 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
aces | +0.108 |
uries | +0.085 |
oll | +0.081 |
ooter | +0.081 |
ival | +0.081 |
Neg logit contributions | |
M | -0.100 |
Suz | -0.098 |
Bee | -0.091 |
Mia | -0.090 |
Maria | -0.090 |
Token | . |
Token ID | 13 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
aces | +0.358 |
ooter | +0.306 |
uries | +0.298 |
ival | +0.296 |
ests | +0.296 |
Neg logit contributions | |
Suz | -0.135 |
M | -0.133 |
Bee | -0.128 |
Mia | -0.123 |
Andy | -0.122 |
Token |
|
Token ID | 198 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
aces | +0.069 |
ooter | +0.057 |
uries | +0.056 |
ests | +0.055 |
ival | +0.054 |
Neg logit contributions | |
Suz | -0.037 |
Bee | -0.037 |
M | -0.035 |
Andy | -0.035 |
Joe | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
aces | +0.050 |
ests | +0.042 |
ival | +0.041 |
ooter | +0.041 |
uries | +0.041 |
Neg logit contributions | |
Suz | -0.027 |
Bee | -0.027 |
M | -0.025 |
boiling | -0.025 |
Andy | -0.025 |
Token | Today |
Token ID | 8888 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
aces | +0.023 |
ooter | +0.018 |
uries | +0.018 |
ests | +0.017 |
ival | +0.017 |
Neg logit contributions | |
Suz | -0.024 |
Bee | -0.024 |
M | -0.024 |
Andy | -0.023 |
Joe | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +1.56e-03 |
Pos logit contributions | |
aces | +0.084 |
ooter | +0.070 |
ival | +0.068 |
cand | +0.068 |
oll | +0.068 |
Neg logit contributions | |
Bee | -0.047 |
Suz | -0.046 |
Andy | -0.043 |
M | -0.042 |
Ali | -0.042 |
Token | She |
Token ID | 1375 |
Feature activation | -6.89e-03 |
Pos logit contributions | |
aces | +0.093 |
ooter | +0.079 |
uries | +0.078 |
ival | +0.078 |
lor | +0.075 |
Neg logit contributions | |
M | -0.046 |
Suz | -0.045 |
Mia | -0.045 |
Bee | -0.044 |
Liz | -0.041 |
Token | loved |
Token ID | 6151 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
aces | +0.017 |
ooter | +0.014 |
uries | +0.014 |
ests | +0.014 |
ival | +0.014 |
Neg logit contributions | |
Suz | -0.010 |
Bee | -0.010 |
M | -0.010 |
Mia | -0.009 |
Andy | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
aces | +0.087 |
uries | +0.073 |
ooter | +0.072 |
ests | +0.070 |
ival | +0.070 |
Neg logit contributions | |
Suz | -0.034 |
M | -0.033 |
Bee | -0.033 |
Andy | -0.031 |
Mia | -0.031 |
Token | go |
Token ID | 467 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
aces | +0.084 |
uries | +0.070 |
ival | +0.068 |
ooter | +0.068 |
lor | +0.067 |
Neg logit contributions | |
M | -0.051 |
Suz | -0.050 |
Bee | -0.049 |
Mia | -0.048 |
Joe | -0.047 |
Token | on |
Token ID | 319 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
aces | +0.164 |
uries | +0.134 |
ooter | +0.130 |
ests | +0.128 |
ival | +0.127 |
Neg logit contributions | |
Suz | -0.090 |
M | -0.089 |
Bee | -0.087 |
Andy | -0.084 |
Mia | -0.083 |
Token | pic |
Token ID | 8301 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
aces | +0.043 |
uries | +0.034 |
ooter | +0.034 |
ests | +0.032 |
ival | +0.031 |
Neg logit contributions | |
M | -0.037 |
Suz | -0.036 |
Bee | -0.036 |
Andy | -0.035 |
Mia | -0.035 |
Token | n |
Token ID | 77 |
Feature activation | -7.37e-02 |
Pos logit contributions | |
aces | +0.219 |
ests | +0.159 |
oll | +0.153 |
ooter | +0.150 |
uries | +0.143 |
Neg logit contributions | |
Suz | -0.277 |
Bee | -0.276 |
M | -0.276 |
Andy | -0.275 |
Mia | -0.268 |
Token | ics |
Token ID | 873 |
Feature activation | -5.82e-02 |
Pos logit contributions | |
aces | +0.098 |
uries | +0.064 |
ooter | +0.064 |
ests | +0.060 |
ival | +0.060 |
Neg logit contributions | |
Suz | -0.188 |
Bee | -0.185 |
M | -0.184 |
Andy | -0.182 |
Joe | -0.181 |
Token | with |
Token ID | 351 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
aces | +0.179 |
ooter | +0.158 |
uries | +0.153 |
ival | +0.151 |
ests | +0.148 |
Neg logit contributions | |
M | -0.048 |
its | -0.047 |
Mia | -0.047 |
Bee | -0.046 |
Suz | -0.044 |
Token | her |
Token ID | 607 |
Feature activation | -7.26e-02 |
Pos logit contributions | |
aces | +0.055 |
ooter | +0.048 |
uries | +0.048 |
ival | +0.046 |
ests | +0.046 |
Neg logit contributions | |
M | -0.018 |
Suz | -0.017 |
Bee | -0.017 |
Mia | -0.017 |
Andy | -0.016 |
Token | family |
Token ID | 1641 |
Feature activation | -4.75e-02 |
Pos logit contributions | |
aces | +0.203 |
uries | +0.175 |
ooter | +0.171 |
ival | +0.166 |
seek | +0.165 |
Neg logit contributions | |
M | -0.088 |
Bee | -0.086 |
Suz | -0.084 |
Andy | -0.081 |
Mia | -0.080 |
Token | did |
Token ID | 750 |
Feature activation | -6.83e-02 |
Pos logit contributions | |
aces | +0.081 |
ooter | +0.068 |
uries | +0.067 |
ests | +0.065 |
ival | +0.064 |
Neg logit contributions | |
M | -0.036 |
Suz | -0.035 |
Bee | -0.034 |
Mia | -0.033 |
Joe | -0.032 |
Token | something |
Token ID | 1223 |
Feature activation | -5.60e-03 |
Pos logit contributions | |
aces | +0.188 |
ooter | +0.158 |
uries | +0.155 |
ests | +0.153 |
oll | +0.152 |
Neg logit contributions | |
Suz | -0.079 |
M | -0.078 |
Mia | -0.075 |
Bee | -0.074 |
Joe | -0.072 |
Token | special |
Token ID | 2041 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
aces | +0.014 |
ooter | +0.012 |
uries | +0.012 |
ests | +0.011 |
ival | +0.011 |
Neg logit contributions | |
Suz | -0.008 |
M | -0.008 |
Bee | -0.007 |
Mia | -0.007 |
Andy | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
aces | +0.106 |
ooter | +0.094 |
ival | +0.092 |
uries | +0.092 |
ode | +0.090 |
Neg logit contributions | |
M | -0.029 |
Mia | -0.026 |
Suz | -0.026 |
Joe | -0.024 |
Bee | -0.024 |
Token | On |
Token ID | 1550 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
aces | +0.070 |
ooter | +0.057 |
uries | +0.057 |
ests | +0.055 |
ival | +0.055 |
Neg logit contributions | |
Suz | -0.036 |
M | -0.035 |
Bee | -0.035 |
Andy | -0.033 |
Joe | -0.033 |
Token | Wed |
Token ID | 3300 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
aces | +0.043 |
ooter | +0.036 |
uries | +0.036 |
ests | +0.035 |
ival | +0.035 |
Neg logit contributions | |
Suz | -0.016 |
M | -0.015 |
Bee | -0.015 |
Mia | -0.014 |
Andy | -0.014 |
Token | nes |
Token ID | 2516 |
Feature activation | -3.97e-02 |
Pos logit contributions | |
aces | +0.156 |
ests | +0.114 |
ooter | +0.114 |
cand | +0.107 |
sweets | +0.099 |
Neg logit contributions | |
Suz | -0.320 |
Maria | -0.311 |
Bee | -0.307 |
Mia | -0.306 |
Joe | -0.304 |
Token | days |
Token ID | 12545 |
Feature activation | -7.20e-02 |
Pos logit contributions | |
aces | +0.065 |
ooter | +0.050 |
uries | +0.050 |
ests | +0.046 |
seek | +0.043 |
Neg logit contributions | |
Bee | -0.086 |
Suz | -0.084 |
Andy | -0.083 |
M | -0.083 |
Mia | -0.081 |
Token | she |
Token ID | 673 |
Feature activation | -3.62e-02 |
Pos logit contributions | |
aces | +0.220 |
uries | +0.187 |
ooter | +0.182 |
lor | +0.179 |
ode | +0.178 |
Neg logit contributions | |
Suz | -0.073 |
M | -0.071 |
Mia | -0.065 |
Joe | -0.064 |
Bee | -0.062 |
Token | liked |
Token ID | 8288 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
aces | +0.092 |
uries | +0.074 |
ooter | +0.074 |
ests | +0.073 |
ival | +0.072 |
Neg logit contributions | |
M | -0.053 |
Suz | -0.051 |
Mia | -0.050 |
Bee | -0.049 |
Joe | -0.048 |
Token | to |
Token ID | 284 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
aces | +0.066 |
ooter | +0.056 |
uries | +0.056 |
ests | +0.054 |
ival | +0.054 |
Neg logit contributions | |
M | -0.023 |
Suz | -0.023 |
Bee | -0.022 |
Mia | -0.021 |
Joe | -0.021 |
Token | saw |
Token ID | 2497 |
Feature activation | +5.53e-02 |
Pos logit contributions | |
Suz | +0.006 |
Bee | +0.006 |
M | +0.006 |
Andy | +0.005 |
Mia | +0.005 |
Neg logit contributions | |
aces | -0.013 |
ooter | -0.011 |
uries | -0.011 |
ival | -0.010 |
ests | -0.010 |
Token | lots |
Token ID | 6041 |
Feature activation | -1.86e-03 |
Pos logit contributions | |
Suz | +0.074 |
Bee | +0.072 |
M | +0.071 |
Andy | +0.068 |
Joe | +0.067 |
Neg logit contributions | |
aces | -0.143 |
ooter | -0.117 |
uries | -0.116 |
ests | -0.114 |
ival | -0.113 |
Token | of |
Token ID | 286 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
aces | +0.005 |
uries | +0.005 |
ooter | +0.005 |
ests | +0.004 |
ival | +0.004 |
Neg logit contributions | |
Suz | -0.002 |
M | -0.002 |
Bee | -0.002 |
Mia | -0.002 |
Andy | -0.002 |
Token | people |
Token ID | 661 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
Suz | +0.041 |
Bee | +0.041 |
M | +0.040 |
Andy | +0.039 |
Joe | +0.038 |
Neg logit contributions | |
aces | -0.056 |
ooter | -0.044 |
uries | -0.043 |
ests | -0.043 |
ival | -0.042 |
Token | having |
Token ID | 1719 |
Feature activation | -5.47e-02 |
Pos logit contributions | |
aces | +0.040 |
ests | +0.033 |
uries | +0.033 |
ooter | +0.033 |
lor | +0.032 |
Neg logit contributions | |
Suz | -0.016 |
M | -0.016 |
Joe | -0.016 |
Bee | -0.015 |
Andy | -0.015 |
Token | pic |
Token ID | 8301 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
aces | +0.142 |
ooter | +0.126 |
uries | +0.122 |
lor | +0.118 |
oll | +0.118 |
Neg logit contributions | |
M | -0.073 |
Suz | -0.073 |
Joe | -0.071 |
Mia | -0.069 |
Andy | -0.068 |
Token | n |
Token ID | 77 |
Feature activation | -6.05e-02 |
Pos logit contributions | |
aces | +0.210 |
ests | +0.156 |
ooter | +0.156 |
oll | +0.150 |
uries | +0.142 |
Neg logit contributions | |
Suz | -0.276 |
Andy | -0.270 |
Joe | -0.267 |
Bee | -0.263 |
M | -0.262 |
Token | ics |
Token ID | 873 |
Feature activation | -4.58e-02 |
Pos logit contributions | |
aces | +0.081 |
uries | +0.056 |
ooter | +0.055 |
ests | +0.052 |
ival | +0.050 |
Neg logit contributions | |
Suz | -0.153 |
Joe | -0.148 |
Bee | -0.148 |
M | -0.148 |
Andy | -0.147 |
Token | and |
Token ID | 290 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
aces | +0.138 |
ooter | +0.121 |
uries | +0.117 |
ival | +0.115 |
ests | +0.114 |
Neg logit contributions | |
M | -0.041 |
Suz | -0.041 |
Joe | -0.040 |
Mia | -0.040 |
Bee | -0.039 |
Token | walking |
Token ID | 6155 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
aces | +0.026 |
uries | +0.021 |
ooter | +0.021 |
ests | +0.021 |
ival | +0.020 |
Neg logit contributions | |
Suz | -0.014 |
Bee | -0.014 |
M | -0.014 |
Andy | -0.013 |
Mia | -0.013 |
Token | their |
Token ID | 511 |
Feature activation | -5.02e-02 |
Pos logit contributions | |
aces | +0.070 |
ooter | +0.058 |
uries | +0.057 |
oll | +0.056 |
ests | +0.055 |
Neg logit contributions | |
Suz | -0.039 |
M | -0.038 |
Bee | -0.037 |
Joe | -0.036 |
Mia | -0.036 |
Token | decided |
Token ID | 3066 |
Feature activation | -5.38e-02 |
Pos logit contributions | |
Suz | +0.047 |
Bee | +0.046 |
M | +0.045 |
Andy | +0.044 |
Joe | +0.043 |
Neg logit contributions | |
aces | -0.086 |
ooter | -0.071 |
uries | -0.070 |
ests | -0.068 |
ival | -0.067 |
Token | to |
Token ID | 284 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
aces | +0.156 |
ooter | +0.130 |
uries | +0.129 |
ests | +0.128 |
ival | +0.125 |
Neg logit contributions | |
Suz | -0.057 |
M | -0.055 |
Bee | -0.055 |
Andy | -0.053 |
Joe | -0.053 |
Token | make |
Token ID | 787 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
aces | +0.065 |
ooter | +0.053 |
uries | +0.052 |
ests | +0.051 |
ival | +0.050 |
Neg logit contributions | |
Suz | -0.039 |
Bee | -0.038 |
M | -0.037 |
Andy | -0.036 |
Mia | -0.036 |
Token | a |
Token ID | 257 |
Feature activation | +6.57e-03 |
Pos logit contributions | |
aces | +0.067 |
rides | +0.052 |
cand | +0.052 |
sweets | +0.052 |
ooter | +0.051 |
Neg logit contributions | |
Suz | -0.044 |
Bee | -0.043 |
M | -0.041 |
Andy | -0.041 |
Ali | -0.040 |
Token | big |
Token ID | 1263 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
Suz | +0.011 |
Bee | +0.010 |
Joe | +0.010 |
Andy | +0.010 |
M | +0.010 |
Neg logit contributions | |
aces | -0.014 |
ooter | -0.012 |
bracelet | -0.011 |
sweets | -0.011 |
ival | -0.011 |
Token | coll |
Token ID | 2927 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
Suz | +0.047 |
Bee | +0.047 |
Ali | +0.045 |
Mia | +0.045 |
M | +0.044 |
Neg logit contributions | |
aces | -0.046 |
ooter | -0.040 |
cand | -0.038 |
bracelet | -0.038 |
sweets | -0.037 |
Token | age |
Token ID | 496 |
Feature activation | -6.65e-03 |
Pos logit contributions | |
aces | +0.151 |
uries | +0.095 |
ooter | +0.093 |
ests | +0.090 |
ival | +0.084 |
Neg logit contributions | |
Suz | -0.327 |
Bee | -0.324 |
Andy | -0.316 |
M | -0.314 |
Joe | -0.310 |
Token | . |
Token ID | 13 |
Feature activation | -5.62e-03 |
Pos logit contributions | |
aces | +0.019 |
uries | +0.016 |
ooter | +0.016 |
ests | +0.016 |
ival | +0.015 |
Neg logit contributions | |
Suz | -0.007 |
Bee | -0.007 |
M | -0.007 |
Andy | -0.007 |
Joe | -0.006 |
Token | The |
Token ID | 383 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
aces | +0.014 |
ooter | +0.011 |
uries | +0.011 |
ests | +0.011 |
ival | +0.010 |
Neg logit contributions | |
Suz | -0.008 |
Bee | -0.008 |
M | -0.008 |
Andy | -0.007 |
Mia | -0.007 |
Token | child |
Token ID | 1200 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
M | +0.034 |
Suz | +0.033 |
Bee | +0.033 |
Mia | +0.031 |
Andy | +0.030 |
Neg logit contributions | |
aces | -0.059 |
uries | -0.048 |
ooter | -0.047 |
ests | -0.046 |
ival | -0.046 |
Token | went |
Token ID | 1816 |
Feature activation | -5.25e-02 |
Pos logit contributions | |
Suz | +0.052 |
Bee | +0.051 |
M | +0.050 |
Joe | +0.048 |
Mia | +0.048 |
Neg logit contributions | |
aces | -0.091 |
ooter | -0.074 |
uries | -0.071 |
ests | -0.070 |
ival | -0.069 |
Token | She |
Token ID | 1375 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
Suz | +0.015 |
Bee | +0.015 |
M | +0.014 |
Andy | +0.014 |
Joe | +0.013 |
Neg logit contributions | |
aces | -0.031 |
ooter | -0.026 |
uries | -0.025 |
ests | -0.025 |
ival | -0.024 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
Suz | +0.016 |
Bee | +0.016 |
M | +0.016 |
Andy | +0.015 |
Mia | +0.015 |
Neg logit contributions | |
aces | -0.032 |
ooter | -0.026 |
uries | -0.026 |
ival | -0.025 |
ests | -0.025 |
Token | to |
Token ID | 284 |
Feature activation | -2.92e-05 |
Pos logit contributions | |
aces | +0.050 |
ooter | +0.042 |
uries | +0.041 |
ests | +0.040 |
ival | +0.040 |
Neg logit contributions | |
Suz | -0.024 |
Bee | -0.023 |
M | -0.022 |
Andy | -0.022 |
Joe | -0.021 |
Token | make |
Token ID | 787 |
Feature activation | -9.12e-03 |
Pos logit contributions | |
aces | +0.000 |
ooter | +0.000 |
uries | +0.000 |
ests | +0.000 |
ival | +0.000 |
Neg logit contributions | |
Suz | -0.000 |
Bee | -0.000 |
M | -0.000 |
Andy | -0.000 |
Mia | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | +8.21e-03 |
Pos logit contributions | |
aces | +0.023 |
ooter | +0.018 |
uries | +0.018 |
rides | +0.018 |
sweets | +0.018 |
Neg logit contributions | |
Bee | -0.012 |
Suz | -0.012 |
Andy | -0.011 |
M | -0.011 |
Joe | -0.010 |
Token | coll |
Token ID | 2927 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Suz | +0.013 |
Bee | +0.013 |
M | +0.012 |
Andy | +0.012 |
Joe | +0.012 |
Neg logit contributions | |
aces | -0.018 |
ooter | -0.015 |
uries | -0.015 |
ival | -0.015 |
sweets | -0.014 |
Token | age |
Token ID | 496 |
Feature activation | -2.54e-04 |
Pos logit contributions | |
aces | +0.148 |
ooter | +0.094 |
uries | +0.093 |
ests | +0.088 |
oll | +0.086 |
Neg logit contributions | |
Suz | -0.325 |
Bee | -0.320 |
Andy | -0.312 |
M | -0.308 |
Joe | -0.307 |
Token | out |
Token ID | 503 |
Feature activation | +6.87e-02 |
Pos logit contributions | |
aces | +0.001 |
uries | +0.001 |
ooter | +0.001 |
ests | +0.001 |
ival | +0.001 |
Neg logit contributions | |
Suz | -0.000 |
M | -0.000 |
Bee | -0.000 |
Mia | -0.000 |
Joe | -0.000 |
Token | of |
Token ID | 286 |
Feature activation | +6.07e-02 |
Pos logit contributions | |
Suz | +0.081 |
Bee | +0.079 |
M | +0.078 |
Andy | +0.074 |
Joe | +0.074 |
Neg logit contributions | |
aces | -0.187 |
ooter | -0.156 |
uries | -0.155 |
ests | -0.151 |
ival | -0.149 |
Token | the |
Token ID | 262 |
Feature activation | -1.19e-03 |
Pos logit contributions | |
Bee | +0.085 |
Suz | +0.083 |
M | +0.080 |
Andy | +0.080 |
Ali | +0.078 |
Neg logit contributions | |
aces | -0.146 |
sweets | -0.117 |
ooter | -0.116 |
uries | -0.115 |
cand | -0.115 |
Token | beautiful |
Token ID | 4950 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
aces | +0.003 |
uries | +0.002 |
ests | +0.002 |
oll | +0.002 |
ooter | +0.002 |
Neg logit contributions | |
M | -0.002 |
Suz | -0.002 |
Bee | -0.002 |
Mia | -0.002 |
crocod | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
aces | +0.012 |
ooter | +0.011 |
uries | +0.010 |
ests | +0.010 |
ival | +0.010 |
Neg logit contributions | |
Suz | -0.005 |
M | -0.005 |
Bee | -0.005 |
Mia | -0.005 |
Andy | -0.004 |
Token | family |
Token ID | 1641 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
Suz | +0.035 |
Joe | +0.033 |
Andy | +0.032 |
Maria | +0.031 |
Bee | +0.031 |
Neg logit contributions | |
aces | -0.046 |
ooter | -0.040 |
ival | -0.039 |
bracelet | -0.039 |
oll | -0.038 |
Token | who |
Token ID | 508 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
aces | +0.044 |
ooter | +0.037 |
uries | +0.036 |
ests | +0.035 |
ival | +0.034 |
Neg logit contributions | |
Suz | -0.022 |
Bee | -0.022 |
M | -0.021 |
Andy | -0.020 |
Joe | -0.020 |
Token | really |
Token ID | 1107 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
M | +0.020 |
Suz | +0.020 |
Bee | +0.019 |
Mia | +0.019 |
Joe | +0.019 |
Neg logit contributions | |
aces | -0.048 |
ooter | -0.042 |
ival | -0.040 |
uries | -0.039 |
lor | -0.039 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
aces | +0.031 |
ooter | +0.026 |
uries | +0.025 |
ests | +0.025 |
lor | +0.025 |
Neg logit contributions | |
Suz | -0.014 |
M | -0.014 |
Bee | -0.014 |
Mia | -0.014 |
Joe | -0.013 |
Token | pic |
Token ID | 8301 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
aces | +0.064 |
ooter | +0.051 |
uries | +0.051 |
ests | +0.050 |
ival | +0.049 |
Neg logit contributions | |
Suz | -0.037 |
Bee | -0.036 |
M | -0.035 |
Andy | -0.034 |
Mia | -0.034 |
Token | n |
Token ID | 77 |
Feature activation | -6.38e-02 |
Pos logit contributions | |
aces | +0.200 |
ooter | +0.146 |
ests | +0.144 |
oll | +0.136 |
uries | +0.135 |
Neg logit contributions | |
Suz | -0.285 |
Andy | -0.280 |
Bee | -0.278 |
M | -0.276 |
Joe | -0.275 |
Token | ics |
Token ID | 873 |
Feature activation | -5.61e-02 |
Pos logit contributions | |
aces | +0.083 |
ooter | +0.055 |
uries | +0.054 |
ests | +0.051 |
ival | +0.050 |
Neg logit contributions | |
Suz | -0.165 |
Bee | -0.162 |
M | -0.161 |
Andy | -0.159 |
Joe | -0.159 |
Token | . |
Token ID | 13 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
aces | +0.171 |
ooter | +0.152 |
uries | +0.148 |
ival | +0.146 |
ests | +0.142 |
Neg logit contributions | |
M | -0.047 |
Bee | -0.045 |
Suz | -0.045 |
its | -0.044 |
Mia | -0.043 |
Token | They |
Token ID | 1119 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
aces | +0.073 |
ooter | +0.061 |
uries | +0.060 |
ival | +0.059 |
ests | +0.059 |
Neg logit contributions | |
M | -0.030 |
Suz | -0.030 |
Bee | -0.029 |
Mia | -0.028 |
Joe | -0.028 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
aces | +0.062 |
ooter | +0.053 |
uries | +0.052 |
ests | +0.050 |
lor | +0.050 |
Neg logit contributions | |
M | -0.031 |
Suz | -0.030 |
Bee | -0.029 |
Joe | -0.028 |
Andy | -0.028 |
Token | dogs |
Token ID | 6844 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
aces | +0.069 |
uries | +0.060 |
ival | +0.060 |
ooter | +0.060 |
atmeal | +0.058 |
Neg logit contributions | |
Suz | -0.024 |
M | -0.024 |
Bee | -0.023 |
Mia | -0.023 |
Andy | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -6.90e-03 |
Pos logit contributions | |
aces | +0.098 |
ooter | +0.086 |
uries | +0.085 |
ests | +0.085 |
ival | +0.084 |
Neg logit contributions | |
Mia | -0.023 |
Bee | -0.023 |
M | -0.022 |
its | -0.021 |
Andy | -0.021 |
Token | You |
Token ID | 921 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
aces | +0.017 |
ooter | +0.014 |
uries | +0.014 |
ests | +0.013 |
ival | +0.013 |
Neg logit contributions | |
Suz | -0.010 |
Bee | -0.010 |
M | -0.010 |
Mia | -0.009 |
Andy | -0.009 |
Token | have |
Token ID | 423 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
aces | +0.140 |
ests | +0.124 |
lor | +0.121 |
ooter | +0.121 |
seek | +0.119 |
Neg logit contributions | |
Bee | -0.054 |
M | -0.051 |
Suz | -0.049 |
Mia | -0.049 |
Sam | -0.048 |
Token | regular |
Token ID | 3218 |
Feature activation | -3.59e-02 |
Pos logit contributions | |
aces | +0.088 |
ooter | +0.076 |
uries | +0.074 |
ests | +0.074 |
ival | +0.074 |
Neg logit contributions | |
M | -0.032 |
Mia | -0.031 |
Bee | -0.031 |
Suz | -0.029 |
its | -0.029 |
Token | coll |
Token ID | 2927 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
aces | +0.064 |
ival | +0.058 |
oll | +0.054 |
lor | +0.054 |
uries | +0.053 |
Neg logit contributions | |
Suz | -0.068 |
M | -0.067 |
Mia | -0.067 |
Bee | -0.065 |
Sam | -0.065 |
Token | ars |
Token ID | 945 |
Feature activation | -4.54e-03 |
Pos logit contributions | |
aces | +0.144 |
atmeal | +0.134 |
ival | +0.128 |
mall | +0.128 |
ooter | +0.128 |
Neg logit contributions | |
Sam | -0.258 |
Bee | -0.249 |
its | -0.246 |
Suz | -0.245 |
Mia | -0.244 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
aces | +0.013 |
uries | +0.011 |
ooter | +0.011 |
ests | +0.011 |
ival | +0.011 |
Neg logit contributions | |
M | -0.004 |
Mia | -0.004 |
Bee | -0.004 |
Suz | -0.004 |
its | -0.004 |
Token | You |
Token ID | 921 |
Feature activation | -4.96e-02 |
Pos logit contributions | |
aces | +0.026 |
ooter | +0.022 |
uries | +0.021 |
ests | +0.021 |
ival | +0.021 |
Neg logit contributions | |
Suz | -0.015 |
Bee | -0.015 |
M | -0.015 |
Mia | -0.014 |
Andy | -0.014 |
Token | are |
Token ID | 389 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
aces | +0.136 |
ests | +0.120 |
ooter | +0.119 |
lor | +0.118 |
seek | +0.115 |
Neg logit contributions | |
Bee | -0.050 |
M | -0.047 |
scared | -0.046 |
Mia | -0.045 |
Sam | -0.045 |
Token | cute |
Token ID | 13779 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
aces | +0.064 |
ooter | +0.055 |
ests | +0.054 |
uries | +0.053 |
ival | +0.053 |
Neg logit contributions | |
Bee | -0.025 |
M | -0.025 |
Suz | -0.025 |
Mia | -0.024 |
Andy | -0.023 |
Token | called |
Token ID | 1444 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
Suz | +0.010 |
Joe | +0.010 |
Andy | +0.010 |
Bee | +0.010 |
Doug | +0.010 |
Neg logit contributions | |
aces | -0.014 |
ooter | -0.012 |
uries | -0.011 |
oll | -0.011 |
rides | -0.011 |
Token | Daisy |
Token ID | 40355 |
Feature activation | -4.63e-03 |
Pos logit contributions | |
aces | +0.066 |
uries | +0.056 |
ooter | +0.056 |
ests | +0.053 |
ival | +0.053 |
Neg logit contributions | |
Suz | -0.020 |
Bee | -0.020 |
M | -0.019 |
Andy | -0.019 |
Joe | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
aces | +0.011 |
ooter | +0.009 |
uries | +0.009 |
ests | +0.009 |
oll | +0.009 |
Neg logit contributions | |
Suz | -0.007 |
Bee | -0.006 |
Andy | -0.006 |
Joe | -0.006 |
M | -0.006 |
Token | Daisy |
Token ID | 40355 |
Feature activation | -3.58e-03 |
Pos logit contributions | |
aces | +0.089 |
ooter | +0.074 |
uries | +0.073 |
ests | +0.071 |
ival | +0.071 |
Neg logit contributions | |
Suz | -0.044 |
Bee | -0.043 |
M | -0.043 |
Andy | -0.041 |
Mia | -0.041 |
Token | loved |
Token ID | 6151 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
aces | +0.010 |
ooter | +0.008 |
uries | +0.008 |
ests | +0.008 |
ival | +0.008 |
Neg logit contributions | |
M | -0.004 |
Suz | -0.004 |
Bee | -0.004 |
Mia | -0.004 |
Andy | -0.004 |
Token | Wed |
Token ID | 3300 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
aces | +0.090 |
uries | +0.075 |
ooter | +0.075 |
ival | +0.073 |
ests | +0.072 |
Neg logit contributions | |
M | -0.035 |
Suz | -0.034 |
Bee | -0.034 |
Mia | -0.032 |
Andy | -0.032 |
Token | nes |
Token ID | 2516 |
Feature activation | -4.62e-02 |
Pos logit contributions | |
aces | +0.138 |
ests | +0.090 |
sweets | +0.077 |
ooter | +0.076 |
cand | +0.076 |
Neg logit contributions | |
Suz | -0.348 |
Bee | -0.327 |
Andy | -0.323 |
M | -0.321 |
Maria | -0.319 |
Token | days |
Token ID | 12545 |
Feature activation | -7.58e-02 |
Pos logit contributions | |
aces | +0.073 |
ooter | +0.055 |
uries | +0.054 |
ests | +0.048 |
seek | +0.046 |
Neg logit contributions | |
Bee | -0.104 |
Andy | -0.100 |
M | -0.100 |
Suz | -0.100 |
Farmer | -0.100 |
Token | because |
Token ID | 780 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
aces | +0.228 |
ooter | +0.193 |
uries | +0.191 |
ests | +0.189 |
ival | +0.189 |
Neg logit contributions | |
M | -0.076 |
Suz | -0.073 |
Joe | -0.065 |
Andy | -0.065 |
Mia | -0.065 |
Token | on |
Token ID | 319 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
aces | +0.034 |
ooter | +0.029 |
uries | +0.028 |
ests | +0.028 |
ival | +0.027 |
Neg logit contributions | |
Suz | -0.016 |
Bee | -0.015 |
M | -0.015 |
Andy | -0.015 |
Mia | -0.015 |
Token | Wed |
Token ID | 3300 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
aces | +0.065 |
uries | +0.057 |
ooter | +0.056 |
ests | +0.054 |
ival | +0.054 |
Neg logit contributions | |
M | -0.019 |
Mia | -0.018 |
Suz | -0.017 |
Joe | -0.016 |
Bee | -0.016 |
Token | dogs |
Token ID | 6844 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
aces | +0.062 |
uries | +0.054 |
ival | +0.053 |
ooter | +0.053 |
ests | +0.052 |
Neg logit contributions | |
Suz | -0.022 |
M | -0.022 |
Bee | -0.021 |
Mia | -0.021 |
Andy | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -5.43e-03 |
Pos logit contributions | |
aces | +0.097 |
ests | +0.085 |
uries | +0.085 |
ooter | +0.085 |
ival | +0.084 |
Neg logit contributions | |
Mia | -0.023 |
Bee | -0.022 |
M | -0.022 |
Andy | -0.021 |
its | -0.021 |
Token | You |
Token ID | 921 |
Feature activation | -4.88e-02 |
Pos logit contributions | |
aces | +0.013 |
ooter | +0.011 |
uries | +0.010 |
ival | +0.010 |
ests | +0.010 |
Neg logit contributions | |
Suz | -0.008 |
Bee | -0.008 |
M | -0.008 |
Mia | -0.008 |
Andy | -0.008 |
Token | have |
Token ID | 423 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
aces | +0.133 |
ests | +0.113 |
seek | +0.111 |
lor | +0.111 |
ooter | +0.110 |
Neg logit contributions | |
Bee | -0.055 |
M | -0.053 |
Suz | -0.053 |
Mia | -0.052 |
Andy | -0.052 |
Token | regular |
Token ID | 3218 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
aces | +0.077 |
ooter | +0.065 |
uries | +0.064 |
ests | +0.063 |
ival | +0.063 |
Neg logit contributions | |
Suz | -0.029 |
M | -0.029 |
Bee | -0.029 |
Mia | -0.028 |
Andy | -0.027 |
Token | coll |
Token ID | 2927 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
aces | +0.062 |
ival | +0.049 |
uries | +0.049 |
ooter | +0.048 |
oll | +0.048 |
Neg logit contributions | |
Suz | -0.065 |
M | -0.064 |
Bee | -0.063 |
Mia | -0.062 |
Andy | -0.062 |
Token | ars |
Token ID | 945 |
Feature activation | -4.08e-03 |
Pos logit contributions | |
aces | +0.149 |
atmeal | +0.136 |
ival | +0.132 |
ooter | +0.130 |
sweets | +0.128 |
Neg logit contributions | |
Sam | -0.257 |
Bee | -0.247 |
Liz | -0.245 |
Suz | -0.244 |
its | -0.243 |
Token | . |
Token ID | 13 |
Feature activation | -9.33e-03 |
Pos logit contributions | |
aces | +0.012 |
uries | +0.010 |
ooter | +0.010 |
ests | +0.010 |
ival | +0.010 |
Neg logit contributions | |
M | -0.004 |
Mia | -0.004 |
Suz | -0.004 |
Bee | -0.004 |
its | -0.003 |
Token | You |
Token ID | 921 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
aces | +0.022 |
ooter | +0.018 |
uries | +0.018 |
ival | +0.017 |
ests | +0.017 |
Neg logit contributions | |
Suz | -0.014 |
Bee | -0.014 |
M | -0.014 |
Mia | -0.014 |
Andy | -0.014 |
Token | are |
Token ID | 389 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
aces | +0.131 |
ests | +0.112 |
lor | +0.111 |
seek | +0.111 |
ooter | +0.110 |
Neg logit contributions | |
Bee | -0.052 |
M | -0.050 |
Mia | -0.049 |
Suz | -0.048 |
Sam | -0.048 |
Token | not |
Token ID | 407 |
Feature activation | +5.18e-02 |
Pos logit contributions | |
aces | +0.055 |
ooter | +0.045 |
uries | +0.045 |
ests | +0.044 |
ival | +0.044 |
Neg logit contributions | |
Suz | -0.025 |
Bee | -0.025 |
M | -0.024 |
Andy | -0.023 |
Mia | -0.023 |
Token | Wed |
Token ID | 3300 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
aces | +0.090 |
uries | +0.075 |
ooter | +0.075 |
ival | +0.073 |
ests | +0.072 |
Neg logit contributions | |
M | -0.035 |
Suz | -0.034 |
Bee | -0.034 |
Mia | -0.032 |
Andy | -0.032 |
Token | nes |
Token ID | 2516 |
Feature activation | -4.62e-02 |
Pos logit contributions | |
aces | +0.138 |
ests | +0.090 |
sweets | +0.077 |
ooter | +0.076 |
cand | +0.076 |
Neg logit contributions | |
Suz | -0.348 |
Bee | -0.327 |
Andy | -0.323 |
M | -0.321 |
Maria | -0.319 |
Token | days |
Token ID | 12545 |
Feature activation | -7.58e-02 |
Pos logit contributions | |
aces | +0.073 |
ooter | +0.055 |
uries | +0.054 |
ests | +0.048 |
seek | +0.046 |
Neg logit contributions | |
Bee | -0.104 |
Andy | -0.100 |
M | -0.100 |
Suz | -0.100 |
Farmer | -0.100 |
Token | because |
Token ID | 780 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
aces | +0.228 |
ooter | +0.193 |
uries | +0.191 |
ests | +0.189 |
ival | +0.189 |
Neg logit contributions | |
M | -0.076 |
Suz | -0.073 |
Joe | -0.065 |
Andy | -0.065 |
Mia | -0.065 |
Token | on |
Token ID | 319 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
aces | +0.034 |
ooter | +0.029 |
uries | +0.028 |
ests | +0.028 |
ival | +0.027 |
Neg logit contributions | |
Suz | -0.016 |
Bee | -0.015 |
M | -0.015 |
Andy | -0.015 |
Mia | -0.015 |
Token | Wed |
Token ID | 3300 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
aces | +0.065 |
uries | +0.057 |
ooter | +0.056 |
ests | +0.054 |
ival | +0.054 |
Neg logit contributions | |
M | -0.019 |
Mia | -0.018 |
Suz | -0.017 |
Joe | -0.016 |
Bee | -0.016 |
Token | nes |
Token ID | 2516 |
Feature activation | -3.97e-02 |
Pos logit contributions | |
aces | +0.156 |
ests | +0.116 |
cand | +0.109 |
sweets | +0.106 |
ooter | +0.104 |
Neg logit contributions | |
Suz | -0.306 |
Maria | -0.289 |
Mia | -0.287 |
Bee | -0.287 |
Andy | -0.287 |
Token | days |
Token ID | 12545 |
Feature activation | -7.04e-02 |
Pos logit contributions | |
aces | +0.063 |
uries | +0.047 |
ooter | +0.047 |
ests | +0.043 |
seek | +0.040 |
Neg logit contributions | |
Bee | -0.090 |
Andy | -0.086 |
M | -0.086 |
Suz | -0.086 |
Farmer | -0.086 |
Token | she |
Token ID | 673 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
aces | +0.210 |
ooter | +0.180 |
uries | +0.179 |
lor | +0.178 |
ode | +0.178 |
Neg logit contributions | |
M | -0.073 |
Suz | -0.072 |
Mia | -0.062 |
Joe | -0.062 |
Liz | -0.060 |
Token | did |
Token ID | 750 |
Feature activation | -6.83e-02 |
Pos logit contributions | |
aces | +0.081 |
ooter | +0.068 |
uries | +0.067 |
ests | +0.065 |
ival | +0.064 |
Neg logit contributions | |
M | -0.036 |
Suz | -0.035 |
Bee | -0.034 |
Mia | -0.033 |
Joe | -0.032 |
Token | something |
Token ID | 1223 |
Feature activation | -5.60e-03 |
Pos logit contributions | |
aces | +0.188 |
ooter | +0.158 |
uries | +0.155 |
ests | +0.153 |
oll | +0.152 |
Neg logit contributions | |
Suz | -0.079 |
M | -0.078 |
Mia | -0.075 |
Bee | -0.074 |
Joe | -0.072 |
Token | about |
Token ID | 546 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
aces | +0.101 |
ooter | +0.082 |
uries | +0.081 |
ests | +0.079 |
ival | +0.077 |
Neg logit contributions | |
Suz | -0.063 |
Bee | -0.061 |
M | -0.061 |
Andy | -0.059 |
Joe | -0.058 |
Token | we |
Token ID | 356 |
Feature activation | -5.20e-02 |
Pos logit contributions | |
M | +0.029 |
Suz | +0.029 |
Bee | +0.028 |
Andy | +0.028 |
Joe | +0.028 |
Neg logit contributions | |
aces | -0.073 |
ooter | -0.061 |
ests | -0.060 |
uries | -0.060 |
oll | -0.059 |
Token | have |
Token ID | 423 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
aces | +0.137 |
ests | +0.111 |
ooter | +0.108 |
oll | +0.106 |
uries | +0.105 |
Neg logit contributions | |
M | -0.073 |
Suz | -0.072 |
Joe | -0.071 |
Bee | -0.070 |
Andy | -0.070 |
Token | our |
Token ID | 674 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
aces | +0.107 |
ooter | +0.093 |
ests | +0.090 |
oll | +0.089 |
uries | +0.089 |
Neg logit contributions | |
M | -0.036 |
Joe | -0.035 |
Suz | -0.033 |
Mia | -0.033 |
its | -0.032 |
Token | own |
Token ID | 898 |
Feature activation | -7.32e-02 |
Pos logit contributions | |
aces | +0.234 |
oll | +0.178 |
lor | +0.177 |
ests | +0.171 |
uries | +0.171 |
Neg logit contributions | |
M | -0.182 |
Joe | -0.174 |
Andy | -0.170 |
crocod | -0.166 |
Suz | -0.164 |
Token | carn |
Token ID | 18466 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
aces | +0.155 |
oll | +0.120 |
uries | +0.114 |
ests | +0.113 |
ooter | +0.107 |
Neg logit contributions | |
M | -0.136 |
Joe | -0.132 |
Suz | -0.129 |
Andy | -0.127 |
Mia | -0.123 |
Token | ival |
Token ID | 2473 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
aces | +0.156 |
ode | +0.096 |
uries | +0.090 |
cand | +0.087 |
ities | +0.086 |
Neg logit contributions | |
Mia | -0.274 |
surprised | -0.261 |
swift | -0.261 |
Joe | -0.257 |
crocod | -0.255 |
Token | at |
Token ID | 379 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
aces | +0.087 |
uries | +0.070 |
oll | +0.070 |
ooter | +0.070 |
ests | +0.069 |
Neg logit contributions | |
M | -0.033 |
Mia | -0.032 |
Joe | -0.032 |
Suz | -0.032 |
Andy | -0.031 |
Token | home |
Token ID | 1363 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
aces | +0.067 |
ooter | +0.056 |
uries | +0.056 |
ests | +0.055 |
oll | +0.054 |
Neg logit contributions | |
Suz | -0.023 |
M | -0.023 |
Bee | -0.022 |
Mia | -0.021 |
Joe | -0.021 |
Token | ? |
Token ID | 30 |
Feature activation | -8.86e-03 |
Pos logit contributions | |
aces | +0.066 |
ooter | +0.055 |
uries | +0.054 |
ests | +0.053 |
ival | +0.053 |
Neg logit contributions | |
Suz | -0.031 |
Bee | -0.030 |
M | -0.029 |
Andy | -0.028 |
Joe | -0.028 |
Token | We |
Token ID | 775 |
Feature activation | -5.56e-02 |
Pos logit contributions | |
aces | +0.024 |
ooter | +0.020 |
uries | +0.019 |
ests | +0.019 |
oll | +0.019 |
Neg logit contributions | |
M | -0.011 |
Suz | -0.011 |
Bee | -0.011 |
Andy | -0.010 |
Mia | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +4.28e-03 |
Pos logit contributions | |
Suz | +0.012 |
M | +0.011 |
Bee | +0.011 |
Mia | +0.010 |
Andy | +0.010 |
Neg logit contributions | |
aces | -0.025 |
rides | -0.020 |
sweets | -0.019 |
uries | -0.019 |
ooter | -0.019 |
Token | It |
Token ID | 632 |
Feature activation | +3.35e-02 |
Pos logit contributions | |
Suz | +0.005 |
Bee | +0.005 |
M | +0.005 |
Andy | +0.005 |
Joe | +0.005 |
Neg logit contributions | |
aces | -0.011 |
ooter | -0.009 |
uries | -0.009 |
ests | -0.009 |
ival | -0.009 |
Token | made |
Token ID | 925 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
Suz | +0.051 |
Joe | +0.047 |
M | +0.046 |
Farmer | +0.046 |
Maria | +0.045 |
Neg logit contributions | |
aces | -0.072 |
case | -0.058 |
rides | -0.056 |
uries | -0.054 |
nes | -0.054 |
Token | a |
Token ID | 257 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
Suz | +0.033 |
Bee | +0.031 |
M | +0.030 |
Joe | +0.029 |
Andy | +0.028 |
Neg logit contributions | |
aces | -0.078 |
rides | -0.063 |
uries | -0.062 |
ival | -0.062 |
sweets | -0.062 |
Token | loud |
Token ID | 7812 |
Feature activation | +6.42e-02 |
Pos logit contributions | |
Suz | +0.044 |
Joe | +0.041 |
Jen | +0.038 |
Liz | +0.038 |
Maria | +0.037 |
Neg logit contributions | |
case | -0.049 |
aces | -0.047 |
medal | -0.045 |
cand | -0.045 |
bracelet | -0.044 |
Token | noise |
Token ID | 7838 |
Feature activation | +7.90e-02 |
Pos logit contributions | |
Suz | +0.111 |
M | +0.106 |
Joe | +0.100 |
Bee | +0.099 |
Jen | +0.099 |
Neg logit contributions | |
aces | -0.118 |
rides | -0.096 |
ooter | -0.092 |
hell | -0.089 |
cand | -0.089 |
Token | like |
Token ID | 588 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
Suz | +0.119 |
Bee | +0.115 |
M | +0.112 |
Mia | +0.106 |
Andy | +0.106 |
Neg logit contributions | |
aces | -0.184 |
uries | -0.145 |
ooter | -0.145 |
rides | -0.143 |
ival | -0.138 |
Token | " |
Token ID | 366 |
Feature activation | -9.88e-03 |
Pos logit contributions | |
Suz | +0.026 |
Bee | +0.024 |
M | +0.024 |
Andy | +0.023 |
Mia | +0.022 |
Neg logit contributions | |
aces | -0.062 |
ooter | -0.051 |
uries | -0.051 |
ival | -0.050 |
ests | -0.050 |
Token | pop |
Token ID | 12924 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
aces | +0.022 |
ooter | +0.017 |
uries | +0.017 |
ests | +0.016 |
ival | +0.016 |
Neg logit contributions | |
Suz | -0.017 |
Bee | -0.017 |
M | -0.017 |
Andy | -0.016 |
Mia | -0.016 |
Token | " |
Token ID | 1 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
Bee | +0.026 |
Suz | +0.026 |
M | +0.025 |
Andy | +0.024 |
Joe | +0.024 |
Neg logit contributions | |
aces | -0.047 |
ooter | -0.040 |
uries | -0.039 |
ests | -0.038 |
ival | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
aces | +0.071 |
uries | +0.060 |
ooter | +0.059 |
ests | +0.057 |
ival | +0.057 |
Neg logit contributions | |
Suz | -0.035 |
M | -0.034 |
Bee | -0.034 |
Mia | -0.032 |
Joe | -0.032 |
Token | he |
Token ID | 339 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
aces | +0.038 |
ooter | +0.032 |
uries | +0.032 |
ests | +0.031 |
ival | +0.031 |
Neg logit contributions | |
Suz | -0.016 |
M | -0.015 |
Bee | -0.015 |
Andy | -0.015 |
Joe | -0.015 |
Token | could |
Token ID | 714 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
aces | +0.072 |
ooter | +0.061 |
ests | +0.060 |
uries | +0.059 |
ival | +0.058 |
Neg logit contributions | |
M | -0.035 |
Suz | -0.035 |
Bee | -0.034 |
Joe | -0.034 |
Andy | -0.033 |
Token | get |
Token ID | 651 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
aces | +0.135 |
ival | +0.112 |
ests | +0.111 |
ooter | +0.109 |
uries | +0.108 |
Neg logit contributions | |
Suz | -0.072 |
M | -0.071 |
Bee | -0.068 |
Mia | -0.066 |
Joe | -0.066 |
Token | his |
Token ID | 465 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
Suz | +0.013 |
M | +0.013 |
Bee | +0.012 |
Mia | +0.012 |
Joe | +0.012 |
Neg logit contributions | |
aces | -0.037 |
ooter | -0.031 |
uries | -0.031 |
ests | -0.031 |
ival | -0.030 |
Token | feather |
Token ID | 17972 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
aces | +0.153 |
uries | +0.131 |
ival | +0.128 |
ests | +0.128 |
seek | +0.127 |
Neg logit contributions | |
M | -0.093 |
Suz | -0.089 |
Bee | -0.089 |
its | -0.088 |
Joe | -0.084 |
Token | out |
Token ID | 503 |
Feature activation | +8.38e-02 |
Pos logit contributions | |
aces | +0.085 |
ival | +0.076 |
uries | +0.075 |
ests | +0.074 |
seek | +0.070 |
Neg logit contributions | |
Suz | -0.048 |
its | -0.048 |
M | -0.047 |
Bee | -0.047 |
Andy | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | -6.16e-03 |
Pos logit contributions | |
Suz | +0.101 |
Bee | +0.099 |
M | +0.097 |
Andy | +0.093 |
Joe | +0.092 |
Neg logit contributions | |
aces | -0.226 |
ooter | -0.188 |
uries | -0.186 |
ests | -0.182 |
ival | -0.180 |
Token | they |
Token ID | 484 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
aces | +0.014 |
ooter | +0.012 |
uries | +0.012 |
ests | +0.011 |
ival | +0.011 |
Neg logit contributions | |
Suz | -0.010 |
Bee | -0.009 |
M | -0.009 |
Andy | -0.009 |
Joe | -0.009 |
Token | could |
Token ID | 714 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
aces | +0.035 |
ooter | +0.029 |
uries | +0.029 |
ival | +0.028 |
ests | +0.028 |
Neg logit contributions | |
Suz | -0.022 |
M | -0.022 |
Bee | -0.021 |
Andy | -0.020 |
Joe | -0.020 |
Token | have |
Token ID | 423 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
aces | +0.093 |
ooter | +0.076 |
ival | +0.075 |
ests | +0.075 |
uries | +0.074 |
Neg logit contributions | |
Suz | -0.053 |
M | -0.052 |
Bee | -0.051 |
Andy | -0.050 |
Joe | -0.049 |
Token | lots |
Token ID | 6041 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
aces | +0.100 |
ooter | +0.088 |
uries | +0.086 |
ests | +0.082 |
ival | +0.082 |
Neg logit contributions | |
Suz | -0.045 |
its | -0.044 |
M | -0.044 |
Mia | -0.043 |
Joe | -0.042 |
Token | kind |
Token ID | 1611 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
Suz | +0.083 |
M | +0.078 |
Bee | +0.077 |
Joe | +0.077 |
Andy | +0.076 |
Neg logit contributions | |
aces | -0.149 |
ooter | -0.130 |
ival | -0.128 |
bracelet | -0.121 |
sweets | -0.121 |
Token | zo |
Token ID | 40565 |
Feature activation | +4.28e-02 |
Pos logit contributions | |
Suz | +0.052 |
Bee | +0.050 |
M | +0.050 |
Andy | +0.049 |
Ali | +0.048 |
Neg logit contributions | |
aces | -0.076 |
ooter | -0.065 |
ival | -0.059 |
oll | -0.059 |
uries | -0.059 |
Token | oke |
Token ID | 2088 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
Suz | +0.049 |
M | +0.047 |
Bee | +0.047 |
Andy | +0.045 |
Joe | +0.044 |
Neg logit contributions | |
aces | -0.119 |
ooter | -0.100 |
uries | -0.097 |
ival | -0.096 |
ests | -0.096 |
Token | eper |
Token ID | 5723 |
Feature activation | +6.84e-02 |
Pos logit contributions | |
Suz | +0.039 |
M | +0.039 |
Bee | +0.038 |
Andy | +0.037 |
Joe | +0.036 |
Neg logit contributions | |
aces | -0.043 |
ooter | -0.033 |
ests | -0.031 |
uries | -0.030 |
ival | -0.030 |
Token | came |
Token ID | 1625 |
Feature activation | +7.20e-02 |
Pos logit contributions | |
Suz | +0.082 |
Bee | +0.079 |
M | +0.078 |
Andy | +0.074 |
Mia | +0.073 |
Neg logit contributions | |
aces | -0.183 |
ooter | -0.153 |
uries | -0.147 |
ival | -0.146 |
ests | -0.145 |
Token | up |
Token ID | 510 |
Feature activation | +9.73e-02 |
Pos logit contributions | |
Suz | +0.114 |
Bee | +0.110 |
Mia | +0.106 |
M | +0.106 |
boiling | +0.105 |
Neg logit contributions | |
aces | -0.148 |
ooter | -0.121 |
uries | -0.114 |
rides | -0.110 |
seek | -0.109 |
Token | to |
Token ID | 284 |
Feature activation | +7.64e-02 |
Pos logit contributions | |
Suz | +0.161 |
Bee | +0.154 |
Andy | +0.146 |
Liz | +0.146 |
Ali | +0.145 |
Neg logit contributions | |
aces | -0.197 |
seek | -0.158 |
ooter | -0.156 |
rides | -0.155 |
uries | -0.154 |
Token | them |
Token ID | 606 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
Suz | +0.089 |
Bee | +0.087 |
Ali | +0.082 |
M | +0.081 |
boiling | +0.080 |
Neg logit contributions | |
aces | -0.175 |
sweets | -0.154 |
uries | -0.152 |
rides | -0.151 |
parties | -0.149 |
Token | and |
Token ID | 290 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
M | +0.025 |
Suz | +0.024 |
Joe | +0.023 |
Bee | +0.023 |
Andy | +0.023 |
Neg logit contributions | |
aces | -0.081 |
ests | -0.070 |
ooter | -0.069 |
uries | -0.068 |
ival | -0.067 |
Token | said |
Token ID | 531 |
Feature activation | +4.98e-03 |
Pos logit contributions | |
Suz | +0.029 |
Bee | +0.029 |
Ali | +0.027 |
M | +0.026 |
boiling | +0.026 |
Neg logit contributions | |
aces | -0.044 |
sweets | -0.039 |
ival | -0.039 |
rides | -0.039 |
cand | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
Suz | +0.006 |
Bee | +0.006 |
M | +0.005 |
Andy | +0.005 |
Ali | +0.005 |
Neg logit contributions | |
aces | -0.013 |
ooter | -0.011 |
ival | -0.011 |
uries | -0.011 |
sweets | -0.010 |
Token | her |
Token ID | 607 |
Feature activation | -7.52e-03 |
Pos logit contributions | |
Bee | +0.082 |
Suz | +0.082 |
crocod | +0.077 |
swarm | +0.077 |
booming | +0.076 |
Neg logit contributions | |
aces | -0.173 |
ooter | -0.139 |
ests | -0.136 |
oll | -0.135 |
sweets | -0.134 |
Token | hand |
Token ID | 1021 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
aces | +0.019 |
ests | +0.016 |
uries | +0.015 |
ival | +0.015 |
ooter | +0.015 |
Neg logit contributions | |
M | -0.011 |
Bee | -0.010 |
Mia | -0.010 |
Suz | -0.010 |
Andy | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
M | +0.056 |
Suz | +0.055 |
Bee | +0.054 |
Mia | +0.051 |
Andy | +0.050 |
Neg logit contributions | |
aces | -0.148 |
uries | -0.126 |
ooter | -0.126 |
ests | -0.125 |
ival | -0.125 |
Token | It |
Token ID | 632 |
Feature activation | +4.40e-02 |
Pos logit contributions | |
Suz | +0.043 |
Bee | +0.042 |
Andy | +0.041 |
Joe | +0.040 |
M | +0.039 |
Neg logit contributions | |
aces | -0.057 |
ooter | -0.044 |
uries | -0.043 |
ests | -0.042 |
oll | -0.042 |
Token | was |
Token ID | 373 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
Suz | +0.060 |
Joe | +0.059 |
Andy | +0.056 |
Bee | +0.056 |
Maria | +0.055 |
Neg logit contributions | |
aces | -0.106 |
oll | -0.084 |
rides | -0.084 |
ooter | -0.083 |
case | -0.083 |
Token | not |
Token ID | 407 |
Feature activation | +8.11e-02 |
Pos logit contributions | |
Suz | +0.050 |
Bee | +0.048 |
Joe | +0.047 |
Andy | +0.046 |
M | +0.046 |
Neg logit contributions | |
aces | -0.079 |
oll | -0.062 |
ooter | -0.061 |
uries | -0.061 |
sweets | -0.059 |
Token | burned |
Token ID | 11544 |
Feature activation | +8.18e-02 |
Pos logit contributions | |
Suz | +0.111 |
Bee | +0.107 |
M | +0.106 |
Andy | +0.103 |
Mia | +0.102 |
Neg logit contributions | |
aces | -0.206 |
ooter | -0.172 |
uries | -0.171 |
ests | -0.169 |
ival | -0.168 |
Token | . |
Token ID | 13 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
Suz | +0.111 |
Bee | +0.109 |
M | +0.105 |
Andy | +0.103 |
Joe | +0.101 |
Neg logit contributions | |
aces | -0.208 |
ooter | -0.167 |
uries | -0.166 |
ests | -0.161 |
oll | -0.158 |
Token | It |
Token ID | 632 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
Suz | +0.050 |
Bee | +0.049 |
Andy | +0.049 |
M | +0.047 |
Joe | +0.047 |
Neg logit contributions | |
aces | -0.071 |
ooter | -0.055 |
uries | -0.055 |
ests | -0.054 |
oll | -0.053 |
Token | was |
Token ID | 373 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
Suz | +0.063 |
Joe | +0.061 |
Bee | +0.059 |
Andy | +0.058 |
Maria | +0.057 |
Neg logit contributions | |
aces | -0.115 |
ooter | -0.091 |
oll | -0.091 |
rides | -0.091 |
case | -0.090 |
Token | just |
Token ID | 655 |
Feature activation | +7.84e-02 |
Pos logit contributions | |
Suz | +0.051 |
Bee | +0.049 |
Joe | +0.048 |
Andy | +0.047 |
M | +0.047 |
Neg logit contributions | |
aces | -0.083 |
oll | -0.066 |
ooter | -0.064 |
uries | -0.064 |
sweets | -0.062 |
Token | ily |
Token ID | 813 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
Suz | +0.035 |
Mia | +0.034 |
Bee | +0.034 |
M | +0.033 |
Joe | +0.033 |
Neg logit contributions | |
aces | -0.030 |
uries | -0.024 |
ooter | -0.023 |
ival | -0.022 |
ests | -0.022 |
Token | hears |
Token ID | 23180 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
Suz | +0.040 |
Bee | +0.039 |
M | +0.039 |
Andy | +0.037 |
Joe | +0.037 |
Neg logit contributions | |
aces | -0.074 |
ooter | -0.061 |
uries | -0.060 |
ests | -0.059 |
ival | -0.058 |
Token | Tom |
Token ID | 4186 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
Suz | +0.083 |
Bee | +0.079 |
M | +0.076 |
Andy | +0.074 |
Joe | +0.071 |
Neg logit contributions | |
aces | -0.204 |
ooter | -0.168 |
uries | -0.164 |
rides | -0.164 |
ests | -0.164 |
Token | and |
Token ID | 290 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
Suz | +0.015 |
Bee | +0.015 |
M | +0.015 |
Andy | +0.014 |
Joe | +0.014 |
Neg logit contributions | |
aces | -0.029 |
ooter | -0.024 |
uries | -0.023 |
ests | -0.023 |
ival | -0.023 |
Token | looks |
Token ID | 3073 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
Suz | +0.025 |
boiling | +0.024 |
Farmer | +0.023 |
Maria | +0.023 |
Andy | +0.023 |
Neg logit contributions | |
aces | -0.028 |
rides | -0.024 |
ooter | -0.022 |
sweets | -0.019 |
ance | -0.019 |
Token | up |
Token ID | 510 |
Feature activation | +8.58e-02 |
Pos logit contributions | |
Suz | +0.090 |
Bee | +0.088 |
Andy | +0.084 |
Maria | +0.083 |
M | +0.083 |
Neg logit contributions | |
aces | -0.073 |
rides | -0.056 |
ooter | -0.054 |
sweets | -0.046 |
sunglasses | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
Suz | +0.188 |
Andy | +0.180 |
Bee | +0.177 |
Liz | +0.172 |
Ali | +0.170 |
Neg logit contributions | |
aces | -0.131 |
rides | -0.099 |
ooter | -0.088 |
medals | -0.087 |
seek | -0.084 |
Token | She |
Token ID | 1375 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
Suz | +0.036 |
Bee | +0.036 |
M | +0.035 |
Andy | +0.034 |
Joe | +0.033 |
Neg logit contributions | |
aces | -0.048 |
ooter | -0.038 |
uries | -0.036 |
ests | -0.036 |
ival | -0.035 |
Token | sees |
Token ID | 7224 |
Feature activation | +7.40e-02 |
Pos logit contributions | |
Suz | +0.043 |
Andy | +0.038 |
Bee | +0.037 |
Maria | +0.037 |
M | +0.036 |
Neg logit contributions | |
aces | -0.054 |
rides | -0.046 |
ooter | -0.040 |
ival | -0.038 |
pedals | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
Suz | +0.086 |
Bee | +0.083 |
M | +0.079 |
Andy | +0.076 |
Maria | +0.074 |
Neg logit contributions | |
aces | -0.195 |
rides | -0.157 |
ests | -0.157 |
cand | -0.155 |
ooter | -0.153 |
Token | snake |
Token ID | 17522 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
Suz | +0.019 |
M | +0.017 |
Joe | +0.016 |
Andy | +0.016 |
Liz | +0.016 |
Neg logit contributions | |
aces | -0.031 |
ooter | -0.024 |
bracelet | -0.024 |
medal | -0.023 |
rides | -0.023 |
Token | one |
Token ID | 530 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
Bee | +0.027 |
M | +0.027 |
Mia | +0.026 |
Sam | +0.025 |
crocod | +0.025 |
Neg logit contributions | |
aces | -0.040 |
seek | -0.032 |
ooter | -0.031 |
ests | -0.031 |
ival | -0.031 |
Token | who |
Token ID | 508 |
Feature activation | +4.96e-02 |
Pos logit contributions | |
Suz | +0.035 |
Bee | +0.034 |
M | +0.033 |
Andy | +0.032 |
Mia | +0.032 |
Neg logit contributions | |
aces | -0.068 |
ooter | -0.056 |
uries | -0.055 |
ests | -0.054 |
ival | -0.053 |
Token | made |
Token ID | 925 |
Feature activation | +4.50e-03 |
Pos logit contributions | |
Bee | +0.067 |
M | +0.067 |
Suz | +0.067 |
Mia | +0.066 |
Joe | +0.065 |
Neg logit contributions | |
aces | -0.124 |
ooter | -0.103 |
uries | -0.102 |
ests | -0.099 |
seek | -0.097 |
Token | the |
Token ID | 262 |
Feature activation | +2.64e-03 |
Pos logit contributions | |
Suz | +0.005 |
M | +0.005 |
Bee | +0.005 |
Mia | +0.005 |
Joe | +0.005 |
Neg logit contributions | |
aces | -0.013 |
ooter | -0.011 |
uries | -0.010 |
ests | -0.010 |
ival | -0.010 |
Token | test |
Token ID | 1332 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
M | +0.004 |
Mia | +0.004 |
Bee | +0.004 |
Suz | +0.004 |
crocod | +0.004 |
Neg logit contributions | |
aces | -0.006 |
ooter | -0.005 |
seek | -0.005 |
oll | -0.005 |
uries | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
Suz | +0.029 |
Mia | +0.029 |
M | +0.028 |
Bee | +0.027 |
Joe | +0.027 |
Neg logit contributions | |
aces | -0.077 |
uries | -0.066 |
ests | -0.065 |
ooter | -0.065 |
ival | -0.064 |
Token | He |
Token ID | 679 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
Suz | +0.018 |
Bee | +0.018 |
M | +0.017 |
Andy | +0.017 |
Joe | +0.017 |
Neg logit contributions | |
aces | -0.034 |
ooter | -0.027 |
uries | -0.027 |
ests | -0.027 |
ival | -0.026 |
Token | is |
Token ID | 318 |
Feature activation | +5.05e-03 |
Pos logit contributions | |
Bee | +0.016 |
M | +0.016 |
Suz | +0.016 |
Mia | +0.016 |
Joe | +0.015 |
Neg logit contributions | |
aces | -0.034 |
ooter | -0.029 |
uries | -0.029 |
ests | -0.028 |
ival | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
Suz | +0.007 |
Bee | +0.007 |
M | +0.007 |
Andy | +0.007 |
Joe | +0.007 |
Neg logit contributions | |
aces | -0.013 |
uries | -0.010 |
ooter | -0.010 |
oll | -0.010 |
rides | -0.009 |
Token | teacher |
Token ID | 4701 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
Suz | +0.042 |
Bee | +0.040 |
M | +0.040 |
Andy | +0.039 |
Joe | +0.039 |
Neg logit contributions | |
aces | -0.052 |
ooter | -0.043 |
uries | -0.042 |
ival | -0.041 |
ests | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
Mia | +0.020 |
M | +0.019 |
Suz | +0.019 |
Bee | +0.019 |
Joe | +0.018 |
Neg logit contributions | |
aces | -0.060 |
ooter | -0.051 |
ests | -0.051 |
uries | -0.050 |
ival | -0.049 |
Token | when |
Token ID | 618 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
Suz | +0.005 |
Bee | +0.005 |
M | +0.005 |
Andy | +0.005 |
Joe | +0.005 |
Neg logit contributions | |
aces | -0.010 |
ooter | -0.009 |
uries | -0.009 |
ests | -0.008 |
ival | -0.008 |
Token | they |
Token ID | 484 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
Bee | +0.050 |
Suz | +0.048 |
M | +0.046 |
Ali | +0.043 |
Mia | +0.043 |
Neg logit contributions | |
aces | -0.126 |
ooter | -0.107 |
rides | -0.106 |
ival | -0.106 |
uries | -0.105 |
Token | saw |
Token ID | 2497 |
Feature activation | +5.73e-02 |
Pos logit contributions | |
aces | +0.034 |
ooter | +0.029 |
ival | +0.029 |
uries | +0.029 |
ests | +0.028 |
Neg logit contributions | |
Suz | -0.010 |
Bee | -0.010 |
Andy | -0.010 |
M | -0.009 |
Liz | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
Suz | +0.083 |
Bee | +0.083 |
M | +0.080 |
Ali | +0.076 |
Andy | +0.076 |
Neg logit contributions | |
aces | -0.134 |
ooter | -0.107 |
ests | -0.106 |
rides | -0.106 |
ival | -0.105 |
Token | big |
Token ID | 1263 |
Feature activation | +4.83e-02 |
Pos logit contributions | |
Suz | +0.052 |
M | +0.048 |
Bee | +0.048 |
Joe | +0.047 |
Mia | +0.047 |
Neg logit contributions | |
aces | -0.079 |
ooter | -0.073 |
ival | -0.073 |
uries | -0.069 |
bracelet | -0.069 |
Token | , |
Token ID | 11 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
Suz | +0.084 |
Bee | +0.081 |
M | +0.081 |
Ali | +0.077 |
Liz | +0.076 |
Neg logit contributions | |
aces | -0.094 |
ooter | -0.082 |
rides | -0.077 |
sweets | -0.076 |
cand | -0.076 |
Token | scary |
Token ID | 14343 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
Bee | +0.044 |
Suz | +0.043 |
M | +0.041 |
Ali | +0.039 |
Mia | +0.039 |
Neg logit contributions | |
aces | -0.097 |
ooter | -0.082 |
uries | -0.079 |
sweets | -0.078 |
rides | -0.077 |
Token | tiger |
Token ID | 26241 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
Suz | +0.064 |
M | +0.063 |
Bee | +0.060 |
Ali | +0.059 |
Liz | +0.059 |
Neg logit contributions | |
aces | -0.080 |
ooter | -0.069 |
rides | -0.064 |
uries | -0.062 |
cand | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
Suz | +0.045 |
Bee | +0.043 |
M | +0.043 |
Andy | +0.040 |
Joe | +0.040 |
Neg logit contributions | |
aces | -0.087 |
ooter | -0.073 |
uries | -0.071 |
ival | -0.069 |
ests | -0.068 |
Token | The |
Token ID | 383 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
Bee | +0.019 |
boiling | +0.017 |
buzzing | +0.017 |
Ali | +0.017 |
swarm | +0.017 |
Neg logit contributions | |
aces | -0.031 |
ooter | -0.029 |
rides | -0.027 |
uries | -0.027 |
case | -0.026 |
Token | tiger |
Token ID | 26241 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
Suz | +0.049 |
M | +0.046 |
Bee | +0.046 |
Joe | +0.044 |
Mia | +0.044 |
Neg logit contributions | |
aces | -0.069 |
ooter | -0.057 |
uries | -0.055 |
ival | -0.054 |
ests | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
aces | +0.031 |
ooter | +0.026 |
uries | +0.026 |
ests | +0.025 |
ival | +0.025 |
Neg logit contributions | |
Suz | -0.011 |
Bee | -0.011 |
M | -0.011 |
Andy | -0.010 |
Mia | -0.010 |
Token | " |
Token ID | 366 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
Suz | +0.019 |
Bee | +0.018 |
M | +0.017 |
Andy | +0.017 |
Joe | +0.016 |
Neg logit contributions | |
aces | -0.077 |
ooter | -0.066 |
uries | -0.066 |
ival | -0.064 |
ests | -0.063 |
Token | Thank |
Token ID | 10449 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
aces | +0.029 |
ooter | +0.024 |
uries | +0.023 |
ival | +0.022 |
ests | +0.022 |
Neg logit contributions | |
Suz | -0.018 |
M | -0.018 |
Bee | -0.018 |
Andy | -0.017 |
Mia | -0.017 |
Token | you |
Token ID | 345 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
aces | +0.027 |
ooter | +0.022 |
uries | +0.021 |
ests | +0.021 |
ival | +0.020 |
Neg logit contributions | |
Suz | -0.020 |
Bee | -0.019 |
M | -0.019 |
Andy | -0.018 |
Mia | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
aces | +0.097 |
ooter | +0.082 |
uries | +0.081 |
ests | +0.079 |
ival | +0.078 |
Neg logit contributions | |
Suz | -0.036 |
Bee | -0.035 |
M | -0.035 |
Andy | -0.033 |
Joe | -0.033 |
Token | Mom |
Token ID | 11254 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
Suz | +0.014 |
Bee | +0.013 |
M | +0.013 |
Andy | +0.013 |
Mia | +0.012 |
Neg logit contributions | |
aces | -0.040 |
ooter | -0.033 |
uries | -0.033 |
ests | -0.032 |
ival | -0.032 |
Token | my |
Token ID | 1820 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
Suz | +0.048 |
Bee | +0.048 |
M | +0.047 |
Andy | +0.045 |
Joe | +0.045 |
Neg logit contributions | |
aces | -0.071 |
ooter | -0.057 |
uries | -0.056 |
ests | -0.055 |
ival | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
Suz | +0.031 |
Bee | +0.030 |
M | +0.030 |
Andy | +0.028 |
Joe | +0.028 |
Neg logit contributions | |
aces | -0.079 |
ooter | -0.066 |
uries | -0.066 |
ests | -0.064 |
ival | -0.064 |
Token | for |
Token ID | 329 |
Feature activation | -9.76e-03 |
Pos logit contributions | |
M | +0.027 |
Suz | +0.027 |
Bee | +0.027 |
Mia | +0.026 |
Joe | +0.025 |
Neg logit contributions | |
aces | -0.060 |
uries | -0.049 |
ooter | -0.049 |
ests | -0.049 |
seek | -0.048 |
Token | helping |
Token ID | 5742 |
Feature activation | -4.60e-03 |
Pos logit contributions | |
aces | +0.026 |
ooter | +0.021 |
uries | +0.021 |
ests | +0.020 |
ival | +0.020 |
Neg logit contributions | |
Suz | -0.012 |
Bee | -0.012 |
M | -0.012 |
Andy | -0.011 |
Joe | -0.011 |
Token | me |
Token ID | 502 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
aces | +0.013 |
ooter | +0.011 |
uries | +0.011 |
ests | +0.011 |
ival | +0.010 |
Neg logit contributions | |
Suz | -0.005 |
Bee | -0.005 |
M | -0.005 |
Andy | -0.005 |
Mia | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -6.50e-03 |
Pos logit contributions | |
aces | +0.132 |
ests | +0.116 |
ival | +0.114 |
ooter | +0.113 |
lor | +0.113 |
Neg logit contributions | |
Mia | -0.035 |
M | -0.031 |
Sam | -0.030 |
Bee | -0.029 |
Liz | -0.027 |
Token | You |
Token ID | 921 |
Feature activation | -4.93e-02 |
Pos logit contributions | |
aces | +0.016 |
ooter | +0.013 |
ival | +0.013 |
uries | +0.013 |
ests | +0.013 |
Neg logit contributions | |
Suz | -0.010 |
M | -0.010 |
Bee | -0.010 |
Mia | -0.009 |
Andy | -0.009 |
Token | have |
Token ID | 423 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
aces | +0.129 |
ooter | +0.111 |
ests | +0.110 |
lor | +0.109 |
uries | +0.108 |
Neg logit contributions | |
Bee | -0.058 |
M | -0.057 |
Mia | -0.056 |
Sam | -0.055 |
Suz | -0.054 |
Token | me |
Token ID | 502 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
aces | +0.085 |
ooter | +0.073 |
uries | +0.072 |
ival | +0.072 |
ests | +0.071 |
Neg logit contributions | |
M | -0.031 |
Mia | -0.030 |
Suz | -0.030 |
Bee | -0.030 |
its | -0.028 |
Token | ." |
Token ID | 526 |
Feature activation | -2.33e-03 |
Pos logit contributions | |
aces | +0.081 |
ests | +0.070 |
ival | +0.069 |
uries | +0.069 |
lor | +0.069 |
Neg logit contributions | |
M | -0.028 |
Mia | -0.028 |
Suz | -0.027 |
Bee | -0.026 |
its | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
aces | +0.006 |
ooter | +0.005 |
uries | +0.005 |
ests | +0.005 |
ival | +0.005 |
Neg logit contributions | |
Suz | -0.003 |
Bee | -0.003 |
Andy | -0.003 |
M | -0.003 |
Joe | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
Suz | +0.022 |
Bee | +0.021 |
boiling | +0.021 |
Andy | +0.020 |
Joe | +0.020 |
Neg logit contributions | |
aces | -0.030 |
ests | -0.025 |
rides | -0.025 |
ival | -0.024 |
ooter | -0.024 |
Token | She |
Token ID | 3347 |
Feature activation | +9.63e-03 |
Pos logit contributions | |
Suz | +0.032 |
M | +0.031 |
Bee | +0.031 |
Joe | +0.030 |
Andy | +0.030 |
Neg logit contributions | |
aces | -0.037 |
ooter | -0.030 |
uries | -0.029 |
ests | -0.029 |
ival | -0.029 |
Token | hugs |
Token ID | 40657 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
M | +0.012 |
Mia | +0.012 |
Bee | +0.012 |
Suz | +0.012 |
Joe | +0.011 |
Neg logit contributions | |
aces | -0.025 |
uries | -0.021 |
ooter | -0.021 |
ests | -0.020 |
seek | -0.020 |
Token | her |
Token ID | 607 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
Suz | +0.021 |
M | +0.020 |
Bee | +0.020 |
Mia | +0.019 |
Andy | +0.019 |
Neg logit contributions | |
aces | -0.067 |
ooter | -0.057 |
uries | -0.057 |
ival | -0.055 |
ests | -0.055 |
Token | doll |
Token ID | 3654 |
Feature activation | +1.13e-03 |
Pos logit contributions | |
aces | +0.026 |
uries | +0.021 |
ooter | +0.021 |
ival | +0.020 |
ests | +0.020 |
Neg logit contributions | |
Suz | -0.019 |
M | -0.019 |
Bee | -0.019 |
Mia | -0.019 |
Andy | -0.018 |
Token | affe |
Token ID | 21223 |
Feature activation | +3.35e-02 |
Pos logit contributions | |
aces | +0.003 |
uries | +0.002 |
ooter | +0.002 |
ests | +0.002 |
ival | +0.002 |
Neg logit contributions | |
Suz | -0.004 |
Bee | -0.004 |
M | -0.004 |
Andy | -0.004 |
Joe | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +5.07e-03 |
Pos logit contributions | |
Bee | +0.034 |
Suz | +0.033 |
M | +0.033 |
Mia | +0.032 |
Andy | +0.031 |
Neg logit contributions | |
aces | -0.098 |
ooter | -0.084 |
uries | -0.083 |
ests | -0.082 |
ival | -0.081 |
Token | The |
Token ID | 383 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
Suz | +0.007 |
Bee | +0.006 |
M | +0.006 |
Andy | +0.006 |
Mia | +0.006 |
Neg logit contributions | |
aces | -0.013 |
ooter | -0.011 |
uries | -0.011 |
ests | -0.011 |
ival | -0.010 |
Token | gir |
Token ID | 37370 |
Feature activation | +6.47e-03 |
Pos logit contributions | |
Suz | +0.037 |
Bee | +0.036 |
M | +0.036 |
Mia | +0.035 |
Joe | +0.034 |
Neg logit contributions | |
aces | -0.073 |
uries | -0.059 |
ooter | -0.059 |
ests | -0.059 |
ival | -0.058 |
Token | affe |
Token ID | 21223 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
Suz | +0.015 |
Bee | +0.015 |
M | +0.014 |
Andy | +0.014 |
Joe | +0.014 |
Neg logit contributions | |
aces | -0.010 |
uries | -0.008 |
ooter | -0.007 |
ests | -0.007 |
ival | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
Bee | +0.046 |
Suz | +0.046 |
M | +0.045 |
Andy | +0.043 |
Mia | +0.043 |
Neg logit contributions | |
aces | -0.114 |
ooter | -0.097 |
uries | -0.096 |
ests | -0.094 |
ival | -0.091 |
Token | very |
Token ID | 845 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
Suz | +0.020 |
Bee | +0.019 |
M | +0.019 |
Andy | +0.018 |
Joe | +0.018 |
Neg logit contributions | |
aces | -0.029 |
uries | -0.023 |
ooter | -0.023 |
ival | -0.022 |
oll | -0.022 |
Token | tall |
Token ID | 7331 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
Suz | +0.044 |
Bee | +0.043 |
M | +0.043 |
Ali | +0.041 |
Andy | +0.041 |
Neg logit contributions | |
aces | -0.064 |
ooter | -0.053 |
uries | -0.052 |
ival | -0.052 |
oll | -0.049 |
Token | and |
Token ID | 290 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
M | +0.035 |
Bee | +0.034 |
Suz | +0.034 |
Joe | +0.033 |
Mia | +0.033 |
Neg logit contributions | |
aces | -0.111 |
ooter | -0.098 |
uries | -0.096 |
ests | -0.095 |
ival | -0.095 |
Token | had |
Token ID | 550 |
Feature activation | -7.88e-03 |
Pos logit contributions | |
Suz | +0.036 |
Bee | +0.034 |
M | +0.033 |
boiling | +0.032 |
Ali | +0.030 |
Neg logit contributions | |
aces | -0.061 |
sweets | -0.048 |
uries | -0.048 |
ival | -0.047 |
rides | -0.047 |
Token | a |
Token ID | 257 |
Feature activation | -1.94e-04 |
Pos logit contributions | |
aces | +0.020 |
ooter | +0.016 |
uries | +0.016 |
ests | +0.016 |
ival | +0.016 |
Neg logit contributions | |
Suz | -0.011 |
Bee | -0.011 |
M | -0.011 |
Joe | -0.011 |
Andy | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | -1.83e-03 |
Pos logit contributions | |
aces | +0.030 |
ooter | +0.024 |
ests | +0.024 |
rides | +0.024 |
ival | +0.024 |
Neg logit contributions | |
Suz | -0.015 |
Bee | -0.014 |
M | -0.014 |
Andy | -0.013 |
Ali | -0.013 |
Token | buyer |
Token ID | 17872 |
Feature activation | -8.86e-03 |
Pos logit contributions | |
aces | +0.004 |
ooter | +0.004 |
uries | +0.004 |
ival | +0.004 |
ests | +0.003 |
Neg logit contributions | |
Suz | -0.003 |
Bee | -0.003 |
M | -0.003 |
Andy | -0.002 |
Joe | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
aces | +0.027 |
ooter | +0.023 |
ests | +0.023 |
uries | +0.023 |
ival | +0.022 |
Neg logit contributions | |
M | -0.007 |
Joe | -0.007 |
Suz | -0.007 |
Mia | -0.007 |
Andy | -0.007 |
Token | following |
Token ID | 1708 |
Feature activation | -7.59e-03 |
Pos logit contributions | |
aces | +0.048 |
ests | +0.038 |
oll | +0.037 |
lor | +0.037 |
ooter | +0.037 |
Neg logit contributions | |
Mia | -0.032 |
Joe | -0.032 |
Farmer | -0.031 |
M | -0.031 |
Bee | -0.031 |
Token | weekend |
Token ID | 5041 |
Feature activation | -5.16e-02 |
Pos logit contributions | |
aces | +0.018 |
oll | +0.015 |
uries | +0.015 |
ooter | +0.015 |
lor | +0.014 |
Neg logit contributions | |
Joe | -0.011 |
Mia | -0.011 |
M | -0.011 |
Sam | -0.011 |
its | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -5.29e-04 |
Pos logit contributions | |
aces | +0.159 |
ooter | +0.139 |
ests | +0.137 |
ival | +0.136 |
oll | +0.135 |
Neg logit contributions | |
Joe | -0.040 |
M | -0.040 |
Mia | -0.039 |
Sam | -0.037 |
Andy | -0.035 |
Token | He |
Token ID | 679 |
Feature activation | -1.03e-03 |
Pos logit contributions | |
aces | +0.001 |
ooter | +0.001 |
uries | +0.001 |
ests | +0.001 |
ival | +0.001 |
Neg logit contributions | |
Bee | -0.001 |
Suz | -0.001 |
M | -0.001 |
Mia | -0.001 |
Andy | -0.001 |
Token | posted |
Token ID | 4481 |
Feature activation | -4.64e-03 |
Pos logit contributions | |
aces | +0.003 |
ooter | +0.002 |
uries | +0.002 |
ests | +0.002 |
oll | +0.002 |
Neg logit contributions | |
Suz | -0.001 |
M | -0.001 |
Bee | -0.001 |
Andy | -0.001 |
Joe | -0.001 |
Token | signs |
Token ID | 5895 |
Feature activation | -5.71e-03 |
Pos logit contributions | |
aces | +0.014 |
ooter | +0.011 |
ests | +0.011 |
ival | +0.011 |
uries | +0.011 |
Neg logit contributions | |
Bee | -0.004 |
Suz | -0.004 |
M | -0.004 |
Andy | -0.004 |
Ali | -0.004 |
Token | all |
Token ID | 477 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
aces | +0.017 |
uries | +0.015 |
ooter | +0.015 |
atmeal | +0.015 |
ests | +0.015 |
Neg logit contributions | |
Joe | -0.005 |
M | -0.004 |
Andy | -0.004 |
Suz | -0.004 |
Sam | -0.004 |
Token | around |
Token ID | 1088 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
Suz | +0.019 |
Bee | +0.018 |
M | +0.017 |
Andy | +0.016 |
Mia | +0.016 |
Neg logit contributions | |
aces | -0.076 |
ooter | -0.065 |
uries | -0.064 |
ests | -0.063 |
ival | -0.062 |
Token | dangerous |
Token ID | 4923 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
aces | +0.010 |
uries | +0.008 |
ooter | +0.008 |
ests | +0.008 |
ival | +0.008 |
Neg logit contributions | |
Suz | -0.004 |
Bee | -0.004 |
M | -0.004 |
Andy | -0.004 |
Joe | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
Bee | +0.015 |
M | +0.015 |
Suz | +0.014 |
Mia | +0.014 |
Andy | +0.014 |
Neg logit contributions | |
aces | -0.044 |
ooter | -0.038 |
uries | -0.037 |
ival | -0.037 |
ests | -0.036 |
Token | but |
Token ID | 475 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
Suz | +0.021 |
Bee | +0.020 |
M | +0.020 |
Andy | +0.019 |
Joe | +0.019 |
Neg logit contributions | |
aces | -0.041 |
uries | -0.033 |
ooter | -0.033 |
ests | -0.032 |
ival | -0.031 |
Token | also |
Token ID | 635 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
Suz | +0.022 |
M | +0.021 |
Bee | +0.021 |
Ali | +0.020 |
Liz | +0.020 |
Neg logit contributions | |
aces | -0.036 |
uries | -0.030 |
ooter | -0.029 |
rides | -0.028 |
cand | -0.028 |
Token | that |
Token ID | 326 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
Suz | +0.040 |
Bee | +0.037 |
M | +0.037 |
Andy | +0.036 |
Joe | +0.035 |
Neg logit contributions | |
aces | -0.064 |
ooter | -0.052 |
uries | -0.051 |
rides | -0.049 |
ests | -0.049 |
Token | there |
Token ID | 612 |
Feature activation | +5.39e-03 |
Pos logit contributions | |
Suz | +0.024 |
Bee | +0.022 |
M | +0.022 |
Andy | +0.021 |
Joe | +0.021 |
Neg logit contributions | |
aces | -0.048 |
uries | -0.038 |
ooter | -0.038 |
ests | -0.038 |
rides | -0.037 |
Token | are |
Token ID | 389 |
Feature activation | +8.47e-03 |
Pos logit contributions | |
Suz | +0.007 |
M | +0.007 |
Bee | +0.007 |
Andy | +0.007 |
Joe | +0.007 |
Neg logit contributions | |
aces | -0.014 |
ooter | -0.011 |
uries | -0.011 |
ests | -0.011 |
ival | -0.011 |
Token | kind |
Token ID | 1611 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
Suz | +0.012 |
Bee | +0.012 |
M | +0.012 |
Andy | +0.011 |
Mia | +0.011 |
Neg logit contributions | |
aces | -0.021 |
ooter | -0.017 |
uries | -0.017 |
ests | -0.016 |
ival | -0.016 |
Token | people |
Token ID | 661 |
Feature activation | +3.99e-03 |
Pos logit contributions | |
Bee | +0.027 |
Suz | +0.026 |
M | +0.026 |
Mia | +0.025 |
Joe | +0.025 |
Neg logit contributions | |
aces | -0.066 |
ooter | -0.057 |
uries | -0.056 |
ival | -0.054 |
oll | -0.053 |
Token | who |
Token ID | 508 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
Bee | +0.004 |
M | +0.004 |
Mia | +0.004 |
its | +0.004 |
Joe | +0.004 |
Neg logit contributions | |
aces | -0.011 |
ooter | -0.010 |
ests | -0.010 |
uries | -0.009 |
ival | -0.009 |
Token | can |
Token ID | 460 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
Suz | +0.027 |
Bee | +0.027 |
M | +0.026 |
Andy | +0.025 |
Mia | +0.025 |
Neg logit contributions | |
aces | -0.043 |
ooter | -0.035 |
uries | -0.034 |
ests | -0.033 |
ival | -0.033 |
Token | boat |
Token ID | 8848 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
aces | +0.050 |
uries | +0.040 |
ooter | +0.040 |
ests | +0.039 |
oll | +0.038 |
Neg logit contributions | |
Suz | -0.029 |
M | -0.029 |
Bee | -0.029 |
Andy | -0.028 |
Joe | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
aces | +0.051 |
ests | +0.043 |
uries | +0.043 |
oll | +0.043 |
ooter | +0.042 |
Neg logit contributions | |
Suz | -0.018 |
M | -0.017 |
Joe | -0.017 |
Andy | -0.017 |
Bee | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -8.49e-03 |
Pos logit contributions | |
aces | +0.040 |
ooter | +0.035 |
uries | +0.034 |
ests | +0.033 |
ival | +0.033 |
Neg logit contributions | |
Bee | -0.024 |
Suz | -0.024 |
swarm | -0.022 |
boiling | -0.021 |
buzzing | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | -2.09e-03 |
Pos logit contributions | |
aces | +0.017 |
ival | +0.015 |
ests | +0.015 |
ooter | +0.015 |
case | +0.015 |
Neg logit contributions | |
Suz | -0.013 |
Bee | -0.013 |
boiling | -0.012 |
booming | -0.012 |
M | -0.012 |
Token | After |
Token ID | 3260 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
aces | +0.005 |
ooter | +0.004 |
uries | +0.004 |
ests | +0.004 |
ival | +0.004 |
Neg logit contributions | |
Suz | -0.003 |
Bee | -0.003 |
M | -0.003 |
Andy | -0.003 |
Mia | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
aces | +0.030 |
ooter | +0.025 |
uries | +0.025 |
ests | +0.024 |
ival | +0.024 |
Neg logit contributions | |
Suz | -0.010 |
M | -0.010 |
Bee | -0.010 |
Joe | -0.009 |
Andy | -0.009 |
Token | boat |
Token ID | 8848 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
aces | +0.038 |
uries | +0.030 |
ooter | +0.029 |
ests | +0.028 |
oll | +0.028 |
Neg logit contributions | |
Bee | -0.022 |
M | -0.022 |
Suz | -0.021 |
Andy | -0.021 |
Joe | -0.021 |
Token | ride |
Token ID | 6594 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
aces | +0.072 |
uries | +0.061 |
ooter | +0.060 |
ests | +0.059 |
oll | +0.058 |
Neg logit contributions | |
Suz | -0.025 |
Bee | -0.024 |
M | -0.023 |
Andy | -0.022 |
Joe | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | -5.10e-03 |
Pos logit contributions | |
aces | +0.099 |
ooter | +0.083 |
uries | +0.083 |
ests | +0.081 |
ival | +0.080 |
Neg logit contributions | |
Suz | -0.034 |
Bee | -0.032 |
M | -0.032 |
Andy | -0.031 |
Joe | -0.030 |
Token | Tim |
Token ID | 5045 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
aces | +0.014 |
sweets | +0.012 |
ooter | +0.012 |
cand | +0.012 |
ival | +0.012 |
Neg logit contributions | |
Bee | -0.004 |
Suz | -0.004 |
Ali | -0.004 |
M | -0.004 |
Mia | -0.004 |
Token | my |
Token ID | 1820 |
Feature activation | +8.76e-03 |
Pos logit contributions | |
M | +0.017 |
Suz | +0.017 |
Bee | +0.016 |
Joe | +0.016 |
Andy | +0.016 |
Neg logit contributions | |
aces | -0.036 |
uries | -0.030 |
ival | -0.030 |
ooter | -0.029 |
ests | -0.028 |
Token | across |
Token ID | 1973 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
Suz | +0.008 |
M | +0.008 |
Bee | +0.008 |
its | +0.008 |
Joe | +0.007 |
Neg logit contributions | |
aces | -0.022 |
ests | -0.019 |
ooter | -0.019 |
uries | -0.019 |
ival | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +1.01e-03 |
Pos logit contributions | |
Suz | +0.032 |
Bee | +0.031 |
Andy | +0.030 |
Ali | +0.027 |
M | +0.027 |
Neg logit contributions | |
aces | -0.104 |
rides | -0.085 |
sweets | -0.083 |
ooter | -0.083 |
parties | -0.083 |
Token | world |
Token ID | 995 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
M | +0.002 |
Bee | +0.001 |
Suz | +0.001 |
Joe | +0.001 |
its | +0.001 |
Neg logit contributions | |
aces | -0.003 |
ests | -0.002 |
oll | -0.002 |
uries | -0.002 |
ooter | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -7.72e-03 |
Pos logit contributions | |
aces | +0.110 |
ests | +0.095 |
uries | +0.094 |
ooter | +0.094 |
oll | +0.093 |
Neg logit contributions | |
Suz | -0.036 |
M | -0.036 |
Bee | -0.035 |
Mia | -0.034 |
Joe | -0.034 |
Token | make |
Token ID | 787 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
aces | +0.018 |
ooter | +0.015 |
uries | +0.015 |
ests | +0.014 |
ival | +0.014 |
Neg logit contributions | |
Suz | -0.012 |
Bee | -0.011 |
M | -0.011 |
Andy | -0.011 |
Joe | -0.011 |
Token | everything |
Token ID | 2279 |
Feature activation | -5.31e-03 |
Pos logit contributions | |
aces | +0.055 |
ooter | +0.046 |
uries | +0.045 |
ests | +0.044 |
ival | +0.044 |
Neg logit contributions | |
Suz | -0.024 |
Bee | -0.024 |
M | -0.023 |
Andy | -0.022 |
Joe | -0.022 |
Token | better |
Token ID | 1365 |
Feature activation | +3.36e-03 |
Pos logit contributions | |
aces | +0.014 |
ooter | +0.012 |
uries | +0.012 |
ests | +0.011 |
ival | +0.011 |
Neg logit contributions | |
Suz | -0.007 |
M | -0.007 |
Bee | -0.007 |
Mia | -0.007 |
Joe | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
Suz | +0.004 |
M | +0.004 |
Bee | +0.004 |
Mia | +0.003 |
Joe | +0.003 |
Neg logit contributions | |
aces | -0.009 |
ooter | -0.008 |
uries | -0.008 |
ests | -0.008 |
ival | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
aces | +0.082 |
ooter | +0.070 |
uries | +0.070 |
oll | +0.068 |
ival | +0.067 |
Neg logit contributions | |
M | -0.022 |
Suz | -0.022 |
Bee | -0.021 |
Mia | -0.020 |
Andy | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -3.55e-03 |
Pos logit contributions | |
aces | +0.026 |
ests | +0.022 |
ooter | +0.022 |
ival | +0.022 |
uries | +0.022 |
Neg logit contributions | |
Suz | -0.014 |
Bee | -0.013 |
M | -0.012 |
Andy | -0.012 |
Joe | -0.012 |
Token | One |
Token ID | 3198 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
aces | +0.009 |
ooter | +0.008 |
oll | +0.008 |
uries | +0.007 |
ests | +0.007 |
Neg logit contributions | |
Bee | -0.005 |
Mia | -0.004 |
M | -0.004 |
Suz | -0.004 |
Andy | -0.004 |
Token | ed |
Token ID | 276 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
Suz | +0.031 |
Bee | +0.031 |
M | +0.030 |
Andy | +0.030 |
Joe | +0.029 |
Neg logit contributions | |
aces | -0.024 |
ooter | -0.017 |
uries | -0.017 |
ests | -0.016 |
ival | -0.016 |
Token | at |
Token ID | 379 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
Suz | +0.079 |
Bee | +0.073 |
Ali | +0.072 |
Joe | +0.071 |
M | +0.070 |
Neg logit contributions | |
aces | -0.101 |
rides | -0.076 |
ooter | -0.076 |
sweets | -0.073 |
cand | -0.073 |
Token | her |
Token ID | 607 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
Suz | +0.048 |
Bee | +0.047 |
M | +0.046 |
Andy | +0.044 |
Joe | +0.044 |
Neg logit contributions | |
aces | -0.123 |
ooter | -0.103 |
uries | -0.102 |
ests | -0.100 |
ival | -0.099 |
Token | and |
Token ID | 290 |
Feature activation | -3.89e-03 |
Pos logit contributions | |
aces | +0.048 |
ival | +0.041 |
ests | +0.040 |
uries | +0.040 |
ooter | +0.040 |
Neg logit contributions | |
M | -0.015 |
Suz | -0.015 |
Bee | -0.015 |
Mia | -0.014 |
Joe | -0.014 |
Token | scared |
Token ID | 12008 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
aces | +0.008 |
cand | +0.007 |
sweets | +0.006 |
rides | +0.006 |
bracelet | +0.006 |
Neg logit contributions | |
Suz | -0.006 |
boiling | -0.006 |
Maria | -0.006 |
Joe | -0.006 |
Bee | -0.005 |
Token | her |
Token ID | 607 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
Suz | +0.042 |
Bee | +0.041 |
M | +0.041 |
Mia | +0.039 |
Andy | +0.038 |
Neg logit contributions | |
aces | -0.108 |
ooter | -0.091 |
uries | -0.090 |
ests | -0.088 |
ival | -0.087 |
Token | so |
Token ID | 523 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
aces | +0.074 |
ival | +0.065 |
ests | +0.064 |
uries | +0.063 |
ooter | +0.061 |
Neg logit contributions | |
M | -0.021 |
Suz | -0.021 |
Bee | -0.021 |
Mia | -0.020 |
Andy | -0.020 |
Token | much |
Token ID | 881 |
Feature activation | +8.27e-03 |
Pos logit contributions | |
Suz | +0.033 |
Bee | +0.031 |
M | +0.031 |
Joe | +0.031 |
boiling | +0.030 |
Neg logit contributions | |
aces | -0.046 |
oll | -0.035 |
ooter | -0.035 |
case | -0.034 |
rides | -0.034 |
Token | that |
Token ID | 326 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
Suz | +0.010 |
Bee | +0.009 |
M | +0.009 |
Andy | +0.009 |
Mia | +0.009 |
Neg logit contributions | |
aces | -0.023 |
ooter | -0.019 |
uries | -0.019 |
ests | -0.019 |
ival | -0.018 |
Token | she |
Token ID | 673 |
Feature activation | -5.80e-03 |
Pos logit contributions | |
Suz | +0.036 |
Bee | +0.035 |
Joe | +0.033 |
M | +0.033 |
Andy | +0.033 |
Neg logit contributions | |
aces | -0.056 |
ooter | -0.045 |
uries | -0.044 |
sweets | -0.043 |
rides | -0.043 |
Token | started |
Token ID | 2067 |
Feature activation | +1.97e-03 |
Pos logit contributions | |
aces | +0.015 |
ooter | +0.012 |
uries | +0.012 |
ests | +0.012 |
ival | +0.012 |
Neg logit contributions | |
Suz | -0.008 |
Bee | -0.008 |
M | -0.008 |
Andy | -0.007 |
Joe | -0.007 |
Token | grocery |
Token ID | 16918 |
Feature activation | -8.04e-02 |
Pos logit contributions | |
aces | +0.202 |
lor | +0.168 |
seek | +0.165 |
uries | +0.159 |
ival | +0.158 |
Neg logit contributions | |
M | -0.181 |
Andy | -0.166 |
Bee | -0.162 |
Farmer | -0.160 |
Mia | -0.159 |
Token | list |
Token ID | 1351 |
Feature activation | -6.76e-02 |
Pos logit contributions | |
aces | +0.184 |
uries | +0.142 |
oll | +0.139 |
ooter | +0.136 |
ests | +0.136 |
Neg logit contributions | |
M | -0.128 |
Suz | -0.123 |
Mia | -0.122 |
Bee | -0.119 |
Andy | -0.118 |
Token | to |
Token ID | 284 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
aces | +0.194 |
ooter | +0.163 |
uries | +0.163 |
ode | +0.160 |
ests | +0.159 |
Neg logit contributions | |
M | -0.065 |
Suz | -0.064 |
Mia | -0.062 |
Joe | -0.061 |
Andy | -0.058 |
Token | find |
Token ID | 1064 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
aces | +0.049 |
ooter | +0.038 |
uries | +0.037 |
ests | +0.036 |
ival | +0.035 |
Neg logit contributions | |
Suz | -0.049 |
Bee | -0.048 |
M | -0.048 |
Andy | -0.047 |
Joe | -0.046 |
Token | what |
Token ID | 644 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
aces | +0.057 |
ooter | +0.047 |
uries | +0.047 |
ests | +0.045 |
ival | +0.045 |
Neg logit contributions | |
Suz | -0.028 |
Bee | -0.027 |
M | -0.027 |
Andy | -0.025 |
Joe | -0.025 |
Token | we |
Token ID | 356 |
Feature activation | -6.69e-02 |
Pos logit contributions | |
aces | +0.041 |
ooter | +0.035 |
uries | +0.035 |
ests | +0.034 |
oll | +0.033 |
Neg logit contributions | |
M | -0.013 |
Mia | -0.013 |
Bee | -0.013 |
Joe | -0.012 |
Andy | -0.012 |
Token | need |
Token ID | 761 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
aces | +0.182 |
ooter | +0.154 |
lor | +0.153 |
ests | +0.151 |
seek | +0.149 |
Neg logit contributions | |
M | -0.075 |
Suz | -0.072 |
Bee | -0.071 |
Joe | -0.070 |
Andy | -0.068 |
Token | ." |
Token ID | 526 |
Feature activation | -1.67e-03 |
Pos logit contributions | |
aces | +0.129 |
ooter | +0.108 |
ests | +0.105 |
uries | +0.105 |
oll | +0.103 |
Neg logit contributions | |
M | -0.055 |
Suz | -0.054 |
Bee | -0.052 |
Joe | -0.051 |
Mia | -0.051 |
Token |
|
Token ID | 198 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
aces | +0.004 |
ooter | +0.004 |
uries | +0.004 |
ests | +0.003 |
ival | +0.003 |
Neg logit contributions | |
Suz | -0.002 |
Bee | -0.002 |
M | -0.002 |
Andy | -0.002 |
Joe | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
Suz | +0.020 |
Bee | +0.018 |
Joe | +0.017 |
Maria | +0.017 |
Andy | +0.017 |
Neg logit contributions | |
aces | -0.032 |
ival | -0.027 |
ests | -0.027 |
ooter | -0.027 |
rides | -0.026 |
Token | Baby |
Token ID | 36534 |
Feature activation | -9.26e-03 |
Pos logit contributions | |
Suz | +0.025 |
Bee | +0.025 |
M | +0.025 |
Andy | +0.024 |
Joe | +0.023 |
Neg logit contributions | |
aces | -0.046 |
ooter | -0.037 |
uries | -0.037 |
ests | -0.036 |
ival | -0.035 |
Token | her |
Token ID | 607 |
Feature activation | -5.16e-02 |
Pos logit contributions | |
Suz | +0.021 |
Bee | +0.020 |
M | +0.020 |
Andy | +0.018 |
Joe | +0.018 |
Neg logit contributions | |
aces | -0.101 |
ooter | -0.087 |
uries | -0.086 |
ests | -0.085 |
ival | -0.084 |
Token | arm |
Token ID | 3211 |
Feature activation | -8.75e-03 |
Pos logit contributions | |
aces | +0.133 |
uries | +0.112 |
ival | +0.106 |
ests | +0.105 |
ooter | +0.105 |
Neg logit contributions | |
M | -0.073 |
Bee | -0.070 |
Suz | -0.070 |
Mia | -0.068 |
Andy | -0.065 |
Token | chair |
Token ID | 16337 |
Feature activation | +1.67e-03 |
Pos logit contributions | |
aces | +0.014 |
uries | +0.013 |
ival | +0.011 |
chery | +0.011 |
ode | +0.010 |
Neg logit contributions | |
M | -0.019 |
Mia | -0.018 |
Bee | -0.018 |
Suz | -0.018 |
Andy | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
M | +0.002 |
Bee | +0.002 |
Mia | +0.001 |
its | +0.001 |
Suz | +0.001 |
Neg logit contributions | |
aces | -0.005 |
uries | -0.004 |
ival | -0.004 |
ooter | -0.004 |
ests | -0.004 |
Token | read |
Token ID | 1100 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
aces | +0.052 |
ooter | +0.041 |
uries | +0.040 |
ests | +0.038 |
ival | +0.038 |
Neg logit contributions | |
Suz | -0.045 |
Bee | -0.044 |
M | -0.043 |
Andy | -0.042 |
Joe | -0.042 |
Token | her |
Token ID | 607 |
Feature activation | -6.71e-02 |
Pos logit contributions | |
aces | +0.120 |
ooter | +0.102 |
uries | +0.101 |
ests | +0.097 |
ival | +0.096 |
Neg logit contributions | |
M | -0.055 |
Suz | -0.054 |
Bee | -0.054 |
Mia | -0.052 |
Andy | -0.051 |
Token | favorite |
Token ID | 4004 |
Feature activation | -4.70e-02 |
Pos logit contributions | |
aces | +0.136 |
uries | +0.115 |
ival | +0.109 |
ooter | +0.108 |
ests | +0.104 |
Neg logit contributions | |
M | -0.126 |
Bee | -0.123 |
Suz | -0.119 |
Andy | -0.119 |
Mia | -0.117 |
Token | books |
Token ID | 3835 |
Feature activation | -7.64e-02 |
Pos logit contributions | |
aces | +0.093 |
uries | +0.074 |
ival | +0.071 |
ooter | +0.071 |
oll | +0.069 |
Neg logit contributions | |
M | -0.091 |
Bee | -0.090 |
Suz | -0.088 |
Mia | -0.087 |
Andy | -0.086 |
Token | . |
Token ID | 13 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
aces | +0.230 |
uries | +0.209 |
ooter | +0.203 |
ode | +0.202 |
ests | +0.199 |
Neg logit contributions | |
M | -0.057 |
Suz | -0.056 |
Mia | -0.055 |
its | -0.055 |
Bee | -0.049 |
Token | One |
Token ID | 1881 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
aces | +0.037 |
uries | +0.030 |
ooter | +0.030 |
ival | +0.030 |
ests | +0.030 |
Neg logit contributions | |
M | -0.022 |
Suz | -0.022 |
Bee | -0.021 |
Mia | -0.021 |
Andy | -0.020 |
Token | day |
Token ID | 1110 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
aces | +0.018 |
ooter | +0.014 |
uries | +0.013 |
ests | +0.013 |
oll | +0.013 |
Neg logit contributions | |
Suz | -0.022 |
Bee | -0.022 |
M | -0.021 |
Andy | -0.021 |
Joe | -0.021 |
Token | safe |
Token ID | 3338 |
Feature activation | +2.51e-03 |
Pos logit contributions | |
Suz | +0.022 |
M | +0.021 |
Bee | +0.021 |
Joe | +0.020 |
Andy | +0.020 |
Neg logit contributions | |
aces | -0.041 |
ooter | -0.032 |
uries | -0.032 |
rides | -0.031 |
oll | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +1.69e-03 |
Pos logit contributions | |
Suz | +0.003 |
Bee | +0.003 |
M | +0.003 |
Andy | +0.003 |
Joe | +0.003 |
Neg logit contributions | |
aces | -0.007 |
ooter | -0.006 |
uries | -0.006 |
ests | -0.005 |
ival | -0.005 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
Suz | +0.003 |
Bee | +0.002 |
M | +0.002 |
Andy | +0.002 |
Ali | +0.002 |
Neg logit contributions | |
aces | -0.004 |
rides | -0.003 |
sweets | -0.003 |
cand | -0.003 |
ooter | -0.003 |
Token | again |
Token ID | 757 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
aces | +0.040 |
ooter | +0.033 |
uries | +0.033 |
ests | +0.032 |
ival | +0.032 |
Neg logit contributions | |
Suz | -0.017 |
Bee | -0.017 |
M | -0.017 |
Andy | -0.016 |
Joe | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -9.52e-03 |
Pos logit contributions | |
Suz | +0.078 |
Bee | +0.074 |
M | +0.072 |
Andy | +0.071 |
Joe | +0.069 |
Neg logit contributions | |
aces | -0.128 |
uries | -0.101 |
ooter | -0.100 |
seek | -0.096 |
rides | -0.096 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -7.02e-02 |
Pos logit contributions | |
aces | +0.024 |
ooter | +0.019 |
uries | +0.019 |
ests | +0.019 |
rides | +0.018 |
Neg logit contributions | |
Suz | -0.012 |
Bee | -0.012 |
boiling | -0.012 |
M | -0.011 |
Andy | -0.011 |
Token | Once |
Token ID | 7454 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
aces | +0.207 |
ooter | +0.174 |
uries | +0.173 |
ests | +0.170 |
ival | +0.168 |
Neg logit contributions | |
Suz | -0.068 |
Bee | -0.065 |
M | -0.064 |
Andy | -0.061 |
Joe | -0.060 |
Token | upon |
Token ID | 2402 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
aces | +0.134 |
ooter | +0.115 |
case | +0.111 |
oll | +0.108 |
ival | +0.105 |
Neg logit contributions | |
booming | -0.077 |
Suz | -0.076 |
Bee | -0.076 |
boiling | -0.075 |
Farmer | -0.075 |
Token | a |
Token ID | 257 |
Feature activation | -1.84e-03 |
Pos logit contributions | |
aces | +0.041 |
ooter | +0.035 |
uries | +0.034 |
ests | +0.033 |
ival | +0.033 |
Neg logit contributions | |
Suz | -0.019 |
Bee | -0.019 |
M | -0.018 |
Andy | -0.018 |
Mia | -0.018 |
Token | time |
Token ID | 640 |
Feature activation | -4.94e-02 |
Pos logit contributions | |
aces | +0.003 |
ooter | +0.002 |
uries | +0.002 |
oll | +0.002 |
ests | +0.002 |
Neg logit contributions | |
Suz | -0.004 |
Bee | -0.004 |
M | -0.004 |
Andy | -0.004 |
Joe | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
aces | +0.110 |
ooter | +0.088 |
ival | +0.084 |
oll | +0.083 |
case | +0.082 |
Neg logit contributions | |
boiling | -0.074 |
Suz | -0.071 |
Bee | -0.070 |
booming | -0.068 |
M | -0.067 |
Token | have |
Token ID | 423 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
aces | +0.078 |
ooter | +0.064 |
uries | +0.063 |
ests | +0.062 |
ival | +0.062 |
Neg logit contributions | |
Suz | -0.038 |
Bee | -0.037 |
M | -0.037 |
Mia | -0.035 |
Andy | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
aces | +0.081 |
ooter | +0.066 |
uries | +0.065 |
ests | +0.063 |
ival | +0.063 |
Neg logit contributions | |
Suz | -0.047 |
Bee | -0.046 |
M | -0.046 |
Mia | -0.044 |
Andy | -0.044 |
Token | happy |
Token ID | 3772 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
aces | +0.038 |
ooter | +0.032 |
uries | +0.031 |
ival | +0.031 |
ests | +0.030 |
Neg logit contributions | |
Suz | -0.028 |
Bee | -0.027 |
M | -0.026 |
Andy | -0.026 |
Joe | -0.026 |
Token | birthday |
Token ID | 10955 |
Feature activation | -4.97e-02 |
Pos logit contributions | |
aces | +0.063 |
ooter | +0.047 |
uries | +0.046 |
ests | +0.045 |
ival | +0.044 |
Neg logit contributions | |
Suz | -0.068 |
M | -0.067 |
Bee | -0.067 |
Mia | -0.065 |
Joe | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
aces | +0.138 |
ooter | +0.117 |
uries | +0.113 |
ests | +0.109 |
ance | +0.107 |
Neg logit contributions | |
Mia | -0.062 |
M | -0.060 |
Bee | -0.057 |
Suz | -0.054 |
Joe | -0.052 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -7.65e-02 |
Pos logit contributions | |
aces | +0.042 |
uries | +0.035 |
ests | +0.034 |
oll | +0.033 |
ooter | +0.033 |
Neg logit contributions | |
Suz | -0.025 |
Andy | -0.022 |
Bee | -0.022 |
Joe | -0.021 |
Maria | -0.021 |
Token | Anna |
Token ID | 31160 |
Feature activation | +5.95e-03 |
Pos logit contributions | |
aces | +0.238 |
uries | +0.215 |
ooter | +0.212 |
ival | +0.195 |
seek | +0.194 |
Neg logit contributions | |
Bee | -0.063 |
M | -0.062 |
Mia | -0.059 |
Suz | -0.055 |
Joe | -0.052 |
Token | and |
Token ID | 290 |
Feature activation | -6.94e-02 |
Pos logit contributions | |
M | +0.006 |
Bee | +0.006 |
Mia | +0.006 |
Suz | +0.006 |
Joe | +0.006 |
Neg logit contributions | |
aces | -0.017 |
ooter | -0.015 |
uries | -0.014 |
ival | -0.014 |
ests | -0.014 |
Token | Ben |
Token ID | 3932 |
Feature activation | -4.91e-02 |
Pos logit contributions | |
aces | +0.205 |
uries | +0.175 |
ooter | +0.174 |
ests | +0.171 |
ival | +0.170 |
Neg logit contributions | |
Suz | -0.072 |
M | -0.070 |
Bee | -0.068 |
Joe | -0.068 |
Mia | -0.068 |
Token | are |
Token ID | 389 |
Feature activation | -4.01e-02 |
Pos logit contributions | |
aces | +0.131 |
ooter | +0.116 |
lor | +0.109 |
uries | +0.109 |
ival | +0.108 |
Neg logit contributions | |
M | -0.062 |
Joe | -0.061 |
Mia | -0.060 |
Suz | -0.059 |
Sam | -0.057 |
Token | friends |
Token ID | 2460 |
Feature activation | -3.59e-02 |
Pos logit contributions | |
aces | +0.100 |
ooter | +0.082 |
uries | +0.081 |
ests | +0.079 |
ival | +0.078 |
Neg logit contributions | |
Suz | -0.059 |
M | -0.058 |
Bee | -0.057 |
Mia | -0.056 |
Joe | -0.055 |
Token | fun |
Token ID | 1257 |
Feature activation | -6.01e-02 |
Pos logit contributions | |
Suz | +0.001 |
Bee | +0.001 |
M | +0.001 |
Andy | +0.001 |
Joe | +0.001 |
Neg logit contributions | |
aces | -0.002 |
ooter | -0.001 |
uries | -0.001 |
ests | -0.001 |
ival | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -1.19e-03 |
Pos logit contributions | |
aces | +0.170 |
ooter | +0.145 |
uries | +0.143 |
ests | +0.140 |
ival | +0.139 |
Neg logit contributions | |
Suz | -0.063 |
M | -0.061 |
Bee | -0.060 |
Joe | -0.058 |
Mia | -0.058 |
Token | They |
Token ID | 1119 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
aces | +0.003 |
ooter | +0.003 |
uries | +0.003 |
ests | +0.003 |
ival | +0.003 |
Neg logit contributions | |
Suz | -0.001 |
Bee | -0.001 |
M | -0.001 |
Andy | -0.001 |
Mia | -0.001 |
Token | laughed |
Token ID | 13818 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
aces | +0.047 |
ooter | +0.038 |
uries | +0.038 |
ests | +0.037 |
ival | +0.037 |
Neg logit contributions | |
Suz | -0.027 |
Bee | -0.027 |
M | -0.026 |
Andy | -0.025 |
Joe | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
Suz | +0.017 |
Bee | +0.016 |
M | +0.016 |
Andy | +0.015 |
Mia | +0.015 |
Neg logit contributions | |
aces | -0.040 |
ooter | -0.034 |
uries | -0.034 |
ests | -0.033 |
ival | -0.032 |
Token | played |
Token ID | 2826 |
Feature activation | -7.29e-02 |
Pos logit contributions | |
aces | +0.067 |
ooter | +0.055 |
uries | +0.054 |
ests | +0.053 |
rides | +0.052 |
Neg logit contributions | |
Suz | -0.032 |
Bee | -0.031 |
M | -0.030 |
Andy | -0.029 |
Joe | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
aces | +0.197 |
ooter | +0.167 |
uries | +0.163 |
ests | +0.159 |
oll | +0.157 |
Neg logit contributions | |
Suz | -0.087 |
Bee | -0.086 |
M | -0.085 |
Mia | -0.083 |
Andy | -0.081 |
Token | pretended |
Token ID | 36766 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
aces | +0.079 |
ooter | +0.064 |
uries | +0.063 |
ests | +0.061 |
ival | +0.060 |
Neg logit contributions | |
Suz | -0.051 |
Bee | -0.049 |
M | -0.049 |
Andy | -0.047 |
Joe | -0.047 |
Token | to |
Token ID | 284 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
aces | +0.149 |
ooter | +0.127 |
uries | +0.126 |
ests | +0.124 |
oll | +0.123 |
Neg logit contributions | |
Suz | -0.047 |
M | -0.045 |
Mia | -0.045 |
Bee | -0.044 |
Joe | -0.044 |
Token | be |
Token ID | 307 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
aces | +0.051 |
ooter | +0.041 |
uries | +0.041 |
ests | +0.040 |
ival | +0.039 |
Neg logit contributions | |
Suz | -0.029 |
Bee | -0.028 |
M | -0.028 |
Andy | -0.027 |
Mia | -0.026 |
Token | factory |
Token ID | 8860 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
aces | +0.072 |
ooter | +0.060 |
uries | +0.059 |
ests | +0.058 |
ival | +0.057 |
Neg logit contributions | |
Suz | -0.039 |
Bee | -0.038 |
M | -0.037 |
Andy | -0.036 |
Joe | -0.036 |