Token | . |
Token ID | 13 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
Today | +0.093 |
Nice | +0.078 |
This | +0.075 |
These | +0.069 |
Of | +0.065 |
Neg logit contributions | |
forgot | -0.114 |
waited | -0.104 |
stayed | -0.104 |
put | -0.102 |
remembered | -0.101 |
Token | Ben |
Token ID | 3932 |
Feature activation | -6.49e-02 |
Pos logit contributions | |
Today | +0.129 |
Nice | +0.128 |
opl | +0.125 |
anes | +0.124 |
oing | +0.116 |
Neg logit contributions | |
forgot | -0.126 |
put | -0.118 |
tried | -0.110 |
remembered | -0.110 |
waited | -0.109 |
Token | likes |
Token ID | 7832 |
Feature activation | +9.89e-03 |
Pos logit contributions | |
forgot | +0.132 |
punished | +0.124 |
managed | +0.119 |
stayed | +0.115 |
remembered | +0.115 |
Neg logit contributions | |
Today | -0.138 |
This | -0.113 |
These | -0.103 |
Nice | -0.101 |
On | -0.095 |
Token | to |
Token ID | 284 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
Today | +0.018 |
This | +0.015 |
Nice | +0.015 |
These | +0.013 |
Of | +0.013 |
Neg logit contributions | |
forgot | -0.024 |
remembered | -0.021 |
waited | -0.021 |
managed | -0.021 |
stayed | -0.021 |
Token | use |
Token ID | 779 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
forgot | +0.036 |
remembered | +0.033 |
punished | +0.031 |
managed | +0.031 |
drowned | +0.030 |
Neg logit contributions | |
Today | -0.047 |
This | -0.040 |
On | -0.036 |
Nice | -0.033 |
These | -0.033 |
Token | h |
Token ID | 289 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
Today | +0.028 |
This | +0.024 |
Nice | +0.023 |
These | +0.021 |
Of | +0.020 |
Neg logit contributions | |
forgot | -0.027 |
waited | -0.024 |
remembered | -0.023 |
stayed | -0.023 |
managed | -0.022 |
Token | angers |
Token ID | 6606 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
Today | +0.188 |
Nice | +0.154 |
This | +0.144 |
These | +0.126 |
Of | +0.121 |
Neg logit contributions | |
forgot | -0.275 |
waited | -0.253 |
stayed | -0.251 |
put | -0.249 |
remembered | -0.243 |
Token | to |
Token ID | 284 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
Today | +0.114 |
This | +0.095 |
Nice | +0.094 |
These | +0.084 |
ummy | +0.079 |
Neg logit contributions | |
forgot | -0.130 |
waited | -0.116 |
remembered | -0.116 |
stayed | -0.114 |
dug | -0.110 |
Token | make |
Token ID | 787 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
forgot | +0.038 |
remembered | +0.033 |
managed | +0.031 |
waited | +0.031 |
punished | +0.030 |
Neg logit contributions | |
Today | -0.057 |
This | -0.049 |
Nice | -0.044 |
These | -0.043 |
On | -0.043 |
Token | funny |
Token ID | 8258 |
Feature activation | +4.83e-02 |
Pos logit contributions | |
Today | +0.059 |
This | +0.051 |
Nice | +0.049 |
These | +0.046 |
Of | +0.044 |
Neg logit contributions | |
forgot | -0.052 |
remembered | -0.045 |
waited | -0.045 |
stayed | -0.044 |
managed | -0.043 |
Token | shapes |
Token ID | 15268 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
Today | +0.121 |
Nice | +0.104 |
This | +0.103 |
These | +0.095 |
Of | +0.091 |
Neg logit contributions | |
forgot | -0.086 |
waited | -0.075 |
remembered | -0.074 |
stayed | -0.074 |
managed | -0.071 |
Token | , |
Token ID | 11 |
Feature activation | +7.02e-03 |
Pos logit contributions | |
forgot | +0.104 |
waited | +0.093 |
stayed | +0.093 |
remembered | +0.090 |
dug | +0.089 |
Neg logit contributions | |
Today | -0.096 |
This | -0.080 |
Nice | -0.077 |
These | -0.071 |
ummy | -0.069 |
Token | can |
Token ID | 460 |
Feature activation | +3.27e-03 |
Pos logit contributions | |
Today | +0.016 |
This | +0.013 |
Nice | +0.013 |
These | +0.012 |
Of | +0.011 |
Neg logit contributions | |
forgot | -0.015 |
punished | -0.013 |
managed | -0.013 |
remembered | -0.013 |
ts | -0.013 |
Token | I |
Token ID | 314 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
Today | +0.006 |
This | +0.005 |
Nice | +0.005 |
These | +0.005 |
Of | +0.004 |
Neg logit contributions | |
forgot | -0.008 |
remembered | -0.007 |
waited | -0.007 |
managed | -0.007 |
stayed | -0.007 |
Token | have |
Token ID | 423 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
forgot | +0.041 |
ts | +0.037 |
remembered | +0.035 |
waited | +0.034 |
stayed | +0.034 |
Neg logit contributions | |
Today | -0.060 |
This | -0.051 |
These | -0.046 |
Nice | -0.045 |
On | -0.045 |
Token | more |
Token ID | 517 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
forgot | +0.069 |
remembered | +0.060 |
managed | +0.058 |
stayed | +0.058 |
waited | +0.057 |
Neg logit contributions | |
Today | -0.058 |
This | -0.052 |
These | -0.045 |
Nice | -0.045 |
On | -0.040 |
Token | h |
Token ID | 289 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
Today | +0.030 |
This | +0.025 |
Nice | +0.024 |
These | +0.023 |
ummy | +0.022 |
Neg logit contributions | |
forgot | -0.021 |
remembered | -0.018 |
stayed | -0.018 |
waited | -0.018 |
managed | -0.017 |
Token | angers |
Token ID | 6606 |
Feature activation | +6.17e-02 |
Pos logit contributions | |
Today | +0.180 |
Nice | +0.146 |
This | +0.139 |
These | +0.119 |
Of | +0.114 |
Neg logit contributions | |
forgot | -0.280 |
waited | -0.258 |
stayed | -0.255 |
put | -0.253 |
remembered | -0.248 |
Token | for |
Token ID | 329 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
Today | +0.128 |
This | +0.106 |
Nice | +0.104 |
These | +0.095 |
ummy | +0.090 |
Neg logit contributions | |
forgot | -0.136 |
waited | -0.121 |
remembered | -0.120 |
stayed | -0.120 |
managed | -0.115 |
Token | my |
Token ID | 616 |
Feature activation | -5.04e-03 |
Pos logit contributions | |
Today | +0.026 |
This | +0.024 |
These | +0.021 |
ummy | +0.021 |
Nice | +0.021 |
Neg logit contributions | |
forgot | -0.027 |
managed | -0.024 |
remembered | -0.024 |
stayed | -0.022 |
dug | -0.022 |
Token | dolls |
Token ID | 36062 |
Feature activation | +3.89e-02 |
Pos logit contributions | |
forgot | +0.008 |
managed | +0.007 |
waited | +0.007 |
remembered | +0.007 |
stayed | +0.007 |
Neg logit contributions | |
Today | -0.013 |
Nice | -0.011 |
This | -0.011 |
These | -0.010 |
ummy | -0.010 |
Token | ?" |
Token ID | 1701 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
Today | +0.075 |
This | +0.060 |
Nice | +0.056 |
These | +0.051 |
ummy | +0.050 |
Neg logit contributions | |
forgot | -0.091 |
waited | -0.082 |
remembered | -0.081 |
stayed | -0.081 |
managed | -0.080 |
Token | . |
Token ID | 13 |
Feature activation | +6.52e-02 |
Pos logit contributions | |
Today | +0.007 |
Nice | +0.006 |
This | +0.006 |
These | +0.005 |
Of | +0.005 |
Neg logit contributions | |
forgot | -0.008 |
waited | -0.008 |
stayed | -0.008 |
remembered | -0.008 |
put | -0.007 |
Token | Lily |
Token ID | 20037 |
Feature activation | -7.54e-02 |
Pos logit contributions | |
opl | +0.119 |
anes | +0.114 |
Today | +0.110 |
Nice | +0.110 |
ane | +0.103 |
Neg logit contributions | |
forgot | -0.133 |
put | -0.132 |
waited | -0.121 |
tried | -0.119 |
dug | -0.118 |
Token | likes |
Token ID | 7832 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
forgot | +0.147 |
punished | +0.144 |
managed | +0.139 |
ts | +0.137 |
waited | +0.136 |
Neg logit contributions | |
Today | -0.152 |
This | -0.128 |
Nice | -0.114 |
These | -0.113 |
She | -0.108 |
Token | to |
Token ID | 284 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
Today | +0.022 |
This | +0.019 |
Nice | +0.019 |
These | +0.017 |
Of | +0.016 |
Neg logit contributions | |
forgot | -0.026 |
remembered | -0.022 |
waited | -0.022 |
managed | -0.022 |
stayed | -0.022 |
Token | use |
Token ID | 779 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
forgot | +0.043 |
remembered | +0.039 |
managed | +0.038 |
punished | +0.037 |
waited | +0.037 |
Neg logit contributions | |
Today | -0.054 |
This | -0.046 |
On | -0.039 |
These | -0.038 |
Nice | -0.038 |
Token | h |
Token ID | 289 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
Today | +0.025 |
This | +0.021 |
Nice | +0.021 |
These | +0.019 |
Of | +0.018 |
Neg logit contributions | |
forgot | -0.023 |
waited | -0.020 |
remembered | -0.020 |
stayed | -0.019 |
managed | -0.019 |
Token | angers |
Token ID | 6606 |
Feature activation | +5.53e-02 |
Pos logit contributions | |
Today | +0.186 |
Nice | +0.152 |
This | +0.143 |
These | +0.124 |
Of | +0.119 |
Neg logit contributions | |
forgot | -0.274 |
waited | -0.251 |
stayed | -0.249 |
put | -0.247 |
remembered | -0.241 |
Token | to |
Token ID | 284 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
Today | +0.106 |
This | +0.088 |
Nice | +0.086 |
These | +0.077 |
ummy | +0.073 |
Neg logit contributions | |
forgot | -0.129 |
waited | -0.116 |
remembered | -0.116 |
stayed | -0.114 |
dug | -0.110 |
Token | hang |
Token ID | 8181 |
Feature activation | +6.61e-02 |
Pos logit contributions | |
forgot | +0.044 |
remembered | +0.039 |
managed | +0.036 |
waited | +0.036 |
punished | +0.035 |
Neg logit contributions | |
Today | -0.062 |
This | -0.054 |
These | -0.046 |
On | -0.046 |
Nice | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
Today | +0.160 |
Nice | +0.137 |
This | +0.134 |
These | +0.126 |
Of | +0.120 |
Neg logit contributions | |
forgot | -0.120 |
stayed | -0.108 |
waited | -0.107 |
put | -0.107 |
remembered | -0.103 |
Token | clothes |
Token ID | 8242 |
Feature activation | +6.61e-02 |
Pos logit contributions | |
Today | +0.033 |
Nice | +0.029 |
This | +0.028 |
These | +0.026 |
ummy | +0.025 |
Neg logit contributions | |
forgot | -0.021 |
remembered | -0.018 |
waited | -0.017 |
stayed | -0.017 |
managed | -0.017 |
Token | they |
Token ID | 484 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
Today | +0.058 |
Nice | +0.050 |
This | +0.049 |
These | +0.045 |
Of | +0.043 |
Neg logit contributions | |
forgot | -0.048 |
waited | -0.042 |
stayed | -0.042 |
remembered | -0.041 |
put | -0.040 |
Token | came |
Token ID | 1625 |
Feature activation | +7.93e-04 |
Pos logit contributions | |
forgot | +0.072 |
ppa | +0.059 |
mistake | +0.057 |
punished | +0.056 |
ilia | +0.054 |
Neg logit contributions | |
Today | -0.116 |
On | -0.103 |
The | -0.102 |
This | -0.100 |
Right | -0.098 |
Token | to |
Token ID | 284 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
Today | +0.002 |
Nice | +0.001 |
This | +0.001 |
These | +0.001 |
Of | +0.001 |
Neg logit contributions | |
forgot | -0.002 |
waited | -0.002 |
stayed | -0.002 |
remembered | -0.001 |
put | -0.001 |
Token | help |
Token ID | 1037 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
forgot | +0.031 |
stayed | +0.026 |
remembered | +0.026 |
managed | +0.025 |
waited | +0.025 |
Neg logit contributions | |
Today | -0.034 |
This | -0.029 |
Nice | -0.027 |
Of | -0.025 |
These | -0.025 |
Token | with |
Token ID | 351 |
Feature activation | +5.28e-03 |
Pos logit contributions | |
Today | +0.059 |
Nice | +0.050 |
This | +0.049 |
These | +0.046 |
Of | +0.043 |
Neg logit contributions | |
forgot | -0.053 |
waited | -0.047 |
stayed | -0.047 |
remembered | -0.046 |
put | -0.046 |
Token | h |
Token ID | 289 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
Today | +0.011 |
This | +0.009 |
Nice | +0.009 |
These | +0.008 |
Of | +0.008 |
Neg logit contributions | |
forgot | -0.012 |
waited | -0.010 |
stayed | -0.010 |
remembered | -0.010 |
managed | -0.009 |
Token | oses |
Token ID | 4629 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
Today | +0.211 |
Nice | +0.180 |
This | +0.165 |
Of | +0.146 |
These | +0.145 |
Neg logit contributions | |
forgot | -0.246 |
waited | -0.226 |
stayed | -0.223 |
put | -0.220 |
cleaned | -0.218 |
Token | and |
Token ID | 290 |
Feature activation | +8.39e-03 |
Pos logit contributions | |
Today | +0.044 |
This | +0.037 |
Nice | +0.036 |
These | +0.033 |
Of | +0.031 |
Neg logit contributions | |
forgot | -0.049 |
waited | -0.044 |
remembered | -0.043 |
stayed | -0.043 |
put | -0.042 |
Token | axes |
Token ID | 34197 |
Feature activation | +4.03e-02 |
Pos logit contributions | |
Today | +0.017 |
This | +0.016 |
These | +0.014 |
Nice | +0.014 |
Right | +0.014 |
Neg logit contributions | |
forgot | -0.014 |
stayed | -0.012 |
remembered | -0.011 |
ppa | -0.011 |
managed | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +6.82e-02 |
Pos logit contributions | |
Today | +0.075 |
Nice | +0.061 |
This | +0.061 |
These | +0.054 |
Of | +0.050 |
Neg logit contributions | |
forgot | -0.097 |
waited | -0.087 |
remembered | -0.087 |
stayed | -0.086 |
put | -0.084 |
Token | She |
Token ID | 1375 |
Feature activation | -9.32e-02 |
Pos logit contributions | |
Today | +0.099 |
Nice | +0.091 |
uttering | +0.080 |
opl | +0.078 |
anes | +0.075 |
Neg logit contributions | |
forgot | -0.168 |
waited | -0.166 |
tried | -0.160 |
never | -0.156 |
put | -0.155 |
Token | , |
Token ID | 11 |
Feature activation | +9.78e-03 |
Pos logit contributions | |
Today | +0.043 |
This | +0.036 |
Nice | +0.034 |
These | +0.031 |
Of | +0.029 |
Neg logit contributions | |
forgot | -0.054 |
remembered | -0.047 |
waited | -0.047 |
stayed | -0.047 |
managed | -0.046 |
Token | who |
Token ID | 508 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
Today | +0.020 |
This | +0.017 |
Nice | +0.017 |
These | +0.015 |
Of | +0.015 |
Neg logit contributions | |
forgot | -0.021 |
remembered | -0.018 |
waited | -0.018 |
managed | -0.018 |
stayed | -0.018 |
Token | always |
Token ID | 1464 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
forgot | +0.035 |
remembered | +0.030 |
dug | +0.029 |
ode | +0.029 |
stayed | +0.028 |
Neg logit contributions | |
Today | -0.064 |
This | -0.060 |
Nice | -0.055 |
These | -0.055 |
ore | -0.054 |
Token | gave |
Token ID | 2921 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
ode | +0.043 |
ts | +0.041 |
forgot | +0.040 |
drowned | +0.039 |
ils | +0.039 |
Neg logit contributions | |
Today | -0.108 |
This | -0.100 |
Nice | -0.096 |
Of | -0.095 |
A | -0.088 |
Token | good |
Token ID | 922 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
Today | +0.037 |
This | +0.032 |
Nice | +0.031 |
These | +0.028 |
Of | +0.026 |
Neg logit contributions | |
forgot | -0.047 |
remembered | -0.041 |
waited | -0.041 |
stayed | -0.040 |
managed | -0.039 |
Token | hairc |
Token ID | 37363 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
Today | +0.086 |
This | +0.073 |
Nice | +0.072 |
These | +0.067 |
Of | +0.067 |
Neg logit contributions | |
forgot | -0.069 |
managed | -0.057 |
stayed | -0.057 |
remembered | -0.057 |
never | -0.056 |
Token | uts |
Token ID | 5500 |
Feature activation | +5.49e-02 |
Pos logit contributions | |
Today | +0.167 |
Nice | +0.133 |
This | +0.115 |
Right | +0.106 |
These | +0.104 |
Neg logit contributions | |
forgot | -0.290 |
waited | -0.262 |
stayed | -0.259 |
put | -0.257 |
never | -0.255 |
Token | . |
Token ID | 13 |
Feature activation | +6.12e-02 |
Pos logit contributions | |
Today | +0.111 |
Nice | +0.092 |
This | +0.089 |
These | +0.084 |
Of | +0.079 |
Neg logit contributions | |
forgot | -0.122 |
stayed | -0.110 |
waited | -0.110 |
remembered | -0.107 |
put | -0.107 |
Token |
|
Token ID | 198 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
rier | +0.113 |
Today | +0.110 |
uttering | +0.109 |
Nice | +0.104 |
andel | +0.101 |
Neg logit contributions | |
forgot | -0.116 |
put | -0.115 |
waited | -0.112 |
tried | -0.111 |
did | -0.108 |
Token |
|
Token ID | 198 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
Today | +0.044 |
Nice | +0.041 |
umm | +0.038 |
This | +0.035 |
oky | +0.035 |
Neg logit contributions | |
forgot | -0.064 |
put | -0.062 |
never | -0.060 |
waited | -0.059 |
tried | -0.058 |
Token | As |
Token ID | 1722 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
Today | +0.087 |
Nice | +0.076 |
This | +0.072 |
ummy | +0.066 |
Of | +0.066 |
Neg logit contributions | |
forgot | -0.076 |
waited | -0.069 |
put | -0.067 |
stayed | -0.066 |
never | -0.065 |
Token | hair |
Token ID | 4190 |
Feature activation | +4.77e-02 |
Pos logit contributions | |
Today | +0.063 |
Nice | +0.053 |
This | +0.053 |
These | +0.048 |
Of | +0.047 |
Neg logit contributions | |
forgot | -0.052 |
waited | -0.045 |
stayed | -0.045 |
remembered | -0.044 |
managed | -0.043 |
Token | salon |
Token ID | 46608 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
Today | +0.113 |
This | +0.096 |
Nice | +0.095 |
These | +0.088 |
ummy | +0.085 |
Neg logit contributions | |
forgot | -0.090 |
remembered | -0.079 |
waited | -0.077 |
stayed | -0.075 |
dug | -0.075 |
Token | and |
Token ID | 290 |
Feature activation | +7.86e-03 |
Pos logit contributions | |
Today | +0.055 |
This | +0.047 |
Nice | +0.044 |
These | +0.040 |
Of | +0.039 |
Neg logit contributions | |
forgot | -0.063 |
remembered | -0.057 |
waited | -0.057 |
stayed | -0.055 |
dug | -0.055 |
Token | getting |
Token ID | 1972 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
Today | +0.017 |
This | +0.017 |
Nice | +0.016 |
Of | +0.015 |
These | +0.015 |
Neg logit contributions | |
forgot | -0.011 |
ts | -0.011 |
punished | -0.010 |
dug | -0.010 |
ppy | -0.010 |
Token | different |
Token ID | 1180 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
Today | +0.030 |
Nice | +0.025 |
This | +0.025 |
These | +0.023 |
Of | +0.022 |
Neg logit contributions | |
forgot | -0.024 |
waited | -0.021 |
stayed | -0.021 |
remembered | -0.020 |
put | -0.019 |
Token | hairc |
Token ID | 37363 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
Today | +0.062 |
Nice | +0.053 |
This | +0.052 |
These | +0.048 |
Of | +0.045 |
Neg logit contributions | |
forgot | -0.058 |
waited | -0.052 |
stayed | -0.051 |
remembered | -0.050 |
put | -0.050 |
Token | uts |
Token ID | 5500 |
Feature activation | +5.57e-02 |
Pos logit contributions | |
Today | +0.163 |
Nice | +0.132 |
This | +0.115 |
These | +0.101 |
Of | +0.097 |
Neg logit contributions | |
forgot | -0.300 |
waited | -0.270 |
stayed | -0.267 |
put | -0.266 |
never | -0.262 |
Token | with |
Token ID | 351 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
Today | +0.108 |
Nice | +0.089 |
This | +0.086 |
These | +0.079 |
Of | +0.074 |
Neg logit contributions | |
forgot | -0.131 |
waited | -0.118 |
stayed | -0.118 |
remembered | -0.116 |
put | -0.115 |
Token | colorful |
Token ID | 20239 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
Today | +0.037 |
Nice | +0.032 |
This | +0.032 |
These | +0.029 |
Of | +0.028 |
Neg logit contributions | |
forgot | -0.033 |
waited | -0.029 |
remembered | -0.028 |
stayed | -0.028 |
dug | -0.027 |
Token | clips |
Token ID | 19166 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
Today | +0.063 |
Nice | +0.054 |
This | +0.054 |
These | +0.050 |
Of | +0.048 |
Neg logit contributions | |
forgot | -0.046 |
waited | -0.039 |
remembered | -0.039 |
stayed | -0.039 |
managed | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | +6.53e-02 |
Pos logit contributions | |
Today | +0.113 |
Nice | +0.092 |
This | +0.092 |
These | +0.082 |
ummy | +0.077 |
Neg logit contributions | |
forgot | -0.145 |
waited | -0.131 |
remembered | -0.130 |
stayed | -0.130 |
put | -0.125 |
Token | she |
Token ID | 673 |
Feature activation | -7.33e-02 |
Pos logit contributions | |
Today | +0.005 |
This | +0.004 |
Nice | +0.004 |
Of | +0.004 |
These | +0.004 |
Neg logit contributions | |
forgot | -0.012 |
dug | -0.011 |
managed | -0.011 |
remembered | -0.010 |
waited | -0.010 |
Token | could |
Token ID | 714 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
ts | +0.134 |
punished | +0.124 |
ep | +0.120 |
forgot | +0.117 |
scar | +0.117 |
Neg logit contributions | |
Today | -0.146 |
This | -0.129 |
Nice | -0.123 |
These | -0.114 |
Of | -0.112 |
Token | have |
Token ID | 423 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
forgot | +0.052 |
remembered | +0.044 |
waited | +0.043 |
stayed | +0.042 |
managed | +0.041 |
Neg logit contributions | |
Today | -0.088 |
This | -0.076 |
Nice | -0.073 |
These | -0.069 |
On | -0.067 |
Token | some |
Token ID | 617 |
Feature activation | -9.94e-03 |
Pos logit contributions | |
forgot | +0.069 |
remembered | +0.060 |
managed | +0.059 |
stayed | +0.058 |
waited | +0.058 |
Neg logit contributions | |
Today | -0.052 |
This | -0.047 |
These | -0.039 |
Nice | -0.038 |
A | -0.036 |
Token | more |
Token ID | 517 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
forgot | +0.018 |
remembered | +0.015 |
managed | +0.015 |
waited | +0.015 |
stayed | +0.014 |
Neg logit contributions | |
Today | -0.025 |
Nice | -0.021 |
This | -0.021 |
These | -0.020 |
ummy | -0.019 |
Token | h |
Token ID | 289 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
Today | +0.032 |
This | +0.027 |
Nice | +0.027 |
These | +0.025 |
Of | +0.024 |
Neg logit contributions | |
forgot | -0.020 |
remembered | -0.017 |
waited | -0.016 |
managed | -0.016 |
stayed | -0.016 |
Token | angers |
Token ID | 6606 |
Feature activation | +5.34e-02 |
Pos logit contributions | |
Today | +0.174 |
Nice | +0.140 |
This | +0.134 |
These | +0.115 |
Of | +0.110 |
Neg logit contributions | |
forgot | -0.278 |
waited | -0.255 |
stayed | -0.253 |
put | -0.249 |
remembered | -0.247 |
Token | . |
Token ID | 13 |
Feature activation | +7.43e-02 |
Pos logit contributions | |
Today | +0.104 |
This | +0.086 |
Nice | +0.085 |
These | +0.076 |
ummy | +0.072 |
Neg logit contributions | |
forgot | -0.122 |
waited | -0.110 |
remembered | -0.110 |
stayed | -0.108 |
dug | -0.104 |
Token |
|
Token ID | 198 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
Nice | +0.124 |
Today | +0.119 |
opl | +0.114 |
anes | +0.111 |
oky | +0.108 |
Neg logit contributions | |
waited | -0.162 |
put | -0.161 |
forgot | -0.154 |
tried | -0.151 |
stayed | -0.151 |
Token |
|
Token ID | 198 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
Today | +0.071 |
Nice | +0.070 |
umm | +0.064 |
oky | +0.058 |
opl | +0.057 |
Neg logit contributions | |
put | -0.084 |
forgot | -0.082 |
waited | -0.080 |
told | -0.080 |
never | -0.079 |
Token | " |
Token ID | 1 |
Feature activation | -2.54e-03 |
Pos logit contributions | |
Today | +0.092 |
Nice | +0.086 |
This | +0.075 |
anes | +0.072 |
opl | +0.069 |
Neg logit contributions | |
forgot | -0.097 |
waited | -0.093 |
put | -0.093 |
stayed | -0.091 |
never | -0.086 |
Token | would |
Token ID | 561 |
Feature activation | -3.84e-02 |
Pos logit contributions | |
ts | +0.098 |
ode | +0.097 |
managed | +0.097 |
forgot | +0.097 |
punished | +0.096 |
Neg logit contributions | |
Today | -0.171 |
This | -0.147 |
Nice | -0.136 |
On | -0.128 |
The | -0.128 |
Token | go |
Token ID | 467 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
forgot | +0.070 |
remembered | +0.062 |
ts | +0.061 |
waited | +0.061 |
managed | +0.061 |
Neg logit contributions | |
Today | -0.090 |
This | -0.078 |
Nice | -0.073 |
On | -0.067 |
These | -0.065 |
Token | outside |
Token ID | 2354 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
Today | +0.020 |
This | +0.016 |
Nice | +0.016 |
These | +0.014 |
Of | +0.013 |
Neg logit contributions | |
forgot | -0.024 |
waited | -0.021 |
stayed | -0.021 |
remembered | -0.021 |
managed | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +4.58e-03 |
Pos logit contributions | |
Today | +0.092 |
Nice | +0.080 |
This | +0.078 |
These | +0.073 |
Of | +0.068 |
Neg logit contributions | |
forgot | -0.078 |
waited | -0.070 |
stayed | -0.069 |
remembered | -0.068 |
put | -0.068 |
Token | fold |
Token ID | 5591 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
Today | +0.010 |
This | +0.009 |
Nice | +0.008 |
On | +0.008 |
Of | +0.008 |
Neg logit contributions | |
forgot | -0.009 |
managed | -0.007 |
ts | -0.007 |
remembered | -0.007 |
waited | -0.007 |
Token | orig |
Token ID | 1796 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
Today | +0.091 |
Nice | +0.078 |
This | +0.077 |
These | +0.071 |
Of | +0.068 |
Neg logit contributions | |
forgot | -0.071 |
waited | -0.062 |
stayed | -0.061 |
remembered | -0.061 |
put | -0.059 |
Token | ami |
Token ID | 6277 |
Feature activation | +8.63e-03 |
Pos logit contributions | |
Today | +0.230 |
Nice | +0.196 |
This | +0.189 |
These | +0.171 |
Of | +0.163 |
Neg logit contributions | |
forgot | -0.219 |
waited | -0.200 |
stayed | -0.198 |
remembered | -0.194 |
put | -0.192 |
Token | animals |
Token ID | 4695 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
Today | +0.018 |
This | +0.015 |
Nice | +0.015 |
These | +0.014 |
Of | +0.013 |
Neg logit contributions | |
forgot | -0.019 |
remembered | -0.017 |
waited | -0.016 |
stayed | -0.016 |
punished | -0.016 |
Token | in |
Token ID | 287 |
Feature activation | +4.71e-04 |
Pos logit contributions | |
Today | +0.051 |
This | +0.041 |
Nice | +0.040 |
These | +0.036 |
Of | +0.033 |
Neg logit contributions | |
forgot | -0.070 |
waited | -0.063 |
remembered | -0.063 |
stayed | -0.062 |
managed | -0.060 |
Token | her |
Token ID | 607 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
Today | +0.001 |
This | +0.001 |
Nice | +0.001 |
These | +0.001 |
Of | +0.001 |
Neg logit contributions | |
forgot | -0.001 |
waited | -0.001 |
stayed | -0.001 |
remembered | -0.001 |
managed | -0.001 |
Token | garden |
Token ID | 11376 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
forgot | +0.033 |
waited | +0.029 |
stayed | +0.028 |
remembered | +0.028 |
managed | +0.028 |
Neg logit contributions | |
Today | -0.042 |
This | -0.037 |
Nice | -0.034 |
These | -0.033 |
ummy | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +7.40e-02 |
Pos logit contributions | |
Today | +0.123 |
This | +0.098 |
Nice | +0.098 |
These | +0.086 |
ummy | +0.081 |
Neg logit contributions | |
forgot | -0.175 |
waited | -0.159 |
stayed | -0.158 |
remembered | -0.158 |
put | -0.152 |
Token | He |
Token ID | 679 |
Feature activation | -8.68e-02 |
Pos logit contributions | |
uttering | +0.111 |
owers | +0.103 |
Today | +0.102 |
Nice | +0.100 |
ore | +0.098 |
Neg logit contributions | |
forgot | -0.171 |
put | -0.170 |
waited | -0.160 |
tried | -0.158 |
stayed | -0.153 |
Token | didn |
Token ID | 1422 |
Feature activation | +2.79e-03 |
Pos logit contributions | |
ts | +0.115 |
forgot | +0.114 |
icians | +0.113 |
ode | +0.104 |
managed | +0.103 |
Neg logit contributions | |
Today | -0.177 |
On | -0.154 |
He | -0.143 |
One | -0.141 |
She | -0.139 |
Token | 't |
Token ID | 470 |
Feature activation | -3.93e-02 |
Pos logit contributions | |
Today | +0.006 |
Nice | +0.005 |
Of | +0.005 |
oky | +0.005 |
owers | +0.005 |
Neg logit contributions | |
forgot | -0.005 |
never | -0.005 |
put | -0.005 |
waited | -0.005 |
stayed | -0.005 |
Token | like |
Token ID | 588 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
forgot | +0.074 |
waited | +0.067 |
stayed | +0.066 |
remembered | +0.065 |
ts | +0.065 |
Neg logit contributions | |
Today | -0.093 |
This | -0.075 |
Nice | -0.068 |
On | -0.065 |
These | -0.062 |
Token | hairc |
Token ID | 37363 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Today | +0.028 |
This | +0.025 |
Nice | +0.024 |
These | +0.022 |
Of | +0.021 |
Neg logit contributions | |
forgot | -0.027 |
remembered | -0.024 |
waited | -0.023 |
stayed | -0.023 |
managed | -0.023 |
Token | uts |
Token ID | 5500 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
Today | +0.150 |
Nice | +0.120 |
This | +0.104 |
These | +0.091 |
Of | +0.087 |
Neg logit contributions | |
forgot | -0.307 |
waited | -0.276 |
stayed | -0.273 |
remembered | -0.270 |
put | -0.268 |
Token | because |
Token ID | 780 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
Today | +0.078 |
Nice | +0.066 |
This | +0.064 |
These | +0.060 |
Of | +0.057 |
Neg logit contributions | |
forgot | -0.074 |
stayed | -0.066 |
waited | -0.066 |
remembered | -0.064 |
put | -0.064 |
Token | they |
Token ID | 484 |
Feature activation | -5.38e-02 |
Pos logit contributions | |
Today | +0.087 |
Nice | +0.072 |
This | +0.072 |
These | +0.065 |
Of | +0.061 |
Neg logit contributions | |
forgot | -0.099 |
waited | -0.088 |
remembered | -0.088 |
stayed | -0.087 |
managed | -0.085 |
Token | made |
Token ID | 925 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
forgot | +0.077 |
remembered | +0.074 |
dug | +0.071 |
managed | +0.070 |
waited | +0.070 |
Neg logit contributions | |
Today | -0.111 |
This | -0.101 |
free | -0.090 |
These | -0.089 |
On | -0.088 |
Token | him |
Token ID | 683 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
Today | +0.025 |
Nice | +0.022 |
This | +0.021 |
These | +0.020 |
Of | +0.019 |
Neg logit contributions | |
forgot | -0.021 |
waited | -0.019 |
stayed | -0.018 |
remembered | -0.018 |
put | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | -5.82e-03 |
Pos logit contributions | |
Today | +0.097 |
Nice | +0.084 |
This | +0.079 |
opl | +0.075 |
ummy | +0.075 |
Neg logit contributions | |
forgot | -0.072 |
waited | -0.067 |
remembered | -0.065 |
put | -0.065 |
tried | -0.064 |
Token | lot |
Token ID | 1256 |
Feature activation | +6.05e-03 |
Pos logit contributions | |
forgot | +0.011 |
waited | +0.009 |
stayed | +0.009 |
remembered | +0.009 |
put | +0.009 |
Neg logit contributions | |
Today | -0.014 |
Nice | -0.012 |
This | -0.012 |
These | -0.011 |
Of | -0.011 |
Token | of |
Token ID | 286 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
Today | +0.011 |
Nice | +0.009 |
This | +0.009 |
These | +0.008 |
Of | +0.007 |
Neg logit contributions | |
forgot | -0.015 |
waited | -0.014 |
stayed | -0.014 |
remembered | -0.014 |
put | -0.013 |
Token | people |
Token ID | 661 |
Feature activation | -3.27e-03 |
Pos logit contributions | |
Today | +0.022 |
This | +0.018 |
Nice | +0.018 |
These | +0.017 |
Of | +0.016 |
Neg logit contributions | |
forgot | -0.022 |
stayed | -0.018 |
remembered | -0.018 |
managed | -0.018 |
waited | -0.018 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
forgot | +0.004 |
waited | +0.004 |
remembered | +0.004 |
stayed | +0.004 |
managed | +0.004 |
Neg logit contributions | |
Today | -0.009 |
This | -0.008 |
Nice | -0.008 |
These | -0.007 |
ore | -0.007 |
Token | hairc |
Token ID | 37363 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
forgot | +0.029 |
remembered | +0.026 |
waited | +0.026 |
stayed | +0.026 |
managed | +0.025 |
Neg logit contributions | |
Today | -0.025 |
This | -0.021 |
Nice | -0.021 |
These | -0.018 |
Of | -0.017 |
Token | uts |
Token ID | 5500 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
Today | +0.161 |
Nice | +0.129 |
This | +0.114 |
These | +0.101 |
Right | +0.099 |
Neg logit contributions | |
forgot | -0.285 |
waited | -0.256 |
stayed | -0.252 |
put | -0.249 |
never | -0.249 |
Token | . |
Token ID | 13 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
Today | +0.088 |
Nice | +0.074 |
This | +0.073 |
These | +0.070 |
Of | +0.065 |
Neg logit contributions | |
forgot | -0.079 |
stayed | -0.072 |
waited | -0.070 |
put | -0.070 |
remembered | -0.068 |
Token | The |
Token ID | 383 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
Today | +0.097 |
Nice | +0.080 |
uttering | +0.071 |
opl | +0.069 |
ummy | +0.067 |
Neg logit contributions | |
forgot | -0.183 |
waited | -0.178 |
put | -0.174 |
tried | -0.170 |
stayed | -0.170 |
Token | bar |
Token ID | 2318 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
Today | +0.025 |
Nice | +0.021 |
This | +0.021 |
These | +0.019 |
Of | +0.018 |
Neg logit contributions | |
forgot | -0.020 |
waited | -0.018 |
stayed | -0.017 |
remembered | -0.017 |
put | -0.017 |
Token | ber |
Token ID | 527 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
Today | +0.034 |
Nice | +0.029 |
This | +0.029 |
These | +0.027 |
Of | +0.026 |
Neg logit contributions | |
forgot | -0.031 |
waited | -0.027 |
stayed | -0.027 |
remembered | -0.026 |
put | -0.026 |
Token | fold |
Token ID | 5591 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
forgot | +0.021 |
ils | +0.019 |
remembered | +0.019 |
ts | +0.019 |
ppy | +0.019 |
Neg logit contributions | |
Today | -0.026 |
This | -0.025 |
On | -0.023 |
Of | -0.023 |
Nice | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +5.98e-04 |
Pos logit contributions | |
Today | +0.099 |
This | +0.084 |
Nice | +0.083 |
These | +0.076 |
Of | +0.073 |
Neg logit contributions | |
forgot | -0.081 |
waited | -0.071 |
stayed | -0.070 |
remembered | -0.070 |
managed | -0.066 |
Token | knob |
Token ID | 36842 |
Feature activation | +4.94e-02 |
Pos logit contributions | |
Today | +0.001 |
Nice | +0.001 |
This | +0.001 |
These | +0.001 |
Of | +0.001 |
Neg logit contributions | |
forgot | -0.001 |
waited | -0.001 |
stayed | -0.001 |
remembered | -0.001 |
put | -0.001 |
Token | into |
Token ID | 656 |
Feature activation | +6.93e-03 |
Pos logit contributions | |
Today | +0.098 |
Nice | +0.081 |
This | +0.080 |
These | +0.072 |
Of | +0.068 |
Neg logit contributions | |
forgot | -0.113 |
waited | -0.102 |
stayed | -0.101 |
remembered | -0.100 |
put | -0.098 |
Token | an |
Token ID | 281 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
Today | +0.013 |
This | +0.011 |
Nice | +0.010 |
These | +0.010 |
Of | +0.010 |
Neg logit contributions | |
forgot | -0.016 |
stayed | -0.014 |
remembered | -0.014 |
waited | -0.014 |
managed | -0.013 |
Token | orig |
Token ID | 1796 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Today | +0.030 |
This | +0.025 |
Nice | +0.025 |
These | +0.023 |
ummy | +0.022 |
Neg logit contributions | |
forgot | -0.028 |
waited | -0.024 |
stayed | -0.024 |
remembered | -0.024 |
managed | -0.023 |
Token | ami |
Token ID | 6277 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
Today | +0.223 |
Nice | +0.189 |
This | +0.185 |
These | +0.168 |
Of | +0.159 |
Neg logit contributions | |
forgot | -0.223 |
waited | -0.201 |
stayed | -0.199 |
remembered | -0.197 |
put | -0.192 |
Token | figure |
Token ID | 3785 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
Today | +0.037 |
This | +0.030 |
Nice | +0.028 |
These | +0.026 |
Of | +0.024 |
Neg logit contributions | |
forgot | -0.047 |
remembered | -0.041 |
waited | -0.041 |
stayed | -0.041 |
punished | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +6.89e-02 |
Pos logit contributions | |
Today | +0.034 |
This | +0.027 |
Nice | +0.026 |
These | +0.023 |
Of | +0.022 |
Neg logit contributions | |
forgot | -0.052 |
waited | -0.047 |
remembered | -0.047 |
stayed | -0.046 |
put | -0.045 |
Token | But |
Token ID | 887 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
Today | +0.085 |
Nice | +0.074 |
uttering | +0.063 |
opl | +0.063 |
anes | +0.055 |
Neg logit contributions | |
waited | -0.185 |
forgot | -0.182 |
put | -0.181 |
tried | -0.175 |
stayed | -0.172 |
Token | no |
Token ID | 645 |
Feature activation | -5.36e-03 |
Pos logit contributions | |
Today | +0.040 |
This | +0.034 |
Nice | +0.032 |
Of | +0.030 |
These | +0.029 |
Neg logit contributions | |
forgot | -0.040 |
remembered | -0.034 |
stayed | -0.034 |
waited | -0.034 |
punished | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
Today | +0.128 |
Nice | +0.108 |
This | +0.102 |
These | +0.096 |
Of | +0.092 |
Neg logit contributions | |
forgot | -0.123 |
stayed | -0.113 |
waited | -0.111 |
put | -0.110 |
remembered | -0.105 |
Token | She |
Token ID | 1375 |
Feature activation | -8.70e-02 |
Pos logit contributions | |
Today | +0.078 |
uttering | +0.073 |
ower | +0.068 |
oky | +0.065 |
Nice | +0.065 |
Neg logit contributions | |
forgot | -0.158 |
never | -0.151 |
learned | -0.146 |
put | -0.144 |
stayed | -0.141 |
Token | also |
Token ID | 635 |
Feature activation | -6.59e-02 |
Pos logit contributions | |
ts | +0.142 |
punished | +0.133 |
mercy | +0.125 |
cher | +0.115 |
wounds | +0.114 |
Neg logit contributions | |
Today | -0.161 |
Nice | -0.132 |
Everywhere | -0.131 |
Round | -0.130 |
She | -0.130 |
Token | loved |
Token ID | 6151 |
Feature activation | +8.02e-03 |
Pos logit contributions | |
ts | +0.089 |
ode | +0.078 |
wounds | +0.070 |
punished | +0.069 |
cast | +0.064 |
Neg logit contributions | |
Today | -0.158 |
This | -0.145 |
Nice | -0.133 |
She | -0.131 |
The | -0.130 |
Token | taking |
Token ID | 2263 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
Today | +0.016 |
Nice | +0.014 |
This | +0.014 |
These | +0.013 |
Of | +0.012 |
Neg logit contributions | |
forgot | -0.018 |
waited | -0.016 |
remembered | -0.015 |
stayed | -0.015 |
punished | -0.015 |
Token | quizz |
Token ID | 48258 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Today | +0.041 |
This | +0.036 |
Nice | +0.035 |
These | +0.032 |
Of | +0.031 |
Neg logit contributions | |
forgot | -0.042 |
waited | -0.037 |
stayed | -0.037 |
remembered | -0.037 |
punished | -0.035 |
Token | es |
Token ID | 274 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
Today | +0.276 |
Nice | +0.239 |
This | +0.234 |
These | +0.218 |
Of | +0.211 |
Neg logit contributions | |
forgot | -0.165 |
waited | -0.143 |
stayed | -0.141 |
remembered | -0.138 |
put | -0.135 |
Token | to |
Token ID | 284 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
Today | +0.070 |
Nice | +0.060 |
This | +0.059 |
These | +0.053 |
Of | +0.050 |
Neg logit contributions | |
forgot | -0.072 |
waited | -0.065 |
remembered | -0.064 |
stayed | -0.063 |
dug | -0.061 |
Token | learn |
Token ID | 2193 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
forgot | +0.024 |
waited | +0.021 |
remembered | +0.021 |
stayed | +0.021 |
managed | +0.020 |
Neg logit contributions | |
Today | -0.034 |
This | -0.029 |
Nice | -0.029 |
These | -0.027 |
Of | -0.026 |
Token | new |
Token ID | 649 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
Today | +0.061 |
Nice | +0.051 |
This | +0.051 |
These | +0.047 |
Of | +0.044 |
Neg logit contributions | |
forgot | -0.052 |
stayed | -0.046 |
waited | -0.046 |
remembered | -0.045 |
put | -0.044 |
Token | things |
Token ID | 1243 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
Today | +0.055 |
Nice | +0.047 |
This | +0.046 |
These | +0.042 |
Of | +0.040 |
Neg logit contributions | |
forgot | -0.054 |
waited | -0.048 |
stayed | -0.047 |
remembered | -0.047 |
put | -0.045 |
Token | ways |
Token ID | 2842 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
Today | +0.041 |
This | +0.034 |
Nice | +0.034 |
These | +0.031 |
Of | +0.031 |
Neg logit contributions | |
forgot | -0.036 |
waited | -0.032 |
stayed | -0.032 |
remembered | -0.031 |
managed | -0.031 |
Token | to |
Token ID | 284 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
Today | +0.090 |
Nice | +0.075 |
This | +0.074 |
These | +0.070 |
Of | +0.065 |
Neg logit contributions | |
forgot | -0.072 |
stayed | -0.065 |
waited | -0.064 |
remembered | -0.063 |
put | -0.063 |
Token | make |
Token ID | 787 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
forgot | +0.039 |
remembered | +0.033 |
waited | +0.033 |
stayed | +0.032 |
managed | +0.031 |
Neg logit contributions | |
Today | -0.047 |
This | -0.044 |
These | -0.039 |
Nice | -0.038 |
Of | -0.038 |
Token | it |
Token ID | 340 |
Feature activation | -6.62e-03 |
Pos logit contributions | |
Today | +0.055 |
This | +0.048 |
Nice | +0.047 |
These | +0.044 |
ummy | +0.043 |
Neg logit contributions | |
forgot | -0.044 |
waited | -0.039 |
stayed | -0.038 |
remembered | -0.038 |
managed | -0.036 |
Token | even |
Token ID | 772 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
forgot | +0.012 |
waited | +0.011 |
remembered | +0.010 |
stayed | +0.010 |
managed | +0.010 |
Neg logit contributions | |
Today | -0.016 |
This | -0.014 |
Nice | -0.014 |
These | -0.012 |
Of | -0.012 |
Token | swe |
Token ID | 3490 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
forgot | +0.025 |
waited | +0.023 |
stayed | +0.022 |
remembered | +0.022 |
never | +0.022 |
Neg logit contributions | |
Today | -0.035 |
Nice | -0.030 |
This | -0.030 |
Of | -0.028 |
These | -0.026 |
Token | eter |
Token ID | 2357 |
Feature activation | +5.31e-02 |
Pos logit contributions | |
Today | +0.202 |
Nice | +0.172 |
This | +0.164 |
These | +0.149 |
Of | +0.140 |
Neg logit contributions | |
forgot | -0.229 |
waited | -0.208 |
stayed | -0.207 |
remembered | -0.205 |
put | -0.202 |
Token | . |
Token ID | 13 |
Feature activation | +6.81e-02 |
Pos logit contributions | |
Today | +0.108 |
Nice | +0.089 |
This | +0.086 |
These | +0.081 |
On | +0.074 |
Neg logit contributions | |
forgot | -0.119 |
waited | -0.112 |
stayed | -0.109 |
put | -0.107 |
remembered | -0.106 |
Token | They |
Token ID | 1119 |
Feature activation | -6.49e-02 |
Pos logit contributions | |
Today | +0.105 |
uttering | +0.084 |
Nice | +0.084 |
owers | +0.077 |
oky | +0.076 |
Neg logit contributions | |
forgot | -0.173 |
never | -0.157 |
learned | -0.154 |
put | -0.152 |
stayed | -0.151 |
Token | were |
Token ID | 547 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
wounds | +0.101 |
punished | +0.100 |
plank | +0.095 |
ts | +0.095 |
tries | +0.095 |
Neg logit contributions | |
Today | -0.095 |
The | -0.090 |
owers | -0.085 |
She | -0.084 |
This | -0.080 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
forgot | +0.078 |
waited | +0.070 |
hid | +0.068 |
dug | +0.068 |
remembered | +0.066 |
Neg logit contributions | |
Today | -0.070 |
This | -0.062 |
Nice | -0.058 |
These | -0.053 |
ummy | -0.052 |
Token | caught |
Token ID | 4978 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
forgot | +0.023 |
ts | +0.021 |
waited | +0.020 |
ode | +0.019 |
punished | +0.019 |
Neg logit contributions | |
Today | -0.045 |
This | -0.044 |
Nice | -0.042 |
Up | -0.038 |
Where | -0.037 |
Token | her |
Token ID | 607 |
Feature activation | -1.79e-03 |
Pos logit contributions | |
Today | +0.031 |
Nice | +0.027 |
This | +0.026 |
These | +0.024 |
Of | +0.023 |
Neg logit contributions | |
forgot | -0.025 |
waited | -0.022 |
stayed | -0.021 |
remembered | -0.021 |
put | -0.020 |
Token | dress |
Token ID | 6576 |
Feature activation | +5.16e-02 |
Pos logit contributions | |
forgot | +0.003 |
waited | +0.003 |
stayed | +0.003 |
remembered | +0.003 |
managed | +0.003 |
Neg logit contributions | |
Today | -0.005 |
Nice | -0.004 |
This | -0.004 |
These | -0.004 |
ummy | -0.003 |
Token | on |
Token ID | 319 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
Today | +0.100 |
Nice | +0.082 |
This | +0.081 |
These | +0.072 |
ummy | +0.069 |
Neg logit contributions | |
forgot | -0.121 |
waited | -0.110 |
remembered | -0.108 |
stayed | -0.108 |
put | -0.104 |
Token | a |
Token ID | 257 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
Today | +0.065 |
Nice | +0.056 |
This | +0.055 |
These | +0.051 |
Of | +0.049 |
Neg logit contributions | |
forgot | -0.046 |
waited | -0.041 |
stayed | -0.040 |
remembered | -0.040 |
put | -0.039 |
Token | h |
Token ID | 289 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Today | +0.024 |
Nice | +0.021 |
This | +0.021 |
These | +0.019 |
ummy | +0.018 |
Neg logit contributions | |
forgot | -0.018 |
waited | -0.016 |
stayed | -0.016 |
remembered | -0.016 |
put | -0.015 |
Token | anger |
Token ID | 2564 |
Feature activation | +5.57e-02 |
Pos logit contributions | |
Today | +0.141 |
Nice | +0.106 |
This | +0.104 |
These | +0.087 |
Of | +0.079 |
Neg logit contributions | |
forgot | -0.299 |
waited | -0.276 |
stayed | -0.274 |
remembered | -0.273 |
put | -0.267 |
Token | . |
Token ID | 13 |
Feature activation | +7.23e-02 |
Pos logit contributions | |
Today | +0.104 |
Nice | +0.085 |
This | +0.084 |
These | +0.075 |
Of | +0.070 |
Neg logit contributions | |
forgot | -0.135 |
waited | -0.121 |
remembered | -0.120 |
stayed | -0.120 |
put | -0.116 |
Token | She |
Token ID | 1375 |
Feature activation | -8.12e-02 |
Pos logit contributions | |
Today | +0.120 |
opl | +0.113 |
Nice | +0.110 |
uttering | +0.106 |
oky | +0.099 |
Neg logit contributions | |
waited | -0.158 |
forgot | -0.157 |
tried | -0.157 |
put | -0.154 |
hid | -0.144 |
Token | felt |
Token ID | 2936 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
ode | +0.155 |
mate | +0.142 |
least | +0.140 |
plank | +0.133 |
ologist | +0.130 |
Neg logit contributions | |
She | -0.110 |
This | -0.105 |
Today | -0.104 |
The | -0.103 |
On | -0.098 |
Token | embarrassed |
Token ID | 21100 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
forgot | +0.028 |
waited | +0.025 |
stayed | +0.025 |
remembered | +0.025 |
put | +0.024 |
Neg logit contributions | |
Today | -0.028 |
Nice | -0.023 |
This | -0.023 |
These | -0.021 |
Of | -0.020 |
Token | now |
Token ID | 783 |
Feature activation | +2.03e-04 |
Pos logit contributions | |
Today | +0.053 |
This | +0.045 |
Nice | +0.045 |
These | +0.042 |
anes | +0.039 |
Neg logit contributions | |
forgot | -0.047 |
remembered | -0.041 |
waited | -0.041 |
stayed | -0.041 |
put | -0.040 |
Token | she |
Token ID | 673 |
Feature activation | -5.88e-02 |
Pos logit contributions | |
Today | +0.000 |
This | +0.000 |
Nice | +0.000 |
These | +0.000 |
Of | +0.000 |
Neg logit contributions | |
forgot | -0.001 |
waited | -0.000 |
stayed | -0.000 |
punished | -0.000 |
ts | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
ts | +0.072 |
punished | +0.066 |
forgot | +0.065 |
argued | +0.061 |
fought | +0.057 |
Neg logit contributions | |
Today | -0.134 |
Nice | -0.127 |
This | -0.117 |
| -0.112 |
Right | -0.110 |
Token | feeling |
Token ID | 4203 |
Feature activation | +3.65e-03 |
Pos logit contributions | |
forgot | +0.066 |
waited | +0.059 |
ts | +0.056 |
stayed | +0.056 |
remembered | +0.055 |
Neg logit contributions | |
Today | -0.081 |
This | -0.069 |
Nice | -0.068 |
ummy | -0.059 |
These | -0.059 |
Token | much |
Token ID | 881 |
Feature activation | +1.72e-03 |
Pos logit contributions | |
Today | +0.008 |
Nice | +0.007 |
This | +0.007 |
These | +0.006 |
Of | +0.006 |
Neg logit contributions | |
forgot | -0.008 |
waited | -0.007 |
stayed | -0.007 |
remembered | -0.007 |
put | -0.006 |
Token | cal |
Token ID | 2386 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
Today | +0.004 |
Nice | +0.004 |
This | +0.003 |
These | +0.003 |
Of | +0.003 |
Neg logit contributions | |
forgot | -0.003 |
waited | -0.003 |
stayed | -0.003 |
remembered | -0.003 |
dug | -0.003 |
Token | mer |
Token ID | 647 |
Feature activation | +5.06e-02 |
Pos logit contributions | |
Today | +0.208 |
Nice | +0.174 |
This | +0.165 |
These | +0.150 |
Everywhere | +0.141 |
Neg logit contributions | |
forgot | -0.242 |
waited | -0.218 |
stayed | -0.213 |
remembered | -0.212 |
put | -0.211 |
Token | and |
Token ID | 290 |
Feature activation | +8.43e-03 |
Pos logit contributions | |
Today | +0.103 |
Nice | +0.086 |
This | +0.085 |
These | +0.077 |
Of | +0.073 |
Neg logit contributions | |
forgot | -0.113 |
waited | -0.101 |
stayed | -0.100 |
remembered | -0.100 |
put | -0.097 |
Token | also |
Token ID | 635 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
Today | +0.017 |
Nice | +0.015 |
This | +0.014 |
Of | +0.013 |
Right | +0.012 |
Neg logit contributions | |
forgot | -0.017 |
ts | -0.015 |
waited | -0.015 |
dug | -0.015 |
remembered | -0.015 |
Token | had |
Token ID | 550 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
forgot | +0.049 |
ts | +0.047 |
waited | +0.043 |
stayed | +0.040 |
dug | +0.039 |
Neg logit contributions | |
Today | -0.090 |
This | -0.081 |
Nice | -0.078 |
Of | -0.071 |
Right | -0.070 |
Token | some |
Token ID | 617 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
forgot | +0.081 |
ts | +0.078 |
punished | +0.071 |
waited | +0.070 |
hid | +0.069 |
Neg logit contributions | |
Today | -0.071 |
This | -0.069 |
Nice | -0.061 |
Everywhere | -0.054 |
The | -0.054 |
Token | hang |
Token ID | 8181 |
Feature activation | +6.57e-02 |
Pos logit contributions | |
forgot | +0.068 |
remembered | +0.061 |
waited | +0.058 |
managed | +0.058 |
stayed | +0.056 |
Neg logit contributions | |
Today | -0.089 |
This | -0.080 |
Nice | -0.070 |
These | -0.069 |
On | -0.068 |
Token | her |
Token ID | 607 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
Today | +0.176 |
Nice | +0.155 |
These | +0.149 |
This | +0.148 |
oky | +0.141 |
Neg logit contributions | |
forgot | -0.094 |
put | -0.094 |
stayed | -0.089 |
waited | -0.086 |
never | -0.085 |
Token | dress |
Token ID | 6576 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
forgot | +0.018 |
waited | +0.015 |
remembered | +0.015 |
managed | +0.015 |
stayed | +0.015 |
Neg logit contributions | |
Today | -0.033 |
This | -0.029 |
Nice | -0.029 |
These | -0.026 |
Of | -0.026 |
Token | on |
Token ID | 319 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
Today | +0.103 |
Nice | +0.087 |
This | +0.085 |
These | +0.079 |
Of | +0.074 |
Neg logit contributions | |
forgot | -0.102 |
waited | -0.091 |
stayed | -0.091 |
put | -0.089 |
remembered | -0.089 |
Token | the |
Token ID | 262 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
Today | +0.067 |
Nice | +0.060 |
This | +0.057 |
These | +0.055 |
Of | +0.052 |
Neg logit contributions | |
forgot | -0.044 |
waited | -0.040 |
put | -0.039 |
stayed | -0.039 |
remembered | -0.037 |
Token | h |
Token ID | 289 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
Today | +0.072 |
This | +0.062 |
Nice | +0.061 |
These | +0.056 |
ummy | +0.055 |
Neg logit contributions | |
forgot | -0.058 |
remembered | -0.050 |
waited | -0.049 |
managed | -0.048 |
stayed | -0.048 |
Token | anger |
Token ID | 2564 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
Today | +0.150 |
Nice | +0.117 |
This | +0.112 |
These | +0.096 |
Of | +0.089 |
Neg logit contributions | |
forgot | -0.286 |
waited | -0.264 |
stayed | -0.262 |
remembered | -0.258 |
put | -0.255 |
Token | , |
Token ID | 11 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
Today | +0.100 |
Nice | +0.083 |
This | +0.082 |
These | +0.074 |
Of | +0.070 |
Neg logit contributions | |
forgot | -0.114 |
waited | -0.102 |
stayed | -0.101 |
remembered | -0.101 |
put | -0.098 |
Token | but |
Token ID | 475 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
Today | +0.051 |
This | +0.042 |
Nice | +0.042 |
These | +0.036 |
Of | +0.036 |
Neg logit contributions | |
forgot | -0.060 |
remembered | -0.054 |
waited | -0.053 |
stayed | -0.053 |
managed | -0.052 |
Token | it |
Token ID | 340 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
Today | +0.032 |
This | +0.026 |
Nice | +0.025 |
Of | +0.022 |
These | +0.021 |
Neg logit contributions | |
forgot | -0.040 |
waited | -0.035 |
managed | -0.035 |
punished | -0.035 |
ts | -0.035 |
Token | was |
Token ID | 373 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
ts | +0.033 |
forgot | +0.033 |
remembered | +0.029 |
ils | +0.029 |
ppa | +0.029 |
Neg logit contributions | |
Today | -0.043 |
This | -0.036 |
Nice | -0.035 |
On | -0.032 |
ained | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +6.35e-02 |
Pos logit contributions | |
Today | +0.029 |
Nice | +0.024 |
This | +0.024 |
These | +0.022 |
Of | +0.021 |
Neg logit contributions | |
forgot | -0.032 |
waited | -0.029 |
stayed | -0.028 |
remembered | -0.028 |
put | -0.027 |
Token | He |
Token ID | 679 |
Feature activation | -8.53e-02 |
Pos logit contributions | |
Today | +0.139 |
Nice | +0.124 |
anes | +0.114 |
opl | +0.111 |
owers | +0.109 |
Neg logit contributions | |
forgot | -0.126 |
waited | -0.112 |
put | -0.111 |
stayed | -0.108 |
cleaned | -0.108 |
Token | used |
Token ID | 973 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
ts | +0.137 |
plank | +0.124 |
ode | +0.118 |
ptions | +0.101 |
icians | +0.096 |
Neg logit contributions | |
Today | -0.163 |
On | -0.142 |
She | -0.139 |
The | -0.137 |
A | -0.134 |
Token | to |
Token ID | 284 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
forgot | +0.043 |
remembered | +0.036 |
waited | +0.036 |
stayed | +0.035 |
managed | +0.033 |
Neg logit contributions | |
Today | -0.034 |
This | -0.031 |
Nice | -0.027 |
Everywhere | -0.026 |
These | -0.025 |
Token | love |
Token ID | 1842 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
forgot | +0.088 |
remembered | +0.073 |
managed | +0.073 |
waited | +0.070 |
ils | +0.068 |
Neg logit contributions | |
Today | -0.124 |
This | -0.106 |
Nice | -0.091 |
On | -0.090 |
These | -0.089 |
Token | po |
Token ID | 745 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
Today | +0.041 |
This | +0.037 |
Nice | +0.035 |
ummy | +0.032 |
These | +0.031 |
Neg logit contributions | |
forgot | -0.051 |
waited | -0.044 |
remembered | -0.043 |
managed | -0.043 |
stayed | -0.042 |
Token | pp |
Token ID | 381 |
Feature activation | +6.08e-02 |
Pos logit contributions | |
Today | +0.261 |
Nice | +0.222 |
This | +0.214 |
These | +0.199 |
Right | +0.195 |
Neg logit contributions | |
forgot | -0.179 |
stayed | -0.157 |
remembered | -0.153 |
waited | -0.153 |
put | -0.151 |
Token | ies |
Token ID | 444 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
Today | +0.156 |
This | +0.138 |
Nice | +0.136 |
These | +0.128 |
ummy | +0.128 |
Neg logit contributions | |
forgot | -0.098 |
waited | -0.088 |
remembered | -0.084 |
stayed | -0.082 |
hid | -0.077 |
Token | and |
Token ID | 290 |
Feature activation | +8.70e-03 |
Pos logit contributions | |
Today | +0.083 |
This | +0.071 |
Nice | +0.070 |
These | +0.063 |
ummy | +0.059 |
Neg logit contributions | |
forgot | -0.092 |
waited | -0.083 |
remembered | -0.081 |
dug | -0.079 |
stayed | -0.078 |
Token | always |
Token ID | 1464 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
Today | +0.017 |
This | +0.017 |
Nice | +0.016 |
Of | +0.015 |
These | +0.015 |
Neg logit contributions | |
forgot | -0.013 |
ts | -0.012 |
managed | -0.011 |
punished | -0.011 |
ppy | -0.011 |
Token | had |
Token ID | 550 |
Feature activation | -4.52e-02 |
Pos logit contributions | |
ts | +0.031 |
forgot | +0.031 |
ils | +0.027 |
managed | +0.024 |
punished | +0.024 |
Neg logit contributions | |
Today | -0.090 |
This | -0.083 |
Nice | -0.081 |
Of | -0.080 |
Right | -0.071 |
Token | have |
Token ID | 423 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
forgot | +0.079 |
remembered | +0.070 |
ts | +0.067 |
managed | +0.065 |
stayed | +0.065 |
Neg logit contributions | |
Today | -0.092 |
This | -0.074 |
On | -0.068 |
These | -0.065 |
ore | -0.064 |
Token | to |
Token ID | 284 |
Feature activation | -5.03e-02 |
Pos logit contributions | |
forgot | +0.099 |
remembered | +0.087 |
managed | +0.085 |
ts | +0.085 |
punished | +0.084 |
Neg logit contributions | |
Today | -0.056 |
This | -0.050 |
Nice | -0.040 |
These | -0.039 |
ummy | -0.036 |
Token | take |
Token ID | 1011 |
Feature activation | +9.28e-03 |
Pos logit contributions | |
forgot | +0.092 |
managed | +0.080 |
remembered | +0.079 |
hid | +0.073 |
ils | +0.072 |
Neg logit contributions | |
Today | -0.119 |
This | -0.099 |
On | -0.084 |
east | -0.083 |
These | -0.082 |
Token | an |
Token ID | 281 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
Today | +0.021 |
This | +0.019 |
Nice | +0.017 |
These | +0.017 |
Of | +0.016 |
Neg logit contributions | |
forgot | -0.019 |
remembered | -0.016 |
stayed | -0.016 |
waited | -0.016 |
managed | -0.015 |
Token | aer |
Token ID | 9551 |
Feature activation | +7.08e-02 |
Pos logit contributions | |
Today | +0.044 |
Nice | +0.037 |
This | +0.037 |
These | +0.034 |
ummy | +0.033 |
Neg logit contributions | |
forgot | -0.034 |
waited | -0.029 |
remembered | -0.029 |
stayed | -0.029 |
managed | -0.028 |
Token | opl |
Token ID | 20106 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
Today | +0.080 |
Nice | +0.061 |
This | +0.054 |
These | +0.047 |
Of | +0.044 |
Neg logit contributions | |
forgot | -0.216 |
waited | -0.201 |
never | -0.200 |
stayed | -0.199 |
put | -0.196 |
Token | ane |
Token ID | 1531 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
Today | +0.148 |
Nice | +0.126 |
This | +0.104 |
Everywhere | +0.093 |
Right | +0.089 |
Neg logit contributions | |
forgot | -0.252 |
waited | -0.250 |
stayed | -0.242 |
never | -0.241 |
put | -0.239 |
Token | ." |
Token ID | 526 |
Feature activation | +5.22e-02 |
Pos logit contributions | |
Today | +0.085 |
This | +0.070 |
Nice | +0.069 |
These | +0.061 |
ummy | +0.058 |
Neg logit contributions | |
forgot | -0.098 |
remembered | -0.087 |
waited | -0.086 |
stayed | -0.086 |
managed | -0.083 |
Token |
|
Token ID | 198 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
Today | +0.130 |
Nice | +0.120 |
anes | +0.109 |
opl | +0.109 |
uttering | +0.108 |
Neg logit contributions | |
forgot | -0.090 |
waited | -0.078 |
put | -0.078 |
tried | -0.074 |
cleaned | -0.073 |
Token |
|
Token ID | 198 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
Today | +0.066 |
Nice | +0.060 |
umm | +0.053 |
opl | +0.052 |
owers | +0.052 |
Neg logit contributions | |
forgot | -0.089 |
put | -0.085 |
cleaned | -0.080 |
waited | -0.080 |
tried | -0.079 |
Token | L |
Token ID | 43 |
Feature activation | +8.99e-03 |
Pos logit contributions | |
Today | +0.086 |
This | +0.072 |
Nice | +0.071 |
These | +0.066 |
Of | +0.063 |
Neg logit contributions | |
forgot | -0.078 |
stayed | -0.069 |
waited | -0.069 |
remembered | -0.068 |
managed | -0.066 |
Token | go |
Token ID | 467 |
Feature activation | +9.09e-03 |
Pos logit contributions | |
forgot | +0.034 |
waited | +0.029 |
remembered | +0.029 |
stayed | +0.029 |
managed | +0.028 |
Neg logit contributions | |
Today | -0.056 |
This | -0.048 |
Nice | -0.047 |
These | -0.044 |
Of | -0.042 |
Token | with |
Token ID | 351 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
Today | +0.021 |
Nice | +0.018 |
This | +0.018 |
These | +0.016 |
Of | +0.016 |
Neg logit contributions | |
forgot | -0.018 |
waited | -0.016 |
stayed | -0.016 |
remembered | -0.016 |
put | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | -8.97e-03 |
Pos logit contributions | |
Today | +0.036 |
This | +0.032 |
Nice | +0.031 |
These | +0.029 |
ummy | +0.028 |
Neg logit contributions | |
forgot | -0.032 |
waited | -0.028 |
remembered | -0.027 |
stayed | -0.027 |
managed | -0.027 |
Token | stranger |
Token ID | 16195 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
forgot | +0.017 |
waited | +0.015 |
stayed | +0.015 |
remembered | +0.015 |
dug | +0.014 |
Neg logit contributions | |
Today | -0.021 |
Nice | -0.018 |
This | -0.018 |
These | -0.017 |
Of | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +6.09e-02 |
Pos logit contributions | |
Today | +0.068 |
This | +0.056 |
Nice | +0.056 |
These | +0.050 |
Of | +0.047 |
Neg logit contributions | |
forgot | -0.078 |
waited | -0.070 |
stayed | -0.069 |
remembered | -0.069 |
dug | -0.067 |
Token | Str |
Token ID | 4285 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
Today | +0.080 |
uttering | +0.067 |
Nice | +0.063 |
ummy | +0.053 |
oky | +0.053 |
Neg logit contributions | |
forgot | -0.155 |
waited | -0.149 |
stayed | -0.146 |
put | -0.146 |
never | -0.143 |
Token | angers |
Token ID | 6606 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
Today | +0.193 |
Nice | +0.169 |
This | +0.155 |
Of | +0.138 |
These | +0.130 |
Neg logit contributions | |
forgot | -0.232 |
waited | -0.209 |
stayed | -0.203 |
remembered | -0.201 |
hid | -0.199 |
Token | can |
Token ID | 460 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
Today | +0.038 |
This | +0.034 |
Nice | +0.032 |
These | +0.031 |
ummy | +0.028 |
Neg logit contributions | |
forgot | -0.032 |
remembered | -0.029 |
waited | -0.028 |
dug | -0.027 |
stayed | -0.027 |
Token | be |
Token ID | 307 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
forgot | +0.024 |
remembered | +0.021 |
managed | +0.021 |
waited | +0.020 |
stayed | +0.019 |
Neg logit contributions | |
Today | -0.035 |
This | -0.031 |
Nice | -0.030 |
These | -0.029 |
ummy | -0.027 |
Token | bad |
Token ID | 2089 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
forgot | +0.051 |
waited | +0.046 |
stayed | +0.044 |
remembered | +0.043 |
managed | +0.043 |
Neg logit contributions | |
Today | -0.051 |
This | -0.044 |
Nice | -0.042 |
These | -0.037 |
oky | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | +8.13e-03 |
Pos logit contributions | |
Today | +0.063 |
Nice | +0.052 |
This | +0.051 |
These | +0.047 |
Of | +0.044 |
Neg logit contributions | |
forgot | -0.067 |
waited | -0.060 |
stayed | -0.060 |
remembered | -0.059 |
put | -0.057 |
Token | excited |
Token ID | 6568 |
Feature activation | +1.14e-03 |
Pos logit contributions | |
forgot | +0.106 |
waited | +0.093 |
stayed | +0.092 |
remembered | +0.092 |
dug | +0.091 |
Neg logit contributions | |
Today | -0.104 |
This | -0.086 |
Nice | -0.083 |
These | -0.073 |
Right | -0.072 |
Token | . |
Token ID | 13 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
Today | +0.002 |
This | +0.002 |
Nice | +0.002 |
ummy | +0.002 |
These | +0.002 |
Neg logit contributions | |
forgot | -0.003 |
remembered | -0.002 |
waited | -0.002 |
stayed | -0.002 |
managed | -0.002 |
Token | She |
Token ID | 1375 |
Feature activation | -9.19e-02 |
Pos logit contributions | |
Today | +0.072 |
Nice | +0.062 |
opl | +0.059 |
anes | +0.057 |
uttering | +0.054 |
Neg logit contributions | |
forgot | -0.147 |
waited | -0.140 |
put | -0.137 |
tried | -0.134 |
stayed | -0.134 |
Token | loves |
Token ID | 10408 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
ts | +0.148 |
ode | +0.119 |
ils | +0.113 |
plank | +0.111 |
ptions | +0.104 |
Neg logit contributions | |
Today | -0.198 |
On | -0.174 |
This | -0.169 |
She | -0.165 |
Nice | -0.163 |
Token | getting |
Token ID | 1972 |
Feature activation | +9.48e-03 |
Pos logit contributions | |
Today | +0.024 |
This | +0.020 |
Nice | +0.020 |
Of | +0.018 |
These | +0.018 |
Neg logit contributions | |
forgot | -0.025 |
remembered | -0.022 |
dug | -0.021 |
managed | -0.021 |
stayed | -0.021 |
Token | hairc |
Token ID | 37363 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
Today | +0.022 |
This | +0.019 |
Nice | +0.018 |
These | +0.017 |
Of | +0.016 |
Neg logit contributions | |
forgot | -0.019 |
remembered | -0.016 |
waited | -0.016 |
stayed | -0.016 |
dug | -0.015 |
Token | uts |
Token ID | 5500 |
Feature activation | +3.95e-02 |
Pos logit contributions | |
Today | +0.151 |
Nice | +0.121 |
This | +0.106 |
These | +0.094 |
Of | +0.090 |
Neg logit contributions | |
forgot | -0.289 |
waited | -0.261 |
stayed | -0.259 |
put | -0.254 |
never | -0.252 |
Token | . |
Token ID | 13 |
Feature activation | +5.96e-02 |
Pos logit contributions | |
Today | +0.090 |
Nice | +0.076 |
This | +0.075 |
These | +0.069 |
Of | +0.065 |
Neg logit contributions | |
forgot | -0.079 |
waited | -0.070 |
stayed | -0.070 |
remembered | -0.069 |
put | -0.067 |
Token | Her |
Token ID | 2332 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
Today | +0.081 |
Nice | +0.075 |
anes | +0.071 |
uttering | +0.068 |
opl | +0.066 |
Neg logit contributions | |
forgot | -0.143 |
waited | -0.138 |
put | -0.135 |
tried | -0.131 |
stayed | -0.131 |
Token | mom |
Token ID | 1995 |
Feature activation | -5.74e-02 |
Pos logit contributions | |
forgot | +0.058 |
waited | +0.050 |
managed | +0.050 |
remembered | +0.050 |
stayed | +0.050 |
Neg logit contributions | |
Today | -0.073 |
Nice | -0.060 |
This | -0.060 |
ummy | -0.055 |
These | -0.054 |
Token | was |
Token ID | 373 |
Feature activation | -4.87e-02 |
Pos logit contributions | |
ts | +0.087 |
plank | +0.073 |
forgot | +0.070 |
dug | +0.067 |
ils | +0.065 |
Neg logit contributions | |
Today | -0.118 |
This | -0.102 |
She | -0.100 |
Of | -0.099 |
ay | -0.099 |
Token | thinks |
Token ID | 6834 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
forgot | +0.143 |
stayed | +0.123 |
waited | +0.123 |
ts | +0.120 |
remembered | +0.119 |
Neg logit contributions | |
Today | -0.194 |
This | -0.165 |
Nice | -0.157 |
These | -0.146 |
Of | -0.140 |
Token | for |
Token ID | 329 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
forgot | +0.068 |
remembered | +0.062 |
waited | +0.062 |
punished | +0.061 |
managed | +0.059 |
Neg logit contributions | |
Today | -0.063 |
This | -0.053 |
Nice | -0.053 |
These | -0.046 |
ummy | -0.043 |
Token | a |
Token ID | 257 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
forgot | +0.076 |
remembered | +0.065 |
managed | +0.065 |
stayed | +0.063 |
waited | +0.062 |
Neg logit contributions | |
Today | -0.063 |
This | -0.057 |
Nice | -0.054 |
These | -0.047 |
Of | -0.046 |
Token | moment |
Token ID | 2589 |
Feature activation | +5.77e-03 |
Pos logit contributions | |
forgot | +0.083 |
waited | +0.074 |
stayed | +0.073 |
remembered | +0.073 |
put | +0.072 |
Neg logit contributions | |
Today | -0.077 |
Nice | -0.065 |
This | -0.064 |
These | -0.059 |
anes | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
Today | +0.013 |
Nice | +0.011 |
This | +0.011 |
These | +0.010 |
Of | +0.010 |
Neg logit contributions | |
forgot | -0.012 |
waited | -0.010 |
stayed | -0.010 |
remembered | -0.010 |
put | -0.010 |
Token | He |
Token ID | 679 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
uttering | +0.040 |
Today | +0.038 |
andel | +0.037 |
owers | +0.037 |
anes | +0.036 |
Neg logit contributions | |
forgot | -0.065 |
put | -0.063 |
waited | -0.061 |
tried | -0.061 |
remembered | -0.061 |
Token | likes |
Token ID | 7832 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
forgot | +0.212 |
ts | +0.195 |
stayed | +0.189 |
managed | +0.185 |
punished | +0.184 |
Neg logit contributions | |
Today | -0.264 |
This | -0.208 |
Nice | -0.203 |
On | -0.194 |
Right | -0.184 |
Token | his |
Token ID | 465 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
forgot | +0.035 |
waited | +0.031 |
remembered | +0.031 |
stayed | +0.031 |
managed | +0.030 |
Neg logit contributions | |
Today | -0.036 |
Nice | -0.031 |
This | -0.031 |
These | -0.028 |
Of | -0.027 |
Token | sun |
Token ID | 4252 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
forgot | +0.075 |
waited | +0.066 |
stayed | +0.066 |
remembered | +0.065 |
put | +0.064 |
Neg logit contributions | |
Today | -0.102 |
Nice | -0.088 |
This | -0.087 |
These | -0.082 |
Of | -0.077 |
Token | flower |
Token ID | 25547 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
Today | +0.049 |
Nice | +0.042 |
This | +0.041 |
These | +0.038 |
Of | +0.036 |
Neg logit contributions | |
forgot | -0.045 |
stayed | -0.041 |
waited | -0.041 |
remembered | -0.040 |
put | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | +1.33e-03 |
Pos logit contributions | |
Today | +0.044 |
Nice | +0.036 |
This | +0.036 |
These | +0.032 |
Of | +0.031 |
Neg logit contributions | |
forgot | -0.047 |
waited | -0.042 |
stayed | -0.042 |
remembered | -0.041 |
put | -0.040 |
Token | felt |
Token ID | 2936 |
Feature activation | -4.16e-02 |
Pos logit contributions | |
forgot | +0.093 |
waited | +0.083 |
managed | +0.081 |
stayed | +0.081 |
remembered | +0.080 |
Neg logit contributions | |
Today | -0.101 |
Nice | -0.088 |
This | -0.087 |
Of | -0.076 |
These | -0.076 |
Token | sorry |
Token ID | 7926 |
Feature activation | -8.19e-03 |
Pos logit contributions | |
forgot | +0.088 |
waited | +0.079 |
stayed | +0.078 |
remembered | +0.078 |
put | +0.075 |
Neg logit contributions | |
Today | -0.089 |
Nice | -0.075 |
This | -0.074 |
These | -0.067 |
Of | -0.064 |
Token | for |
Token ID | 329 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
forgot | +0.017 |
stayed | +0.015 |
waited | +0.015 |
remembered | +0.015 |
put | +0.015 |
Neg logit contributions | |
Today | -0.018 |
Nice | -0.015 |
This | -0.015 |
These | -0.014 |
anes | -0.014 |
Token | them |
Token ID | 606 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
forgot | +0.028 |
waited | +0.025 |
remembered | +0.025 |
stayed | +0.024 |
managed | +0.024 |
Neg logit contributions | |
Today | -0.029 |
Nice | -0.025 |
This | -0.024 |
These | -0.022 |
Of | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
forgot | +0.065 |
waited | +0.060 |
remembered | +0.059 |
stayed | +0.058 |
managed | +0.057 |
Neg logit contributions | |
Today | -0.046 |
Nice | -0.036 |
This | -0.036 |
These | -0.031 |
ummy | -0.030 |
Token | He |
Token ID | 679 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
andel | +0.057 |
uttering | +0.054 |
umm | +0.053 |
Today | +0.051 |
ay | +0.050 |
Neg logit contributions | |
forgot | -0.060 |
never | -0.058 |
waited | -0.057 |
hoped | -0.057 |
tried | -0.056 |
Token | decided |
Token ID | 3066 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
ts | +0.195 |
ode | +0.188 |
ils | +0.172 |
ptions | +0.171 |
plank | +0.168 |
Neg logit contributions | |
He | -0.195 |
She | -0.179 |
The | -0.178 |
| -0.175 |
A | -0.168 |
Token | to |
Token ID | 284 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
forgot | +0.051 |
waited | +0.046 |
remembered | +0.046 |
stayed | +0.045 |
dug | +0.045 |
Neg logit contributions | |
Today | -0.035 |
This | -0.030 |
Nice | -0.029 |
These | -0.024 |
Of | -0.024 |
Token | be |
Token ID | 307 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
forgot | +0.101 |
remembered | +0.095 |
ts | +0.089 |
managed | +0.088 |
imagined | +0.087 |
Neg logit contributions | |
Today | -0.120 |
This | -0.111 |
Everyone | -0.095 |
These | -0.091 |
On | -0.090 |
Token | generous |
Token ID | 14431 |
Feature activation | +9.12e-03 |
Pos logit contributions | |
forgot | +0.084 |
waited | +0.072 |
stayed | +0.068 |
dug | +0.066 |
hid | +0.066 |
Neg logit contributions | |
Today | -0.094 |
This | -0.082 |
Nice | -0.079 |
Right | -0.072 |
Of | -0.071 |
Token | and |
Token ID | 290 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
Today | +0.017 |
Nice | +0.014 |
This | +0.014 |
ummy | +0.013 |
These | +0.012 |
Neg logit contributions | |
forgot | -0.021 |
waited | -0.019 |
stayed | -0.019 |
remembered | -0.018 |
managed | -0.018 |
Token | it |
Token ID | 340 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
forgot | +0.026 |
waited | +0.023 |
remembered | +0.022 |
stayed | +0.022 |
managed | +0.022 |
Neg logit contributions | |
Today | -0.030 |
Nice | -0.026 |
This | -0.026 |
These | -0.023 |
Of | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
forgot | +0.049 |
waited | +0.044 |
stayed | +0.043 |
remembered | +0.043 |
put | +0.042 |
Neg logit contributions | |
Today | -0.044 |
Nice | -0.036 |
This | -0.036 |
These | -0.032 |
ummy | -0.030 |
Token | Ben |
Token ID | 3932 |
Feature activation | -6.88e-02 |
Pos logit contributions | |
forgot | +0.035 |
waited | +0.033 |
managed | +0.031 |
stayed | +0.031 |
dug | +0.031 |
Neg logit contributions | |
Today | -0.051 |
This | -0.046 |
Nice | -0.044 |
These | -0.039 |
She | -0.039 |
Token | sighed |
Token ID | 21893 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
forgot | +0.072 |
ts | +0.070 |
waited | +0.064 |
dug | +0.062 |
stayed | +0.060 |
Neg logit contributions | |
Today | -0.188 |
This | -0.165 |
Nice | -0.158 |
These | -0.149 |
She | -0.148 |
Token | . |
Token ID | 13 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
forgot | +0.022 |
stayed | +0.020 |
remembered | +0.020 |
waited | +0.020 |
put | +0.020 |
Neg logit contributions | |
Today | -0.023 |
Nice | -0.020 |
This | -0.019 |
These | -0.018 |
anes | -0.018 |
Token | He |
Token ID | 679 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
Today | +0.041 |
uttering | +0.039 |
owers | +0.038 |
anes | +0.036 |
andel | +0.036 |
Neg logit contributions | |
forgot | -0.065 |
remembered | -0.059 |
waited | -0.058 |
tried | -0.058 |
put | -0.058 |
Token | wanted |
Token ID | 2227 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
ts | +0.169 |
ode | +0.161 |
plank | +0.146 |
ils | +0.138 |
permission | +0.129 |
Neg logit contributions | |
Today | -0.235 |
He | -0.219 |
On | -0.208 |
Nice | -0.206 |
This | -0.206 |
Token | to |
Token ID | 284 |
Feature activation | -5.46e-02 |
Pos logit contributions | |
forgot | +0.092 |
remembered | +0.081 |
waited | +0.080 |
managed | +0.079 |
stayed | +0.079 |
Neg logit contributions | |
Today | -0.055 |
This | -0.050 |
Nice | -0.047 |
Of | -0.040 |
These | -0.040 |
Token | fix |
Token ID | 4259 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
forgot | +0.092 |
remembered | +0.084 |
waited | +0.082 |
managed | +0.079 |
ts | +0.079 |
Neg logit contributions | |
Today | -0.132 |
This | -0.118 |
Nice | -0.108 |
Everyone | -0.100 |
These | -0.100 |
Token | it |
Token ID | 340 |
Feature activation | -9.47e-03 |
Pos logit contributions | |
Today | +0.038 |
This | +0.033 |
Nice | +0.033 |
These | +0.030 |
Of | +0.028 |
Neg logit contributions | |
forgot | -0.033 |
waited | -0.029 |
stayed | -0.029 |
remembered | -0.029 |
managed | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | +5.88e-03 |
Pos logit contributions | |
forgot | +0.021 |
waited | +0.019 |
stayed | +0.019 |
remembered | +0.019 |
put | +0.018 |
Neg logit contributions | |
Today | -0.019 |
Nice | -0.016 |
This | -0.016 |
These | -0.014 |
Of | -0.014 |
Token | thinks |
Token ID | 6834 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
forgot | +0.132 |
stayed | +0.111 |
ts | +0.107 |
waited | +0.107 |
managed | +0.107 |
Neg logit contributions | |
Today | -0.237 |
This | -0.203 |
Nice | -0.199 |
Of | -0.181 |
These | -0.180 |
Token | for |
Token ID | 329 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
forgot | +0.033 |
waited | +0.030 |
stayed | +0.030 |
remembered | +0.030 |
put | +0.029 |
Neg logit contributions | |
Today | -0.030 |
Nice | -0.025 |
This | -0.025 |
These | -0.022 |
Of | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
forgot | +0.077 |
stayed | +0.066 |
remembered | +0.066 |
waited | +0.065 |
managed | +0.065 |
Neg logit contributions | |
Today | -0.063 |
This | -0.053 |
Nice | -0.052 |
These | -0.044 |
Of | -0.043 |
Token | moment |
Token ID | 2589 |
Feature activation | +1.59e-04 |
Pos logit contributions | |
forgot | +0.056 |
waited | +0.050 |
remembered | +0.050 |
stayed | +0.050 |
put | +0.049 |
Neg logit contributions | |
Today | -0.041 |
This | -0.034 |
Nice | -0.033 |
These | -0.030 |
anes | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
Today | +0.000 |
Nice | +0.000 |
This | +0.000 |
These | +0.000 |
Of | +0.000 |
Neg logit contributions | |
forgot | -0.000 |
waited | -0.000 |
stayed | -0.000 |
remembered | -0.000 |
put | -0.000 |
Token | He |
Token ID | 679 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
Today | +0.049 |
uttering | +0.048 |
owers | +0.047 |
opl | +0.047 |
anes | +0.046 |
Neg logit contributions | |
forgot | -0.070 |
put | -0.067 |
remembered | -0.067 |
tried | -0.066 |
let | -0.066 |
Token | says |
Token ID | 1139 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
forgot | +0.212 |
ts | +0.186 |
stayed | +0.185 |
punished | +0.184 |
waited | +0.181 |
Neg logit contributions | |
Today | -0.277 |
Nice | -0.222 |
This | -0.221 |
On | -0.203 |
Right | -0.198 |
Token | , |
Token ID | 11 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
forgot | +0.048 |
waited | +0.043 |
stayed | +0.043 |
remembered | +0.043 |
put | +0.042 |
Neg logit contributions | |
Today | -0.047 |
Nice | -0.039 |
This | -0.039 |
These | -0.035 |
ummy | -0.033 |
Token | " |
Token ID | 366 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
forgot | +0.038 |
remembered | +0.037 |
put | +0.037 |
waited | +0.037 |
stayed | +0.036 |
Neg logit contributions | |
Today | -0.035 |
oky | -0.030 |
elly | -0.030 |
umm | -0.030 |
ummy | -0.029 |
Token | His |
Token ID | 6653 |
Feature activation | -5.07e-02 |
Pos logit contributions | |
forgot | +0.021 |
waited | +0.019 |
stayed | +0.018 |
remembered | +0.018 |
listened | +0.018 |
Neg logit contributions | |
Today | -0.025 |
Nice | -0.021 |
ummy | -0.021 |
This | -0.021 |
These | -0.021 |
Token | name |
Token ID | 1438 |
Feature activation | -8.30e-03 |
Pos logit contributions | |
forgot | +0.127 |
stayed | +0.116 |
waited | +0.116 |
remembered | +0.116 |
put | +0.116 |
Neg logit contributions | |
Today | -0.085 |
Nice | -0.068 |
This | -0.067 |
These | -0.062 |
anes | -0.059 |
Token | Ow |
Token ID | 11960 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
Today | +0.040 |
Nice | +0.032 |
This | +0.029 |
These | +0.027 |
uttering | +0.027 |
Neg logit contributions | |
forgot | -0.061 |
waited | -0.057 |
stayed | -0.057 |
remembered | -0.056 |
put | -0.056 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
forgot | +0.029 |
waited | +0.026 |
stayed | +0.026 |
remembered | +0.025 |
put | +0.025 |
Neg logit contributions | |
Today | -0.029 |
Nice | -0.024 |
This | -0.024 |
These | -0.022 |
ummy | -0.021 |
Token | Tom |
Token ID | 4186 |
Feature activation | -9.96e-02 |
Pos logit contributions | |
Today | +0.036 |
Nice | +0.030 |
This | +0.028 |
These | +0.027 |
anes | +0.026 |
Neg logit contributions | |
forgot | -0.040 |
waited | -0.037 |
remembered | -0.036 |
stayed | -0.036 |
put | -0.035 |
Token | cried |
Token ID | 16896 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
forgot | +0.151 |
ts | +0.140 |
stayed | +0.134 |
waited | +0.127 |
managed | +0.126 |
Neg logit contributions | |
Today | -0.256 |
This | -0.223 |
Nice | -0.218 |
She | -0.195 |
On | -0.194 |
Token | . |
Token ID | 13 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
forgot | +0.052 |
stayed | +0.048 |
put | +0.048 |
remembered | +0.048 |
waited | +0.047 |
Neg logit contributions | |
Today | -0.054 |
Nice | -0.046 |
This | -0.045 |
These | -0.044 |
anes | -0.041 |
Token | He |
Token ID | 679 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
Today | +0.059 |
uttering | +0.054 |
owers | +0.049 |
ummy | +0.049 |
umm | +0.049 |
Neg logit contributions | |
forgot | -0.080 |
waited | -0.078 |
tried | -0.077 |
never | -0.076 |
put | -0.076 |
Token | dropped |
Token ID | 5710 |
Feature activation | -9.18e-03 |
Pos logit contributions | |
ode | +0.168 |
ptions | +0.159 |
ts | +0.159 |
least | +0.155 |
ils | +0.147 |
Neg logit contributions | |
He | -0.223 |
Today | -0.218 |
She | -0.208 |
Nice | -0.206 |
This | -0.200 |
Token | the |
Token ID | 262 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
forgot | +0.018 |
waited | +0.015 |
stayed | +0.015 |
remembered | +0.015 |
put | +0.015 |
Neg logit contributions | |
Today | -0.022 |
Nice | -0.019 |
This | -0.019 |
These | -0.017 |
Of | -0.016 |
Token | ball |
Token ID | 2613 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
forgot | +0.035 |
waited | +0.031 |
stayed | +0.030 |
remembered | +0.030 |
put | +0.029 |
Neg logit contributions | |
Today | -0.051 |
Nice | -0.044 |
This | -0.044 |
These | -0.041 |
ummy | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
Today | +0.061 |
Nice | +0.052 |
This | +0.051 |
These | +0.048 |
Of | +0.047 |
Neg logit contributions | |
forgot | -0.053 |
stayed | -0.048 |
waited | -0.048 |
put | -0.046 |
remembered | -0.046 |
Token | held |
Token ID | 2714 |
Feature activation | -4.70e-03 |
Pos logit contributions | |
ode | +0.048 |
forgot | +0.047 |
ils | +0.046 |
ppy | +0.043 |
ppa | +0.043 |
Neg logit contributions | |
Today | -0.054 |
Nice | -0.053 |
This | -0.053 |
The | -0.051 |
He | -0.049 |
Token |
|
Token ID | 198 |
Feature activation | -3.40e-03 |
Pos logit contributions | |
forgot | +0.014 |
stayed | +0.013 |
put | +0.013 |
waited | +0.012 |
never | +0.012 |
Neg logit contributions | |
Today | -0.014 |
Nice | -0.012 |
This | -0.011 |
anes | -0.011 |
These | -0.011 |
Token | Tim |
Token ID | 14967 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
forgot | +0.008 |
never | +0.007 |
waited | +0.007 |
remembered | +0.007 |
stayed | +0.007 |
Neg logit contributions | |
Today | -0.006 |
Nice | -0.005 |
This | -0.005 |
ummy | -0.005 |
These | -0.005 |
Token | hugged |
Token ID | 41130 |
Feature activation | +1.17e-03 |
Pos logit contributions | |
ts | +0.194 |
forgot | +0.181 |
stayed | +0.160 |
waited | +0.159 |
ils | +0.155 |
Neg logit contributions | |
Today | -0.211 |
This | -0.165 |
Nice | -0.155 |
The | -0.150 |
He | -0.149 |
Token | Kim |
Token ID | 6502 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
Today | +0.003 |
Nice | +0.002 |
This | +0.002 |
These | +0.002 |
Of | +0.002 |
Neg logit contributions | |
forgot | -0.002 |
waited | -0.002 |
remembered | -0.002 |
stayed | -0.002 |
managed | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
forgot | +0.052 |
waited | +0.045 |
stayed | +0.045 |
remembered | +0.045 |
put | +0.043 |
Neg logit contributions | |
Today | -0.077 |
Nice | -0.067 |
This | -0.066 |
These | -0.062 |
Of | -0.059 |
Token | He |
Token ID | 679 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
uttering | +0.058 |
Today | +0.057 |
owers | +0.056 |
oky | +0.052 |
elly | +0.051 |
Neg logit contributions | |
forgot | -0.087 |
put | -0.087 |
stayed | -0.082 |
remembered | -0.082 |
let | -0.082 |
Token | was |
Token ID | 373 |
Feature activation | -6.27e-02 |
Pos logit contributions | |
ode | +0.204 |
ptions | +0.202 |
ts | +0.199 |
plank | +0.187 |
ils | +0.182 |
Neg logit contributions | |
He | -0.180 |
| -0.176 |
The | -0.171 |
Today | -0.168 |
She | -0.163 |
Token | proud |
Token ID | 6613 |
Feature activation | +6.43e-03 |
Pos logit contributions | |
forgot | +0.151 |
waited | +0.137 |
stayed | +0.132 |
remembered | +0.131 |
managed | +0.130 |
Neg logit contributions | |
Today | -0.108 |
This | -0.088 |
Nice | -0.087 |
These | -0.071 |
Right | -0.070 |
Token | of |
Token ID | 286 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
Today | +0.011 |
Nice | +0.009 |
This | +0.008 |
These | +0.007 |
ummy | +0.007 |
Neg logit contributions | |
forgot | -0.017 |
waited | -0.015 |
stayed | -0.015 |
remembered | -0.015 |
managed | -0.015 |
Token | her |
Token ID | 607 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
Today | +0.032 |
Nice | +0.027 |
This | +0.027 |
These | +0.025 |
Of | +0.024 |
Neg logit contributions | |
forgot | -0.024 |
waited | -0.022 |
stayed | -0.021 |
remembered | -0.021 |
put | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
forgot | +0.030 |
waited | +0.027 |
stayed | +0.027 |
put | +0.027 |
remembered | +0.027 |
Neg logit contributions | |
Today | -0.026 |
Nice | -0.022 |
This | -0.022 |
These | -0.020 |
anes | -0.019 |
Token | it |
Token ID | 340 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
forgot | +0.087 |
stayed | +0.076 |
remembered | +0.075 |
waited | +0.075 |
managed | +0.071 |
Neg logit contributions | |
Today | -0.116 |
This | -0.101 |
Nice | -0.097 |
These | -0.091 |
Of | -0.086 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
forgot | +0.064 |
waited | +0.057 |
stayed | +0.056 |
remembered | +0.056 |
put | +0.054 |
Neg logit contributions | |
Today | -0.067 |
Nice | -0.056 |
This | -0.055 |
These | -0.050 |
Of | -0.048 |
Token | Tom |
Token ID | 4186 |
Feature activation | -9.12e-02 |
Pos logit contributions | |
Today | +0.053 |
Nice | +0.047 |
This | +0.044 |
These | +0.042 |
oky | +0.041 |
Neg logit contributions | |
forgot | -0.039 |
waited | -0.035 |
put | -0.034 |
stayed | -0.033 |
remembered | -0.033 |
Token | cheers |
Token ID | 34550 |
Feature activation | +5.32e-03 |
Pos logit contributions | |
forgot | +0.130 |
ts | +0.121 |
stayed | +0.117 |
managed | +0.111 |
never | +0.109 |
Neg logit contributions | |
Today | -0.240 |
This | -0.209 |
Nice | -0.198 |
On | -0.185 |
These | -0.182 |
Token | . |
Token ID | 13 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
Today | +0.011 |
Nice | +0.009 |
This | +0.009 |
These | +0.008 |
oky | +0.008 |
Neg logit contributions | |
forgot | -0.012 |
waited | -0.011 |
stayed | -0.010 |
remembered | -0.010 |
put | -0.010 |
Token | He |
Token ID | 679 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
Today | +0.065 |
owers | +0.063 |
uttering | +0.062 |
opl | +0.058 |
ummy | +0.056 |
Neg logit contributions | |
forgot | -0.085 |
put | -0.085 |
waited | -0.082 |
tried | -0.081 |
let | -0.080 |
Token | runs |
Token ID | 4539 |
Feature activation | -3.90e-03 |
Pos logit contributions | |
ppa | +0.194 |
forgot | +0.189 |
ts | +0.178 |
ode | +0.178 |
punished | +0.176 |
Neg logit contributions | |
Today | -0.225 |
This | -0.196 |
Nice | -0.196 |
Up | -0.178 |
On | -0.176 |
Token | to |
Token ID | 284 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
forgot | +0.008 |
waited | +0.007 |
stayed | +0.007 |
remembered | +0.007 |
put | +0.007 |
Neg logit contributions | |
Today | -0.008 |
Nice | -0.007 |
This | -0.007 |
These | -0.006 |
Of | -0.006 |
Token | help |
Token ID | 1037 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
forgot | +0.027 |
remembered | +0.024 |
stayed | +0.024 |
managed | +0.023 |
waited | +0.023 |
Neg logit contributions | |
Today | -0.026 |
This | -0.022 |
Nice | -0.021 |
Of | -0.019 |
These | -0.018 |
Token | her |
Token ID | 607 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
Today | +0.024 |
Nice | +0.020 |
This | +0.020 |
These | +0.018 |
Of | +0.017 |
Neg logit contributions | |
forgot | -0.023 |
waited | -0.020 |
remembered | -0.020 |
stayed | -0.020 |
managed | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +4.94e-02 |
Pos logit contributions | |
forgot | +0.076 |
waited | +0.069 |
stayed | +0.069 |
remembered | +0.068 |
managed | +0.066 |
Neg logit contributions | |
Today | -0.059 |
Nice | -0.048 |
This | -0.048 |
These | -0.042 |
Of | -0.040 |
Token | sound |
Token ID | 2128 |
Feature activation | +4.16e-03 |
Pos logit contributions | |
forgot | +0.024 |
remembered | +0.021 |
waited | +0.021 |
stayed | +0.021 |
put | +0.020 |
Neg logit contributions | |
Today | -0.026 |
This | -0.022 |
Nice | -0.022 |
These | -0.020 |
anes | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
Today | +0.008 |
Nice | +0.007 |
This | +0.007 |
These | +0.006 |
Of | +0.006 |
Neg logit contributions | |
forgot | -0.010 |
waited | -0.009 |
stayed | -0.009 |
remembered | -0.009 |
put | -0.008 |
Token | Tom |
Token ID | 4186 |
Feature activation | -9.54e-02 |
Pos logit contributions | |
Today | +0.038 |
uttering | +0.036 |
umm | +0.034 |
Nice | +0.033 |
ummy | +0.033 |
Neg logit contributions | |
forgot | -0.062 |
put | -0.060 |
waited | -0.059 |
tried | -0.058 |
remembered | -0.057 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
forgot | +0.190 |
managed | +0.173 |
ts | +0.173 |
stayed | +0.171 |
remembered | +0.167 |
Neg logit contributions | |
Today | -0.179 |
This | -0.148 |
Nice | -0.136 |
She | -0.128 |
On | -0.126 |
Token | . |
Token ID | 13 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
forgot | +0.029 |
remembered | +0.027 |
put | +0.027 |
stayed | +0.026 |
waited | +0.026 |
Neg logit contributions | |
Today | -0.044 |
These | -0.040 |
This | -0.039 |
Nice | -0.038 |
anes | -0.036 |
Token | He |
Token ID | 679 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
uttering | +0.068 |
owers | +0.064 |
umm | +0.061 |
andel | +0.060 |
Today | +0.059 |
Neg logit contributions | |
forgot | -0.074 |
put | -0.073 |
waited | -0.072 |
tried | -0.071 |
did | -0.071 |
Token | opened |
Token ID | 4721 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
ts | +0.191 |
ode | +0.186 |
punished | +0.170 |
ils | +0.167 |
wed | +0.165 |
Neg logit contributions | |
Today | -0.204 |
Nice | -0.197 |
The | -0.195 |
| -0.195 |
He | -0.192 |
Token | the |
Token ID | 262 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
forgot | +0.046 |
waited | +0.041 |
stayed | +0.040 |
remembered | +0.040 |
put | +0.039 |
Neg logit contributions | |
Today | -0.064 |
Nice | -0.056 |
This | -0.055 |
These | -0.051 |
Of | -0.049 |
Token | door |
Token ID | 3420 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
forgot | +0.042 |
waited | +0.036 |
stayed | +0.036 |
remembered | +0.035 |
managed | +0.034 |
Neg logit contributions | |
Today | -0.062 |
Nice | -0.054 |
This | -0.053 |
These | -0.049 |
Of | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | -3.59e-02 |
Pos logit contributions | |
Today | +0.026 |
Nice | +0.023 |
This | +0.022 |
These | +0.021 |
Of | +0.020 |
Neg logit contributions | |
forgot | -0.020 |
waited | -0.018 |
put | -0.018 |
stayed | -0.018 |
remembered | -0.017 |
Token | got |
Token ID | 1392 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
forgot | +0.044 |
ode | +0.038 |
punished | +0.038 |
never | +0.038 |
ts | +0.037 |
Neg logit contributions | |
Today | -0.083 |
This | -0.079 |
Of | -0.076 |
Nice | -0.076 |
The | -0.074 |
Token | Sara |
Token ID | 24799 |
Feature activation | -7.51e-02 |
Pos logit contributions | |
forgot | +0.039 |
remembered | +0.033 |
stayed | +0.033 |
managed | +0.032 |
punished | +0.032 |
Neg logit contributions | |
Today | -0.062 |
This | -0.055 |
Nice | -0.052 |
These | -0.050 |
Of | -0.049 |
Token | and |
Token ID | 290 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
forgot | +0.084 |
stayed | +0.068 |
ts | +0.068 |
punished | +0.067 |
remembered | +0.065 |
Neg logit contributions | |
Today | -0.201 |
This | -0.184 |
These | -0.168 |
Nice | -0.165 |
She | -0.160 |
Token | Ben |
Token ID | 3932 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
forgot | +0.069 |
waited | +0.062 |
stayed | +0.061 |
managed | +0.061 |
dug | +0.060 |
Neg logit contributions | |
Today | -0.062 |
This | -0.053 |
Nice | -0.051 |
These | -0.046 |
Of | -0.045 |
Token | crying |
Token ID | 13774 |
Feature activation | -2.14e-03 |
Pos logit contributions | |
forgot | +0.081 |
remembered | +0.066 |
waited | +0.066 |
ts | +0.065 |
stayed | +0.065 |
Neg logit contributions | |
Today | -0.171 |
This | -0.151 |
Nice | -0.145 |
These | -0.140 |
Of | -0.130 |
Token | . |
Token ID | 13 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
forgot | +0.005 |
waited | +0.005 |
stayed | +0.005 |
remembered | +0.005 |
put | +0.005 |
Neg logit contributions | |
Today | -0.004 |
Nice | -0.003 |
This | -0.003 |
These | -0.003 |
Of | -0.003 |
Token | She |
Token ID | 1375 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
Today | +0.056 |
umm | +0.054 |
ay | +0.052 |
Nice | +0.052 |
uttering | +0.052 |
Neg logit contributions | |
forgot | -0.073 |
waited | -0.070 |
put | -0.069 |
never | -0.068 |
tried | -0.068 |
Token | was |
Token ID | 373 |
Feature activation | -6.33e-02 |
Pos logit contributions | |
managed | +0.195 |
ts | +0.190 |
forgot | +0.186 |
ode | +0.185 |
stayed | +0.170 |
Neg logit contributions | |
Today | -0.236 |
She | -0.201 |
This | -0.196 |
On | -0.187 |
The | -0.177 |
Token | angry |
Token ID | 7954 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
forgot | +0.147 |
waited | +0.127 |
managed | +0.127 |
remembered | +0.126 |
imagined | +0.125 |
Neg logit contributions | |
Today | -0.103 |
This | -0.092 |
Nice | -0.084 |
Right | -0.074 |
These | -0.074 |
Token | and |
Token ID | 290 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
Today | +0.064 |
Nice | +0.056 |
This | +0.055 |
These | +0.052 |
Of | +0.050 |
Neg logit contributions | |
forgot | -0.039 |
waited | -0.033 |
stayed | -0.033 |
remembered | -0.033 |
put | -0.033 |
Token | sad |
Token ID | 6507 |
Feature activation | +5.21e-03 |
Pos logit contributions | |
forgot | +0.053 |
waited | +0.048 |
stayed | +0.048 |
remembered | +0.047 |
managed | +0.046 |
Neg logit contributions | |
Today | -0.055 |
This | -0.048 |
Nice | -0.047 |
These | -0.042 |
Of | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
Today | +0.010 |
Nice | +0.009 |
This | +0.008 |
These | +0.008 |
Of | +0.007 |
Neg logit contributions | |
forgot | -0.012 |
waited | -0.011 |
stayed | -0.011 |
remembered | -0.011 |
put | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -4.69e-02 |
Pos logit contributions | |
forgot | +0.009 |
waited | +0.008 |
stayed | +0.007 |
hid | +0.007 |
managed | +0.007 |
Neg logit contributions | |
Today | -0.007 |
This | -0.006 |
Nice | -0.006 |
These | -0.006 |
Of | -0.005 |
Token | hugged |
Token ID | 41130 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
forgot | +0.072 |
waited | +0.061 |
remembered | +0.061 |
managed | +0.060 |
stayed | +0.060 |
Neg logit contributions | |
Today | -0.116 |
This | -0.102 |
Nice | -0.101 |
Of | -0.091 |
These | -0.090 |
Token | his |
Token ID | 465 |
Feature activation | -4.34e-02 |
Pos logit contributions | |
Today | +0.033 |
Nice | +0.028 |
This | +0.028 |
These | +0.026 |
Of | +0.025 |
Neg logit contributions | |
forgot | -0.027 |
waited | -0.024 |
stayed | -0.024 |
remembered | -0.024 |
put | -0.023 |
Token | daddy |
Token ID | 35822 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
forgot | +0.072 |
waited | +0.062 |
stayed | +0.061 |
remembered | +0.061 |
put | +0.059 |
Neg logit contributions | |
Today | -0.114 |
Nice | -0.099 |
This | -0.099 |
These | -0.092 |
Of | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
forgot | +0.049 |
waited | +0.045 |
stayed | +0.044 |
remembered | +0.044 |
put | +0.043 |
Neg logit contributions | |
Today | -0.042 |
Nice | -0.035 |
This | -0.034 |
These | -0.031 |
Of | -0.029 |
Token | He |
Token ID | 679 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
Today | +0.047 |
uttering | +0.047 |
oky | +0.043 |
owers | +0.042 |
Nice | +0.040 |
Neg logit contributions | |
forgot | -0.073 |
put | -0.070 |
remembered | -0.068 |
waited | -0.068 |
never | -0.066 |
Token | knew |
Token ID | 2993 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
ode | +0.192 |
ts | +0.188 |
ptions | +0.180 |
plank | +0.169 |
ils | +0.159 |
Neg logit contributions | |
Today | -0.204 |
The | -0.188 |
| -0.182 |
Nice | -0.181 |
He | -0.181 |
Token | that |
Token ID | 326 |
Feature activation | -3.14e-03 |
Pos logit contributions | |
forgot | +0.065 |
waited | +0.057 |
remembered | +0.056 |
managed | +0.056 |
dug | +0.056 |
Neg logit contributions | |
Today | -0.046 |
This | -0.039 |
Nice | -0.039 |
Of | -0.033 |
ummy | -0.032 |
Token | forgiving |
Token ID | 43486 |
Feature activation | +8.89e-03 |
Pos logit contributions | |
forgot | +0.007 |
waited | +0.006 |
remembered | +0.006 |
stayed | +0.006 |
managed | +0.006 |
Neg logit contributions | |
Today | -0.007 |
Nice | -0.006 |
This | -0.006 |
These | -0.005 |
Of | -0.005 |
Token | can |
Token ID | 460 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
Today | +0.020 |
Nice | +0.018 |
This | +0.018 |
These | +0.016 |
Of | +0.015 |
Neg logit contributions | |
forgot | -0.017 |
waited | -0.015 |
remembered | -0.014 |
managed | -0.014 |
dug | -0.014 |
Token | make |
Token ID | 787 |
Feature activation | -2.57e-03 |
Pos logit contributions | |
forgot | +0.045 |
remembered | +0.038 |
waited | +0.038 |
hid | +0.036 |
managed | +0.036 |
Neg logit contributions | |
Today | -0.076 |
This | -0.068 |
Nice | -0.065 |
These | -0.062 |
ummy | -0.059 |
Token | cake |
Token ID | 12187 |
Feature activation | +1.66e-03 |
Pos logit contributions | |
forgot | +0.172 |
stayed | +0.156 |
managed | +0.155 |
punished | +0.149 |
remembered | +0.148 |
Neg logit contributions | |
Today | -0.181 |
This | -0.150 |
These | -0.135 |
On | -0.132 |
Some | -0.131 |
Token | for |
Token ID | 329 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
Today | +0.003 |
This | +0.003 |
Nice | +0.003 |
ummy | +0.002 |
These | +0.002 |
Neg logit contributions | |
forgot | -0.004 |
remembered | -0.003 |
stayed | -0.003 |
waited | -0.003 |
managed | -0.003 |
Token | his |
Token ID | 465 |
Feature activation | -5.02e-02 |
Pos logit contributions | |
forgot | +0.047 |
remembered | +0.040 |
stayed | +0.040 |
managed | +0.039 |
waited | +0.039 |
Neg logit contributions | |
Today | -0.050 |
This | -0.043 |
Nice | -0.041 |
These | -0.039 |
ummy | -0.039 |
Token | mom |
Token ID | 1995 |
Feature activation | -4.50e-02 |
Pos logit contributions | |
forgot | +0.091 |
waited | +0.079 |
stayed | +0.078 |
remembered | +0.078 |
managed | +0.076 |
Neg logit contributions | |
Today | -0.124 |
This | -0.105 |
Nice | -0.105 |
These | -0.096 |
ummy | -0.093 |
Token | . |
Token ID | 13 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
forgot | +0.102 |
waited | +0.091 |
stayed | +0.091 |
remembered | +0.090 |
ts | +0.089 |
Neg logit contributions | |
Today | -0.087 |
This | -0.071 |
Nice | -0.066 |
These | -0.061 |
ummy | -0.059 |
Token | He |
Token ID | 679 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
uttering | +0.042 |
Today | +0.041 |
Nice | +0.036 |
oky | +0.036 |
owers | +0.036 |
Neg logit contributions | |
forgot | -0.065 |
waited | -0.063 |
put | -0.062 |
never | -0.061 |
tried | -0.059 |
Token | finds |
Token ID | 7228 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
forgot | +0.143 |
ts | +0.137 |
ode | +0.129 |
stayed | +0.124 |
ppa | +0.124 |
Neg logit contributions | |
Today | -0.274 |
This | -0.247 |
On | -0.227 |
Nice | -0.221 |
She | -0.219 |
Token | a |
Token ID | 257 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
forgot | +0.081 |
stayed | +0.069 |
remembered | +0.069 |
waited | +0.068 |
managed | +0.065 |
Neg logit contributions | |
Today | -0.075 |
This | -0.066 |
Nice | -0.063 |
These | -0.058 |
ummy | -0.056 |
Token | big |
Token ID | 1263 |
Feature activation | +8.45e-05 |
Pos logit contributions | |
forgot | +0.067 |
waited | +0.060 |
stayed | +0.059 |
remembered | +0.058 |
managed | +0.056 |
Neg logit contributions | |
Today | -0.074 |
Nice | -0.063 |
This | -0.062 |
These | -0.056 |
Of | -0.054 |
Token | bowl |
Token ID | 9396 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
Today | +0.000 |
This | +0.000 |
Nice | +0.000 |
These | +0.000 |
ummy | +0.000 |
Neg logit contributions | |
forgot | -0.000 |
stayed | -0.000 |
waited | -0.000 |
remembered | -0.000 |
managed | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
Today | +0.047 |
Nice | +0.038 |
This | +0.038 |
These | +0.034 |
ummy | +0.033 |
Neg logit contributions | |
forgot | -0.056 |
waited | -0.050 |
remembered | -0.050 |
stayed | -0.050 |
put | -0.048 |
Token |
|
Token ID | 198 |
Feature activation | +4.47e-03 |
Pos logit contributions | |
forgot | +0.010 |
never | +0.009 |
put | +0.009 |
learned | +0.009 |
waited | +0.009 |
Neg logit contributions | |
Today | -0.008 |
Nice | -0.007 |
umm | -0.007 |
owers | -0.006 |
This | -0.006 |
Token | Mom |
Token ID | 29252 |
Feature activation | -8.61e-02 |
Pos logit contributions | |
Today | +0.010 |
Nice | +0.009 |
This | +0.008 |
ummy | +0.008 |
These | +0.008 |
Neg logit contributions | |
forgot | -0.009 |
waited | -0.008 |
never | -0.008 |
remembered | -0.008 |
stayed | -0.008 |
Token | sigh |
Token ID | 19680 |
Feature activation | -5.12e-04 |
Pos logit contributions | |
forgot | +0.150 |
ts | +0.134 |
stayed | +0.124 |
imagined | +0.122 |
managed | +0.120 |
Neg logit contributions | |
Today | -0.194 |
This | -0.165 |
Nice | -0.157 |
These | -0.151 |
ummy | -0.150 |
Token | s |
Token ID | 82 |
Feature activation | -4.99e-02 |
Pos logit contributions | |
forgot | +0.001 |
waited | +0.001 |
stayed | +0.001 |
remembered | +0.001 |
put | +0.001 |
Neg logit contributions | |
Today | -0.001 |
Nice | -0.001 |
This | -0.001 |
These | -0.001 |
Of | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
forgot | +0.100 |
stayed | +0.091 |
waited | +0.091 |
put | +0.090 |
remembered | +0.090 |
Neg logit contributions | |
Today | -0.110 |
Nice | -0.096 |
This | -0.093 |
These | -0.089 |
anes | -0.086 |
Token | She |
Token ID | 1375 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
Today | +0.035 |
Nice | +0.031 |
uttering | +0.029 |
umm | +0.029 |
opl | +0.029 |
Neg logit contributions | |
forgot | -0.059 |
put | -0.057 |
waited | -0.057 |
remembered | -0.056 |
tried | -0.055 |
Token | is |
Token ID | 318 |
Feature activation | -6.45e-02 |
Pos logit contributions | |
ts | +0.166 |
forgot | +0.155 |
ode | +0.153 |
managed | +0.140 |
ppa | +0.137 |
Neg logit contributions | |
Today | -0.258 |
This | -0.220 |
On | -0.209 |
Nice | -0.206 |
She | -0.205 |
Token | still |
Token ID | 991 |
Feature activation | -6.55e-02 |
Pos logit contributions | |
forgot | +0.136 |
waited | +0.121 |
stayed | +0.118 |
dug | +0.117 |
managed | +0.116 |
Neg logit contributions | |
Today | -0.124 |
This | -0.106 |
Nice | -0.100 |
Right | -0.089 |
oky | -0.089 |
Token | angry |
Token ID | 7954 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
forgot | +0.134 |
waited | +0.119 |
stayed | +0.118 |
remembered | +0.117 |
put | +0.113 |
Neg logit contributions | |
Today | -0.146 |
Nice | -0.123 |
This | -0.122 |
These | -0.111 |
Of | -0.106 |
Token | , |
Token ID | 11 |
Feature activation | -7.91e-04 |
Pos logit contributions | |
Today | +0.056 |
Nice | +0.048 |
This | +0.047 |
These | +0.044 |
anes | +0.042 |
Neg logit contributions | |
forgot | -0.055 |
waited | -0.050 |
stayed | -0.049 |
put | -0.049 |
remembered | -0.048 |
Token | but |
Token ID | 475 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
forgot | +0.002 |
waited | +0.002 |
remembered | +0.002 |
stayed | +0.002 |
managed | +0.002 |
Neg logit contributions | |
Today | -0.002 |
Nice | -0.001 |
This | -0.001 |
These | -0.001 |
Of | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +5.46e-03 |
Pos logit contributions | |
forgot | +0.004 |
never | +0.004 |
put | +0.004 |
waited | +0.004 |
learned | +0.004 |
Neg logit contributions | |
Today | -0.003 |
Nice | -0.003 |
umm | -0.003 |
owers | -0.003 |
This | -0.003 |
Token | Dad |
Token ID | 46270 |
Feature activation | -8.21e-02 |
Pos logit contributions | |
Today | +0.012 |
Nice | +0.011 |
This | +0.010 |
ummy | +0.010 |
These | +0.009 |
Neg logit contributions | |
forgot | -0.010 |
waited | -0.010 |
never | -0.009 |
stayed | -0.009 |
remembered | -0.009 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
forgot | +0.134 |
stayed | +0.112 |
imagined | +0.111 |
ts | +0.107 |
punished | +0.105 |
Neg logit contributions | |
Today | -0.188 |
This | -0.172 |
These | -0.159 |
Nice | -0.158 |
On | -0.150 |
Token | too |
Token ID | 1165 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
forgot | +0.020 |
remembered | +0.019 |
put | +0.018 |
stayed | +0.017 |
waited | +0.017 |
Neg logit contributions | |
Today | -0.039 |
These | -0.035 |
This | -0.035 |
Nice | -0.034 |
anes | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
forgot | +0.050 |
put | +0.044 |
waited | +0.044 |
never | +0.043 |
remembered | +0.043 |
Neg logit contributions | |
Today | -0.060 |
Nice | -0.053 |
This | -0.050 |
These | -0.049 |
Of | -0.047 |
Token | He |
Token ID | 679 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
Today | +0.038 |
uttering | +0.035 |
owers | +0.035 |
Nice | +0.032 |
opl | +0.030 |
Neg logit contributions | |
forgot | -0.059 |
put | -0.058 |
waited | -0.056 |
remembered | -0.055 |
hoped | -0.055 |
Token | said |
Token ID | 531 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
ts | +0.174 |
ode | +0.162 |
forgot | +0.155 |
argued | +0.148 |
punished | +0.146 |
Neg logit contributions | |
Today | -0.226 |
Nice | -0.208 |
This | -0.207 |
On | -0.200 |
He | -0.194 |
Token | he |
Token ID | 339 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
forgot | +0.040 |
waited | +0.036 |
stayed | +0.035 |
remembered | +0.035 |
put | +0.034 |
Neg logit contributions | |
Today | -0.042 |
Nice | -0.035 |
This | -0.034 |
These | -0.031 |
oky | -0.030 |
Token | was |
Token ID | 373 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
forgot | +0.144 |
ts | +0.138 |
punished | +0.127 |
waited | +0.125 |
dug | +0.122 |
Neg logit contributions | |
Today | -0.233 |
This | -0.211 |
Nice | -0.207 |
These | -0.188 |
What | -0.183 |
Token | proud |
Token ID | 6613 |
Feature activation | +6.65e-03 |
Pos logit contributions | |
forgot | +0.130 |
waited | +0.115 |
stayed | +0.114 |
remembered | +0.113 |
dug | +0.109 |
Neg logit contributions | |
Today | -0.122 |
This | -0.103 |
Nice | -0.102 |
These | -0.091 |
Of | -0.087 |
Token | of |
Token ID | 286 |
Feature activation | +4.67e-03 |
Pos logit contributions | |
Today | +0.011 |
Nice | +0.009 |
This | +0.009 |
These | +0.007 |
ummy | +0.007 |
Neg logit contributions | |
forgot | -0.018 |
waited | -0.016 |
stayed | -0.016 |
remembered | -0.016 |
managed | -0.015 |
Token | thought |
Token ID | 1807 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
forgot | +0.151 |
ts | +0.138 |
managed | +0.127 |
stayed | +0.127 |
punished | +0.124 |
Neg logit contributions | |
Today | -0.195 |
This | -0.166 |
Nice | -0.160 |
On | -0.145 |
She | -0.144 |
Token | for |
Token ID | 329 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
forgot | +0.047 |
waited | +0.042 |
remembered | +0.042 |
stayed | +0.041 |
managed | +0.040 |
Neg logit contributions | |
Today | -0.037 |
This | -0.030 |
Nice | -0.030 |
These | -0.026 |
Of | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
forgot | +0.087 |
stayed | +0.073 |
remembered | +0.073 |
managed | +0.072 |
waited | +0.071 |
Neg logit contributions | |
Today | -0.062 |
This | -0.052 |
Nice | -0.049 |
These | -0.042 |
Of | -0.042 |
Token | moment |
Token ID | 2589 |
Feature activation | +3.20e-03 |
Pos logit contributions | |
forgot | +0.051 |
waited | +0.046 |
stayed | +0.046 |
remembered | +0.046 |
put | +0.045 |
Neg logit contributions | |
Today | -0.036 |
Nice | -0.029 |
This | -0.029 |
These | -0.026 |
ummy | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
Today | +0.008 |
Nice | +0.007 |
This | +0.007 |
These | +0.006 |
anes | +0.006 |
Neg logit contributions | |
forgot | -0.006 |
waited | -0.005 |
stayed | -0.005 |
remembered | -0.005 |
put | -0.005 |
Token | He |
Token ID | 679 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
Today | +0.051 |
owers | +0.047 |
anes | +0.046 |
uttering | +0.046 |
opl | +0.044 |
Neg logit contributions | |
forgot | -0.083 |
remembered | -0.080 |
waited | -0.080 |
put | -0.079 |
tried | -0.077 |
Token | wanted |
Token ID | 2227 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
ts | +0.163 |
ode | +0.136 |
forgot | +0.133 |
ils | +0.130 |
punished | +0.129 |
Neg logit contributions | |
Today | -0.256 |
He | -0.223 |
On | -0.223 |
Right | -0.221 |
Nice | -0.216 |
Token | to |
Token ID | 284 |
Feature activation | -5.37e-02 |
Pos logit contributions | |
forgot | +0.092 |
remembered | +0.081 |
waited | +0.079 |
managed | +0.079 |
stayed | +0.079 |
Neg logit contributions | |
Today | -0.054 |
This | -0.048 |
Nice | -0.046 |
These | -0.039 |
Of | -0.039 |
Token | sound |
Token ID | 2128 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
forgot | +0.094 |
remembered | +0.083 |
managed | +0.079 |
waited | +0.078 |
ts | +0.077 |
Neg logit contributions | |
Today | -0.130 |
This | -0.116 |
Nice | -0.106 |
These | -0.099 |
Of | -0.097 |
Token | brave |
Token ID | 14802 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
Today | +0.071 |
Nice | +0.060 |
This | +0.059 |
These | +0.055 |
ummy | +0.052 |
Neg logit contributions | |
forgot | -0.065 |
waited | -0.058 |
stayed | -0.058 |
remembered | -0.057 |
put | -0.056 |
Token | and |
Token ID | 290 |
Feature activation | -7.83e-03 |
Pos logit contributions | |
Today | +0.085 |
Nice | +0.072 |
This | +0.072 |
These | +0.065 |
Of | +0.062 |
Neg logit contributions | |
forgot | -0.079 |
waited | -0.070 |
stayed | -0.069 |
remembered | -0.069 |
put | -0.067 |
Token | drain |
Token ID | 14782 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
forgot | +0.016 |
waited | +0.014 |
stayed | +0.014 |
remembered | +0.014 |
put | +0.014 |
Neg logit contributions | |
Today | -0.016 |
Nice | -0.014 |
This | -0.014 |
These | -0.012 |
Of | -0.012 |
Token | by |
Token ID | 416 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
Today | +0.058 |
This | +0.048 |
Nice | +0.047 |
These | +0.042 |
ummy | +0.040 |
Neg logit contributions | |
forgot | -0.068 |
waited | -0.061 |
remembered | -0.061 |
stayed | -0.060 |
managed | -0.058 |
Token | cleaning |
Token ID | 12724 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
forgot | +0.023 |
waited | +0.019 |
remembered | +0.019 |
stayed | +0.019 |
managed | +0.018 |
Neg logit contributions | |
Today | -0.030 |
This | -0.025 |
Nice | -0.024 |
These | -0.023 |
ummy | -0.022 |
Token | it |
Token ID | 340 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
Today | +0.088 |
This | +0.074 |
Nice | +0.073 |
These | +0.067 |
ummy | +0.064 |
Neg logit contributions | |
forgot | -0.086 |
waited | -0.077 |
stayed | -0.076 |
remembered | -0.075 |
managed | -0.072 |
Token | ." |
Token ID | 526 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
forgot | +0.034 |
waited | +0.030 |
remembered | +0.030 |
stayed | +0.030 |
managed | +0.029 |
Neg logit contributions | |
Today | -0.029 |
This | -0.023 |
Nice | -0.023 |
These | -0.020 |
ummy | -0.020 |
Token | He |
Token ID | 679 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
Today | +0.036 |
Nice | +0.031 |
uttering | +0.028 |
oky | +0.027 |
anes | +0.027 |
Neg logit contributions | |
forgot | -0.056 |
waited | -0.052 |
remembered | -0.051 |
put | -0.051 |
tried | -0.051 |
Token | ran |
Token ID | 4966 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
forgot | +0.137 |
ode | +0.135 |
ts | +0.119 |
ppa | +0.112 |
stayed | +0.110 |
Neg logit contributions | |
Today | -0.264 |
This | -0.253 |
On | -0.236 |
She | -0.228 |
Up | -0.227 |
Token | inside |
Token ID | 2641 |
Feature activation | -3.72e-03 |
Pos logit contributions | |
forgot | +0.035 |
waited | +0.031 |
stayed | +0.031 |
remembered | +0.031 |
put | +0.029 |
Neg logit contributions | |
Today | -0.033 |
This | -0.028 |
Nice | -0.028 |
These | -0.025 |
Of | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
forgot | +0.007 |
waited | +0.006 |
stayed | +0.006 |
remembered | +0.006 |
put | +0.006 |
Neg logit contributions | |
Today | -0.009 |
Nice | -0.008 |
This | -0.008 |
These | -0.007 |
Of | -0.007 |
Token | asked |
Token ID | 1965 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
ode | +0.035 |
promise | +0.031 |
forgot | +0.029 |
stayed | +0.027 |
ts | +0.026 |
Neg logit contributions | |
This | -0.060 |
Today | -0.058 |
The | -0.055 |
After | -0.054 |
She | -0.054 |
Token | his |
Token ID | 465 |
Feature activation | -5.13e-02 |
Pos logit contributions | |
forgot | +0.039 |
waited | +0.034 |
stayed | +0.034 |
remembered | +0.033 |
put | +0.032 |
Neg logit contributions | |
Today | -0.043 |
Nice | -0.037 |
This | -0.036 |
These | -0.033 |
Of | -0.032 |
Token | for |
Token ID | 329 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
Today | +0.021 |
Nice | +0.018 |
This | +0.017 |
These | +0.015 |
Of | +0.015 |
Neg logit contributions | |
forgot | -0.024 |
waited | -0.022 |
stayed | -0.021 |
remembered | -0.021 |
managed | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
forgot | +0.080 |
remembered | +0.069 |
stayed | +0.067 |
managed | +0.067 |
waited | +0.067 |
Neg logit contributions | |
Today | -0.081 |
This | -0.071 |
Nice | -0.066 |
These | -0.063 |
ummy | -0.061 |
Token | caul |
Token ID | 46087 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
forgot | +0.065 |
waited | +0.057 |
remembered | +0.057 |
stayed | +0.057 |
managed | +0.054 |
Neg logit contributions | |
Today | -0.076 |
Nice | -0.064 |
This | -0.064 |
These | -0.058 |
ummy | -0.056 |
Token | iflower |
Token ID | 42642 |
Feature activation | +7.25e-03 |
Pos logit contributions | |
Today | +0.048 |
This | +0.039 |
Nice | +0.038 |
ummy | +0.037 |
These | +0.035 |
Neg logit contributions | |
forgot | -0.059 |
waited | -0.054 |
stayed | -0.053 |
remembered | -0.052 |
hid | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
Today | +0.013 |
This | +0.010 |
Nice | +0.010 |
These | +0.009 |
ummy | +0.009 |
Neg logit contributions | |
forgot | -0.018 |
waited | -0.016 |
remembered | -0.016 |
stayed | -0.016 |
managed | -0.015 |
Token | He |
Token ID | 679 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
Today | +0.044 |
uttering | +0.042 |
Nice | +0.038 |
oky | +0.038 |
ummy | +0.035 |
Neg logit contributions | |
forgot | -0.077 |
waited | -0.073 |
put | -0.073 |
never | -0.071 |
stayed | -0.071 |
Token | ran |
Token ID | 4966 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
forgot | +0.136 |
ts | +0.125 |
stayed | +0.111 |
punished | +0.109 |
ode | +0.106 |
Neg logit contributions | |
Today | -0.290 |
This | -0.265 |
Nice | -0.245 |
On | -0.242 |
She | -0.234 |
Token | to |
Token ID | 284 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
forgot | +0.024 |
waited | +0.021 |
stayed | +0.021 |
remembered | +0.021 |
put | +0.020 |
Neg logit contributions | |
Today | -0.023 |
Nice | -0.019 |
This | -0.019 |
These | -0.017 |
Of | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
forgot | +0.040 |
stayed | +0.035 |
remembered | +0.034 |
waited | +0.034 |
managed | +0.033 |
Neg logit contributions | |
Today | -0.044 |
This | -0.038 |
Nice | -0.036 |
These | -0.033 |
Of | -0.033 |
Token | other |
Token ID | 584 |
Feature activation | +4.05e-03 |
Pos logit contributions | |
forgot | +0.029 |
waited | +0.025 |
stayed | +0.025 |
remembered | +0.025 |
managed | +0.024 |
Neg logit contributions | |
Today | -0.033 |
This | -0.028 |
Nice | -0.028 |
These | -0.026 |
ummy | -0.025 |
Token | kids |
Token ID | 3988 |
Feature activation | -4.06e-03 |
Pos logit contributions | |
Today | +0.009 |
This | +0.008 |
Nice | +0.008 |
These | +0.007 |
ummy | +0.007 |
Neg logit contributions | |
forgot | -0.008 |
waited | -0.007 |
stayed | -0.007 |
remembered | -0.007 |
managed | -0.007 |
Token | is |
Token ID | 318 |
Feature activation | -5.50e-02 |
Pos logit contributions | |
forgot | +0.095 |
stayed | +0.081 |
waited | +0.080 |
ts | +0.080 |
punished | +0.080 |
Neg logit contributions | |
This | -0.059 |
Today | -0.053 |
A | -0.043 |
The | -0.042 |
These | -0.041 |
Token | proud |
Token ID | 6613 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
forgot | +0.107 |
waited | +0.093 |
stayed | +0.092 |
remembered | +0.092 |
managed | +0.089 |
Neg logit contributions | |
Today | -0.126 |
This | -0.107 |
Nice | -0.107 |
These | -0.096 |
Of | -0.093 |
Token | of |
Token ID | 286 |
Feature activation | -9.58e-04 |
Pos logit contributions | |
Today | +0.022 |
Nice | +0.018 |
This | +0.017 |
These | +0.016 |
Of | +0.015 |
Neg logit contributions | |
forgot | -0.029 |
waited | -0.026 |
stayed | -0.026 |
remembered | -0.026 |
put | -0.025 |
Token | her |
Token ID | 607 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
forgot | +0.002 |
waited | +0.002 |
remembered | +0.002 |
stayed | +0.002 |
managed | +0.002 |
Neg logit contributions | |
Today | -0.002 |
This | -0.002 |
Nice | -0.002 |
These | -0.002 |
Of | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
forgot | +0.061 |
waited | +0.054 |
stayed | +0.054 |
remembered | +0.053 |
put | +0.052 |
Neg logit contributions | |
Today | -0.069 |
Nice | -0.059 |
This | -0.058 |
These | -0.053 |
Of | -0.051 |
Token | He |
Token ID | 679 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
uttering | +0.038 |
Today | +0.038 |
owers | +0.032 |
eeper | +0.032 |
ower | +0.032 |
Neg logit contributions | |
forgot | -0.067 |
put | -0.065 |
waited | -0.064 |
never | -0.064 |
remembered | -0.063 |
Token | waits |
Token ID | 28364 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
ts | +0.179 |
forgot | +0.179 |
stayed | +0.159 |
managed | +0.156 |
ppa | +0.154 |
Neg logit contributions | |
Today | -0.247 |
This | -0.220 |
Nice | -0.211 |
On | -0.199 |
She | -0.197 |
Token | for |
Token ID | 329 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
Today | +0.033 |
Nice | +0.028 |
This | +0.027 |
These | +0.025 |
Of | +0.024 |
Neg logit contributions | |
forgot | -0.032 |
waited | -0.029 |
stayed | -0.028 |
remembered | -0.028 |
put | -0.028 |
Token | her |
Token ID | 607 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
forgot | +0.037 |
stayed | +0.032 |
remembered | +0.032 |
managed | +0.032 |
waited | +0.031 |
Neg logit contributions | |
Today | -0.034 |
This | -0.029 |
Nice | -0.029 |
ummy | -0.026 |
These | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
forgot | +0.076 |
waited | +0.067 |
stayed | +0.067 |
remembered | +0.066 |
put | +0.064 |
Neg logit contributions | |
Today | -0.075 |
Nice | -0.063 |
This | -0.062 |
These | -0.056 |
Of | -0.054 |
Token | slow |
Token ID | 3105 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
forgot | +0.085 |
remembered | +0.072 |
managed | +0.070 |
stayed | +0.069 |
waited | +0.069 |
Neg logit contributions | |
Today | -0.144 |
This | -0.123 |
Nice | -0.119 |
These | -0.107 |
On | -0.106 |
Token | Tommy |
Token ID | 19919 |
Feature activation | -9.00e-02 |
Pos logit contributions | |
Today | +0.033 |
Nice | +0.029 |
uttering | +0.025 |
This | +0.025 |
anes | +0.025 |
Neg logit contributions | |
forgot | -0.043 |
waited | -0.041 |
put | -0.040 |
remembered | -0.040 |
tried | -0.040 |
Token | nods |
Token ID | 34833 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
forgot | +0.122 |
stayed | +0.103 |
ts | +0.101 |
waited | +0.100 |
managed | +0.097 |
Neg logit contributions | |
Today | -0.254 |
This | -0.219 |
Nice | -0.214 |
On | -0.195 |
These | -0.193 |
Token | and |
Token ID | 290 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
forgot | +0.059 |
remembered | +0.055 |
put | +0.054 |
waited | +0.054 |
stayed | +0.054 |
Neg logit contributions | |
Today | -0.067 |
This | -0.058 |
These | -0.058 |
Nice | -0.058 |
anes | -0.054 |
Token | smiles |
Token ID | 21845 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
forgot | +0.093 |
ts | +0.079 |
never | +0.078 |
punished | +0.078 |
stayed | +0.078 |
Neg logit contributions | |
Today | -0.129 |
This | -0.116 |
Nice | -0.114 |
Of | -0.107 |
Up | -0.102 |
Token | . |
Token ID | 13 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
forgot | +0.036 |
remembered | +0.035 |
waited | +0.034 |
stayed | +0.034 |
put | +0.034 |
Neg logit contributions | |
Today | -0.041 |
These | -0.035 |
Nice | -0.034 |
This | -0.034 |
anes | -0.032 |
Token | He |
Token ID | 679 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
Today | +0.041 |
owers | +0.038 |
uttering | +0.038 |
oky | +0.036 |
opl | +0.036 |
Neg logit contributions | |
forgot | -0.062 |
put | -0.060 |
remembered | -0.058 |
waited | -0.057 |
tried | -0.057 |
Token | likes |
Token ID | 7832 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
forgot | +0.223 |
ts | +0.201 |
stayed | +0.193 |
punished | +0.193 |
waited | +0.191 |
Neg logit contributions | |
Today | -0.250 |
This | -0.207 |
Nice | -0.200 |
On | -0.187 |
Up | -0.182 |
Token | to |
Token ID | 284 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
forgot | +0.042 |
waited | +0.037 |
remembered | +0.036 |
stayed | +0.036 |
managed | +0.035 |
Neg logit contributions | |
Today | -0.041 |
Nice | -0.035 |
This | -0.035 |
These | -0.032 |
Of | -0.030 |
Token | mix |
Token ID | 5022 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
forgot | +0.064 |
waited | +0.055 |
remembered | +0.054 |
stayed | +0.054 |
managed | +0.052 |
Neg logit contributions | |
Today | -0.097 |
This | -0.084 |
Nice | -0.080 |
These | -0.074 |
On | -0.072 |
Token | . |
Token ID | 13 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
Today | +0.097 |
Nice | +0.085 |
This | +0.081 |
These | +0.076 |
Of | +0.071 |
Neg logit contributions | |
forgot | -0.075 |
waited | -0.068 |
put | -0.068 |
stayed | -0.067 |
remembered | -0.065 |
Token | He |
Token ID | 679 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
uttering | +0.065 |
owers | +0.062 |
Today | +0.060 |
ower | +0.056 |
oky | +0.056 |
Neg logit contributions | |
put | -0.083 |
forgot | -0.082 |
let | -0.079 |
waited | -0.076 |
remembered | -0.075 |
Token | yellow |
Token ID | 7872 |
Feature activation | +4.28e-03 |
Pos logit contributions | |
forgot | +0.023 |
waited | +0.020 |
remembered | +0.020 |
stayed | +0.020 |
punished | +0.020 |
Neg logit contributions | |
Today | -0.022 |
This | -0.019 |
Nice | -0.019 |
These | -0.017 |
Of | -0.017 |
Token | ," |
Token ID | 553 |
Feature activation | +5.83e-03 |
Pos logit contributions | |
Today | +0.008 |
Nice | +0.007 |
This | +0.007 |
These | +0.006 |
Of | +0.006 |
Neg logit contributions | |
forgot | -0.010 |
waited | -0.009 |
stayed | -0.009 |
put | -0.009 |
remembered | -0.009 |
Token | Dad |
Token ID | 17415 |
Feature activation | -7.49e-02 |
Pos logit contributions | |
Today | +0.014 |
Nice | +0.012 |
This | +0.012 |
These | +0.011 |
anes | +0.011 |
Neg logit contributions | |
forgot | -0.011 |
waited | -0.010 |
remembered | -0.010 |
stayed | -0.010 |
put | -0.009 |
Token | says |
Token ID | 1139 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
forgot | +0.110 |
stayed | +0.092 |
managed | +0.088 |
ts | +0.087 |
never | +0.087 |
Neg logit contributions | |
Today | -0.198 |
This | -0.176 |
Nice | -0.166 |
Of | -0.162 |
These | -0.160 |
Token | . |
Token ID | 13 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
forgot | +0.056 |
waited | +0.052 |
put | +0.051 |
stayed | +0.051 |
remembered | +0.051 |
Neg logit contributions | |
Today | -0.062 |
Nice | -0.051 |
This | -0.047 |
These | -0.046 |
opl | -0.046 |
Token | He |
Token ID | 679 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
Today | +0.040 |
owers | +0.035 |
uttering | +0.035 |
opl | +0.035 |
Nice | +0.035 |
Neg logit contributions | |
forgot | -0.049 |
put | -0.047 |
remembered | -0.045 |
waited | -0.045 |
tried | -0.044 |
Token | shows |
Token ID | 2523 |
Feature activation | -3.15e-03 |
Pos logit contributions | |
forgot | +0.213 |
stayed | +0.182 |
punished | +0.176 |
ts | +0.175 |
managed | +0.174 |
Neg logit contributions | |
Today | -0.260 |
This | -0.225 |
Nice | -0.211 |
On | -0.203 |
These | -0.202 |
Token | Anna |
Token ID | 11735 |
Feature activation | -5.66e-02 |
Pos logit contributions | |
forgot | +0.007 |
stayed | +0.006 |
remembered | +0.006 |
waited | +0.006 |
managed | +0.006 |
Neg logit contributions | |
Today | -0.007 |
This | -0.006 |
Nice | -0.006 |
These | -0.005 |
Of | -0.005 |
Token | how |
Token ID | 703 |
Feature activation | +6.82e-03 |
Pos logit contributions | |
forgot | +0.113 |
waited | +0.097 |
stayed | +0.095 |
remembered | +0.095 |
managed | +0.091 |
Neg logit contributions | |
Today | -0.130 |
This | -0.115 |
Nice | -0.109 |
These | -0.102 |
Of | -0.096 |
Token | to |
Token ID | 284 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
Today | +0.016 |
Nice | +0.013 |
This | +0.013 |
These | +0.012 |
Of | +0.011 |
Neg logit contributions | |
forgot | -0.014 |
waited | -0.012 |
stayed | -0.012 |
remembered | -0.012 |
put | -0.012 |
Token | cut |
Token ID | 2005 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
forgot | +0.102 |
managed | +0.086 |
remembered | +0.086 |
stayed | +0.083 |
punished | +0.081 |
Neg logit contributions | |
Today | -0.132 |
This | -0.118 |
These | -0.103 |
On | -0.101 |
Nice | -0.100 |
Token | ily |
Token ID | 813 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
Today | +0.067 |
This | +0.057 |
Nice | +0.057 |
These | +0.052 |
anes | +0.051 |
Neg logit contributions | |
forgot | -0.058 |
waited | -0.051 |
put | -0.051 |
remembered | -0.051 |
stayed | -0.051 |
Token | hugged |
Token ID | 41130 |
Feature activation | +6.91e-03 |
Pos logit contributions | |
forgot | +0.124 |
ts | +0.118 |
waited | +0.109 |
stayed | +0.109 |
punished | +0.104 |
Neg logit contributions | |
Today | -0.253 |
This | -0.220 |
Nice | -0.213 |
These | -0.198 |
She | -0.189 |
Token | her |
Token ID | 607 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
Today | +0.017 |
Nice | +0.015 |
This | +0.014 |
These | +0.013 |
Of | +0.013 |
Neg logit contributions | |
forgot | -0.013 |
waited | -0.011 |
stayed | -0.011 |
remembered | -0.011 |
put | -0.011 |
Token | mom |
Token ID | 1995 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
forgot | +0.067 |
waited | +0.058 |
stayed | +0.057 |
remembered | +0.057 |
put | +0.055 |
Neg logit contributions | |
Today | -0.104 |
Nice | -0.090 |
This | -0.089 |
These | -0.083 |
Of | -0.080 |
Token | . |
Token ID | 13 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
forgot | +0.055 |
waited | +0.048 |
stayed | +0.048 |
remembered | +0.047 |
put | +0.046 |
Neg logit contributions | |
Today | -0.080 |
Nice | -0.070 |
This | -0.069 |
These | -0.065 |
Of | -0.061 |
Token | She |
Token ID | 1375 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
uttering | +0.051 |
andel | +0.049 |
Today | +0.049 |
oky | +0.048 |
umm | +0.047 |
Neg logit contributions | |
forgot | -0.073 |
put | -0.070 |
remembered | -0.068 |
let | -0.067 |
tried | -0.067 |
Token | was |
Token ID | 373 |
Feature activation | -6.37e-02 |
Pos logit contributions | |
ode | +0.208 |
plank | +0.200 |
ts | +0.197 |
ptions | +0.185 |
ils | +0.170 |
Neg logit contributions | |
| -0.185 |
The | -0.181 |
She | -0.181 |
Today | -0.174 |
A | -0.162 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
forgot | +0.153 |
waited | +0.136 |
managed | +0.133 |
dug | +0.133 |
ts | +0.132 |
Neg logit contributions | |
Today | -0.105 |
This | -0.086 |
Nice | -0.082 |
ummy | -0.070 |
Right | -0.068 |
Token | . |
Token ID | 13 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
forgot | +0.026 |
waited | +0.023 |
stayed | +0.023 |
remembered | +0.023 |
managed | +0.022 |
Neg logit contributions | |
Today | -0.025 |
Nice | -0.021 |
This | -0.021 |
These | -0.018 |
ummy | -0.018 |
Token | She |
Token ID | 1375 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
andel | +0.073 |
uttering | +0.071 |
rier | +0.071 |
umm | +0.071 |
eeper | +0.070 |
Neg logit contributions | |
forgot | -0.077 |
remembered | -0.076 |
put | -0.075 |
never | -0.074 |
hoped | -0.074 |
Token | said |
Token ID | 531 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
ts | +0.174 |
ode | +0.166 |
ptions | +0.152 |
plank | +0.150 |
ils | +0.132 |
Neg logit contributions | |
She | -0.191 |
The | -0.190 |
| -0.184 |
Today | -0.184 |
And | -0.180 |
Token | play |
Token ID | 711 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
forgot | +0.055 |
ts | +0.048 |
waited | +0.048 |
remembered | +0.047 |
stayed | +0.046 |
Neg logit contributions | |
Today | -0.071 |
This | -0.062 |
Nice | -0.057 |
These | -0.054 |
ay | -0.054 |
Token | with |
Token ID | 351 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
Today | +0.036 |
This | +0.030 |
Nice | +0.029 |
These | +0.025 |
Of | +0.024 |
Neg logit contributions | |
forgot | -0.050 |
waited | -0.045 |
stayed | -0.045 |
remembered | -0.044 |
managed | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | +8.90e-03 |
Pos logit contributions | |
Today | +0.044 |
This | +0.038 |
Nice | +0.037 |
These | +0.035 |
ummy | +0.033 |
Neg logit contributions | |
forgot | -0.039 |
remembered | -0.033 |
waited | -0.033 |
stayed | -0.033 |
managed | -0.032 |
Token | box |
Token ID | 3091 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
Today | +0.025 |
This | +0.022 |
Nice | +0.022 |
These | +0.021 |
ummy | +0.020 |
Neg logit contributions | |
forgot | -0.013 |
waited | -0.011 |
remembered | -0.011 |
stayed | -0.011 |
managed | -0.010 |
Token | too |
Token ID | 1165 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
Today | +0.060 |
Nice | +0.051 |
This | +0.051 |
These | +0.046 |
Of | +0.044 |
Neg logit contributions | |
forgot | -0.055 |
waited | -0.049 |
stayed | -0.048 |
remembered | -0.048 |
put | -0.047 |
Token | ?" |
Token ID | 1701 |
Feature activation | +5.56e-02 |
Pos logit contributions | |
Today | +0.034 |
Nice | +0.032 |
This | +0.030 |
These | +0.030 |
anes | +0.028 |
Neg logit contributions | |
forgot | -0.023 |
put | -0.021 |
waited | -0.021 |
remembered | -0.020 |
stayed | -0.019 |
Token | Tim |
Token ID | 5045 |
Feature activation | -7.91e-02 |
Pos logit contributions | |
Today | +0.143 |
uttering | +0.126 |
Nice | +0.125 |
opl | +0.122 |
anes | +0.118 |
Neg logit contributions | |
forgot | -0.088 |
tried | -0.082 |
put | -0.079 |
waited | -0.078 |
hid | -0.072 |
Token | felt |
Token ID | 2936 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
ts | +0.109 |
forgot | +0.101 |
punished | +0.089 |
never | +0.088 |
ils | +0.087 |
Neg logit contributions | |
Today | -0.204 |
This | -0.176 |
Nice | -0.169 |
She | -0.163 |
Of | -0.160 |
Token | guilty |
Token ID | 6717 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
forgot | +0.050 |
remembered | +0.044 |
put | +0.044 |
stayed | +0.044 |
waited | +0.043 |
Neg logit contributions | |
Today | -0.061 |
Nice | -0.052 |
This | -0.050 |
These | -0.048 |
anes | -0.047 |
Token | because |
Token ID | 780 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
Today | +0.033 |
This | +0.028 |
Nice | +0.028 |
These | +0.028 |
anes | +0.027 |
Neg logit contributions | |
forgot | -0.023 |
put | -0.021 |
stayed | -0.021 |
remembered | -0.020 |
waited | -0.020 |
Token | he |
Token ID | 339 |
Feature activation | -8.61e-02 |
Pos logit contributions | |
Today | +0.065 |
Nice | +0.053 |
This | +0.053 |
These | +0.048 |
Of | +0.044 |
Neg logit contributions | |
forgot | -0.077 |
waited | -0.069 |
stayed | -0.068 |
remembered | -0.068 |
put | -0.067 |
Token | the |
Token ID | 262 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
Today | +0.094 |
Nice | +0.082 |
This | +0.078 |
These | +0.074 |
oky | +0.072 |
Neg logit contributions | |
forgot | -0.062 |
put | -0.056 |
waited | -0.056 |
stayed | -0.056 |
remembered | -0.053 |
Token | child |
Token ID | 1200 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
Today | +0.025 |
This | +0.021 |
Nice | +0.021 |
These | +0.019 |
ummy | +0.018 |
Neg logit contributions | |
forgot | -0.024 |
waited | -0.021 |
stayed | -0.021 |
remembered | -0.021 |
managed | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | -4.15e-02 |
Pos logit contributions | |
forgot | +0.024 |
waited | +0.021 |
remembered | +0.021 |
stayed | +0.021 |
put | +0.020 |
Neg logit contributions | |
Today | -0.021 |
This | -0.017 |
Nice | -0.017 |
These | -0.016 |
Of | -0.015 |
Token | try |
Token ID | 1949 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
forgot | +0.067 |
remembered | +0.058 |
ils | +0.055 |
punished | +0.055 |
waited | +0.054 |
Neg logit contributions | |
Today | -0.103 |
This | -0.090 |
Nice | -0.085 |
Of | -0.077 |
On | -0.076 |
Token | again |
Token ID | 757 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
Today | +0.031 |
Nice | +0.026 |
This | +0.026 |
These | +0.024 |
oky | +0.023 |
Neg logit contributions | |
forgot | -0.026 |
stayed | -0.023 |
remembered | -0.023 |
put | -0.023 |
waited | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +6.11e-02 |
Pos logit contributions | |
Today | +0.041 |
Nice | +0.035 |
This | +0.034 |
These | +0.032 |
anes | +0.030 |
Neg logit contributions | |
forgot | -0.048 |
waited | -0.044 |
put | -0.043 |
remembered | -0.043 |
stayed | -0.043 |
Token | Finally |
Token ID | 9461 |
Feature activation | +6.60e-03 |
Pos logit contributions | |
Today | +0.091 |
Nice | +0.082 |
uttering | +0.076 |
opl | +0.072 |
oky | +0.071 |
Neg logit contributions | |
forgot | -0.131 |
put | -0.130 |
waited | -0.127 |
tried | -0.124 |
learned | -0.123 |
Token | after |
Token ID | 706 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
Today | +0.012 |
This | +0.010 |
Nice | +0.010 |
These | +0.009 |
Of | +0.008 |
Neg logit contributions | |
forgot | -0.016 |
waited | -0.014 |
stayed | -0.014 |
remembered | -0.014 |
dug | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | -6.40e-03 |
Pos logit contributions | |
Today | +0.038 |
Nice | +0.033 |
This | +0.032 |
These | +0.030 |
Of | +0.028 |
Neg logit contributions | |
forgot | -0.029 |
waited | -0.026 |
stayed | -0.025 |
remembered | -0.025 |
put | -0.025 |
Token | few |
Token ID | 1178 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
forgot | +0.014 |
waited | +0.012 |
stayed | +0.012 |
remembered | +0.012 |
put | +0.012 |
Neg logit contributions | |
Today | -0.014 |
Nice | -0.011 |
This | -0.011 |
These | -0.010 |
Of | -0.010 |
Token | tries |
Token ID | 8404 |
Feature activation | +3.96e-03 |
Pos logit contributions | |
forgot | +0.029 |
stayed | +0.025 |
punished | +0.025 |
ppa | +0.025 |
cleaned | +0.025 |
Neg logit contributions | |
Today | -0.032 |
Nice | -0.025 |
This | -0.025 |
These | -0.024 |
single | -0.023 |
Token | she |
Token ID | 673 |
Feature activation | -7.83e-02 |
Pos logit contributions | |
Today | +0.079 |
Nice | +0.066 |
This | +0.065 |
These | +0.059 |
Of | +0.056 |
Neg logit contributions | |
forgot | -0.085 |
waited | -0.077 |
stayed | -0.076 |
remembered | -0.076 |
put | -0.074 |
Token | was |
Token ID | 373 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
ts | +0.104 |
forgot | +0.081 |
scar | +0.079 |
stayed | +0.077 |
cleaned | +0.077 |
Neg logit contributions | |
Today | -0.196 |
This | -0.161 |
Nice | -0.156 |
On | -0.151 |
oky | -0.149 |
Token | even |
Token ID | 772 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
forgot | +0.086 |
waited | +0.076 |
stayed | +0.075 |
remembered | +0.074 |
dug | +0.072 |
Neg logit contributions | |
Today | -0.084 |
This | -0.071 |
Nice | -0.068 |
These | -0.062 |
Right | -0.060 |
Token | more |
Token ID | 517 |
Feature activation | +9.57e-03 |
Pos logit contributions | |
forgot | +0.074 |
stayed | +0.068 |
waited | +0.068 |
never | +0.067 |
dug | +0.064 |
Neg logit contributions | |
Today | -0.080 |
Nice | -0.068 |
This | -0.065 |
Of | -0.064 |
Right | -0.061 |
Token | excited |
Token ID | 6568 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
Today | +0.022 |
Nice | +0.019 |
This | +0.018 |
These | +0.017 |
oky | +0.016 |
Neg logit contributions | |
forgot | -0.019 |
stayed | -0.017 |
waited | -0.016 |
remembered | -0.016 |
dug | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +6.74e-02 |
Pos logit contributions | |
Today | +0.055 |
Nice | +0.046 |
This | +0.045 |
These | +0.042 |
anes | +0.039 |
Neg logit contributions | |
forgot | -0.053 |
waited | -0.048 |
stayed | -0.048 |
put | -0.047 |
remembered | -0.046 |
Token | It |
Token ID | 632 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
Today | +0.080 |
Nice | +0.074 |
opl | +0.071 |
anes | +0.065 |
uttering | +0.063 |
Neg logit contributions | |
waited | -0.170 |
forgot | -0.166 |
put | -0.165 |
stayed | -0.164 |
tried | -0.162 |
Token | was |
Token ID | 373 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
ts | +0.063 |
forgot | +0.061 |
ppa | +0.057 |
punished | +0.056 |
remembered | +0.054 |
Neg logit contributions | |
Today | -0.085 |
Nice | -0.075 |
This | -0.073 |
Right | -0.066 |
On | -0.066 |
Token | time |
Token ID | 640 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
forgot | +0.060 |
waited | +0.053 |
stayed | +0.052 |
remembered | +0.052 |
put | +0.050 |
Neg logit contributions | |
Today | -0.073 |
Nice | -0.062 |
This | -0.061 |
These | -0.056 |
Of | -0.054 |
Token | to |
Token ID | 284 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
Today | +0.027 |
Nice | +0.023 |
This | +0.022 |
These | +0.021 |
Of | +0.020 |
Neg logit contributions | |
forgot | -0.026 |
waited | -0.023 |
stayed | -0.023 |
remembered | -0.023 |
put | -0.023 |
Token | measure |
Token ID | 3953 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
forgot | +0.063 |
remembered | +0.056 |
waited | +0.052 |
managed | +0.052 |
stayed | +0.051 |
Neg logit contributions | |
Today | -0.080 |
This | -0.065 |
Nice | -0.060 |
On | -0.057 |
These | -0.056 |
Token | o |
Token ID | 78 |
Feature activation | -4.52e-02 |
Pos logit contributions | |
forgot | +0.078 |
waited | +0.070 |
stayed | +0.069 |
remembered | +0.068 |
punished | +0.068 |
Neg logit contributions | |
Today | -0.067 |
This | -0.056 |
Nice | -0.055 |
These | -0.049 |
Of | -0.047 |
Token | tried |
Token ID | 3088 |
Feature activation | -3.43e-03 |
Pos logit contributions | |
forgot | +0.054 |
punished | +0.046 |
ts | +0.044 |
never | +0.042 |
remembered | +0.041 |
Neg logit contributions | |
Today | -0.118 |
This | -0.106 |
On | -0.099 |
Up | -0.098 |
Of | -0.097 |
Token | to |
Token ID | 284 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
forgot | +0.008 |
waited | +0.007 |
stayed | +0.007 |
remembered | +0.007 |
punished | +0.007 |
Neg logit contributions | |
Today | -0.007 |
Nice | -0.006 |
This | -0.006 |
These | -0.005 |
Of | -0.005 |
Token | hang |
Token ID | 8181 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
forgot | +0.112 |
remembered | +0.096 |
punished | +0.089 |
managed | +0.087 |
ils | +0.087 |
Neg logit contributions | |
Today | -0.131 |
This | -0.108 |
On | -0.098 |
Of | -0.096 |
Nice | -0.096 |
Token | it |
Token ID | 340 |
Feature activation | -5.83e-03 |
Pos logit contributions | |
Today | +0.159 |
Nice | +0.138 |
This | +0.133 |
These | +0.132 |
oky | +0.127 |
Neg logit contributions | |
forgot | -0.079 |
put | -0.075 |
stayed | -0.070 |
waited | -0.069 |
never | -0.068 |
Token | . |
Token ID | 13 |
Feature activation | +6.34e-02 |
Pos logit contributions | |
forgot | +0.011 |
put | +0.011 |
stayed | +0.010 |
waited | +0.010 |
tried | +0.010 |
Neg logit contributions | |
Today | -0.013 |
Nice | -0.011 |
This | -0.011 |
These | -0.011 |
oky | -0.010 |
Token | But |
Token ID | 887 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
Today | +0.094 |
Nice | +0.075 |
opl | +0.068 |
anes | +0.066 |
oky | +0.064 |
Neg logit contributions | |
forgot | -0.163 |
waited | -0.158 |
put | -0.156 |
stayed | -0.150 |
hid | -0.149 |
Token | the |
Token ID | 262 |
Feature activation | -6.84e-03 |
Pos logit contributions | |
Today | +0.023 |
This | +0.020 |
Nice | +0.019 |
Of | +0.017 |
These | +0.017 |
Neg logit contributions | |
forgot | -0.026 |
punished | -0.022 |
remembered | -0.022 |
cleaned | -0.022 |
dug | -0.022 |
Token | wall |
Token ID | 3355 |
Feature activation | -6.82e-03 |
Pos logit contributions | |
forgot | +0.012 |
waited | +0.011 |
stayed | +0.011 |
remembered | +0.011 |
put | +0.011 |
Neg logit contributions | |
Today | -0.017 |
Nice | -0.015 |
This | -0.014 |
These | -0.013 |
Of | -0.013 |
Token | had |
Token ID | 550 |
Feature activation | -4.58e-02 |
Pos logit contributions | |
forgot | +0.010 |
remembered | +0.009 |
ts | +0.009 |
punished | +0.009 |
waited | +0.008 |
Neg logit contributions | |
Today | -0.017 |
This | -0.014 |
Nice | -0.014 |
ummy | -0.013 |
Of | -0.013 |
Token | no |
Token ID | 645 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
forgot | +0.086 |
ts | +0.075 |
punished | +0.075 |
remembered | +0.074 |
waited | +0.071 |
Neg logit contributions | |
Today | -0.092 |
This | -0.089 |
Nice | -0.079 |
These | -0.074 |
Everywhere | -0.074 |
Token | then |
Token ID | 788 |
Feature activation | +9.50e-03 |
Pos logit contributions | |
Today | +0.060 |
Nice | +0.051 |
This | +0.051 |
These | +0.047 |
Of | +0.046 |
Neg logit contributions | |
forgot | -0.038 |
waited | -0.032 |
stayed | -0.032 |
managed | -0.031 |
remembered | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
Today | +0.019 |
Nice | +0.016 |
This | +0.016 |
These | +0.014 |
Of | +0.013 |
Neg logit contributions | |
forgot | -0.021 |
waited | -0.019 |
stayed | -0.019 |
remembered | -0.019 |
put | -0.018 |
Token | something |
Token ID | 1223 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
Today | +0.071 |
Nice | +0.058 |
This | +0.058 |
These | +0.052 |
Of | +0.050 |
Neg logit contributions | |
forgot | -0.080 |
waited | -0.071 |
stayed | -0.071 |
remembered | -0.070 |
managed | -0.068 |
Token | bad |
Token ID | 2089 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
Today | +0.027 |
Nice | +0.024 |
This | +0.023 |
Of | +0.020 |
These | +0.019 |
Neg logit contributions | |
forgot | -0.030 |
waited | -0.028 |
remembered | -0.027 |
stayed | -0.026 |
punished | -0.026 |
Token | happened |
Token ID | 3022 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
Today | +0.020 |
Nice | +0.016 |
This | +0.015 |
These | +0.012 |
anes | +0.012 |
Neg logit contributions | |
forgot | -0.032 |
punished | -0.029 |
ts | -0.029 |
waited | -0.029 |
remembered | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +6.63e-02 |
Pos logit contributions | |
Today | +0.029 |
Nice | +0.024 |
This | +0.023 |
These | +0.023 |
Of | +0.021 |
Neg logit contributions | |
forgot | -0.030 |
stayed | -0.027 |
remembered | -0.027 |
waited | -0.027 |
never | -0.026 |
Token | Her |
Token ID | 2332 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
Today | +0.098 |
Nice | +0.094 |
opl | +0.089 |
umm | +0.076 |
uttering | +0.076 |
Neg logit contributions | |
put | -0.144 |
forgot | -0.144 |
tried | -0.142 |
waited | -0.142 |
hid | -0.138 |
Token | microphone |
Token ID | 21822 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
forgot | +0.050 |
waited | +0.044 |
managed | +0.044 |
stayed | +0.043 |
dug | +0.043 |
Neg logit contributions | |
Today | -0.064 |
This | -0.054 |
Nice | -0.054 |
ummy | -0.049 |
Of | -0.049 |
Token | disappeared |
Token ID | 12120 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
Today | +0.033 |
This | +0.030 |
Nice | +0.029 |
anes | +0.026 |
These | +0.026 |
Neg logit contributions | |
forgot | -0.018 |
ts | -0.018 |
waited | -0.017 |
ppa | -0.016 |
punished | -0.016 |
Token | ! |
Token ID | 0 |
Feature activation | +6.61e-02 |
Pos logit contributions | |
Today | +0.035 |
Nice | +0.029 |
This | +0.028 |
These | +0.025 |
ummy | +0.024 |
Neg logit contributions | |
forgot | -0.040 |
waited | -0.036 |
stayed | -0.036 |
remembered | -0.036 |
put | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
Today | +0.124 |
Nice | +0.118 |
opl | +0.109 |
ummy | +0.101 |
uttering | +0.100 |
Neg logit contributions | |
forgot | -0.124 |
put | -0.121 |
tried | -0.118 |
waited | -0.117 |
hid | -0.115 |
Token | the |
Token ID | 262 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
Today | +0.010 |
Nice | +0.009 |
This | +0.009 |
These | +0.008 |
ummy | +0.008 |
Neg logit contributions | |
forgot | -0.008 |
waited | -0.007 |
stayed | -0.007 |
put | -0.007 |
remembered | -0.007 |
Token | names |
Token ID | 3891 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
forgot | +0.030 |
waited | +0.027 |
stayed | +0.027 |
remembered | +0.026 |
managed | +0.025 |
Neg logit contributions | |
Today | -0.033 |
Nice | -0.027 |
This | -0.027 |
These | -0.025 |
Of | -0.024 |
Token | of |
Token ID | 286 |
Feature activation | -1.27e-04 |
Pos logit contributions | |
Today | +0.074 |
Nice | +0.062 |
This | +0.060 |
These | +0.055 |
Of | +0.053 |
Neg logit contributions | |
forgot | -0.078 |
stayed | -0.072 |
waited | -0.072 |
put | -0.071 |
remembered | -0.069 |
Token | the |
Token ID | 262 |
Feature activation | +1.16e-06 |
Pos logit contributions | |
forgot | +0.000 |
waited | +0.000 |
remembered | +0.000 |
stayed | +0.000 |
managed | +0.000 |
Neg logit contributions | |
Today | -0.000 |
This | -0.000 |
Nice | -0.000 |
These | -0.000 |
Of | -0.000 |
Token | animals |
Token ID | 4695 |
Feature activation | +2.13e-02 |
Token | . |
Token ID | 13 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
Today | +0.039 |
Nice | +0.032 |
This | +0.032 |
These | +0.028 |
Of | +0.026 |
Neg logit contributions | |
forgot | -0.052 |
waited | -0.047 |
stayed | -0.046 |
remembered | -0.046 |
put | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
uttering | +0.067 |
Today | +0.067 |
Nice | +0.065 |
ore | +0.061 |
ower | +0.061 |
Neg logit contributions | |
forgot | -0.092 |
put | -0.086 |
waited | -0.086 |
learned | -0.082 |
never | -0.082 |
Token |
|
Token ID | 198 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
Today | +0.017 |
Nice | +0.016 |
umm | +0.014 |
This | +0.014 |
owers | +0.013 |
Neg logit contributions | |
forgot | -0.025 |
put | -0.024 |
never | -0.024 |
waited | -0.023 |
learned | -0.023 |
Token | They |
Token ID | 2990 |
Feature activation | -9.27e-02 |
Pos logit contributions | |
Today | +0.036 |
Nice | +0.032 |
This | +0.030 |
These | +0.027 |
Of | +0.027 |
Neg logit contributions | |
forgot | -0.036 |
waited | -0.033 |
stayed | -0.032 |
remembered | -0.032 |
put | -0.032 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
forgot | +0.098 |
ts | +0.096 |
punished | +0.095 |
ode | +0.094 |
wounds | +0.089 |
Neg logit contributions | |
Today | -0.209 |
This | -0.186 |
On | -0.184 |
She | -0.182 |
The | -0.180 |
Token | a |
Token ID | 257 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
forgot | +0.053 |
waited | +0.047 |
stayed | +0.046 |
remembered | +0.046 |
put | +0.044 |
Neg logit contributions | |
Today | -0.063 |
Nice | -0.054 |
This | -0.053 |
These | -0.049 |
Of | -0.047 |
Token | they |
Token ID | 484 |
Feature activation | -7.13e-02 |
Pos logit contributions | |
Today | +0.088 |
Nice | +0.075 |
This | +0.074 |
These | +0.068 |
anes | +0.065 |
Neg logit contributions | |
forgot | -0.074 |
waited | -0.065 |
stayed | -0.064 |
remembered | -0.064 |
put | -0.063 |
Token | see |
Token ID | 766 |
Feature activation | -9.85e-03 |
Pos logit contributions | |
forgot | +0.123 |
ts | +0.118 |
stayed | +0.113 |
punished | +0.112 |
waited | +0.110 |
Neg logit contributions | |
Today | -0.161 |
This | -0.137 |
Nice | -0.125 |
These | -0.124 |
On | -0.123 |
Token | a |
Token ID | 257 |
Feature activation | -4.20e-03 |
Pos logit contributions | |
forgot | +0.019 |
waited | +0.016 |
stayed | +0.016 |
remembered | +0.016 |
put | +0.016 |
Neg logit contributions | |
Today | -0.024 |
Nice | -0.020 |
This | -0.020 |
These | -0.019 |
Of | -0.018 |
Token | big |
Token ID | 1263 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
forgot | +0.009 |
waited | +0.008 |
stayed | +0.008 |
remembered | +0.008 |
put | +0.007 |
Neg logit contributions | |
Today | -0.009 |
Nice | -0.008 |
This | -0.008 |
These | -0.007 |
Of | -0.007 |
Token | tent |
Token ID | 11105 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
Today | +0.052 |
Nice | +0.044 |
This | +0.044 |
These | +0.040 |
ummy | +0.039 |
Neg logit contributions | |
forgot | -0.044 |
waited | -0.039 |
stayed | -0.038 |
remembered | -0.038 |
put | -0.037 |
Token | at |
Token ID | 379 |
Feature activation | -3.60e-03 |
Pos logit contributions | |
Today | +0.088 |
Nice | +0.076 |
This | +0.072 |
These | +0.068 |
Of | +0.065 |
Neg logit contributions | |
forgot | -0.087 |
waited | -0.081 |
put | -0.080 |
stayed | -0.080 |
dug | -0.076 |
Token | the |
Token ID | 262 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
forgot | +0.007 |
stayed | +0.006 |
remembered | +0.006 |
waited | +0.006 |
managed | +0.006 |
Neg logit contributions | |
Today | -0.009 |
This | -0.007 |
Nice | -0.007 |
These | -0.007 |
Of | -0.006 |
Token | park |
Token ID | 3952 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
Today | +0.043 |
This | +0.036 |
Nice | +0.035 |
These | +0.032 |
ummy | +0.031 |
Neg logit contributions | |
forgot | -0.038 |
remembered | -0.033 |
waited | -0.033 |
stayed | -0.033 |
managed | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +6.37e-02 |
Pos logit contributions | |
Today | +0.053 |
Nice | +0.048 |
This | +0.044 |
These | +0.041 |
Of | +0.040 |
Neg logit contributions | |
forgot | -0.054 |
waited | -0.052 |
put | -0.050 |
stayed | -0.050 |
never | -0.049 |
Token | It |
Token ID | 632 |
Feature activation | -4.49e-02 |
Pos logit contributions | |
Today | +0.100 |
opl | +0.100 |
Nice | +0.093 |
anes | +0.084 |
uttering | +0.080 |
Neg logit contributions | |
forgot | -0.151 |
put | -0.146 |
waited | -0.139 |
tried | -0.138 |
dug | -0.137 |
Token | is |
Token ID | 318 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
forgot | +0.093 |
punished | +0.085 |
remembered | +0.081 |
managed | +0.080 |
waited | +0.079 |
Neg logit contributions | |
Today | -0.102 |
This | -0.085 |
Nice | -0.081 |
These | -0.074 |
On | -0.073 |
Token | he |
Token ID | 339 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
Today | +0.061 |
Nice | +0.053 |
This | +0.051 |
These | +0.048 |
Of | +0.047 |
Neg logit contributions | |
forgot | -0.053 |
waited | -0.048 |
stayed | -0.047 |
remembered | -0.046 |
put | -0.046 |
Token | could |
Token ID | 714 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
forgot | +0.077 |
ts | +0.074 |
waited | +0.064 |
stayed | +0.062 |
remembered | +0.062 |
Neg logit contributions | |
Today | -0.184 |
This | -0.162 |
On | -0.149 |
Nice | -0.148 |
These | -0.143 |
Token | play |
Token ID | 711 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
forgot | +0.067 |
remembered | +0.059 |
waited | +0.057 |
stayed | +0.055 |
managed | +0.055 |
Neg logit contributions | |
Today | -0.103 |
This | -0.089 |
Nice | -0.081 |
These | -0.078 |
On | -0.078 |
Token | with |
Token ID | 351 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
Today | +0.043 |
Nice | +0.035 |
This | +0.035 |
These | +0.031 |
Of | +0.029 |
Neg logit contributions | |
forgot | -0.053 |
waited | -0.048 |
stayed | -0.047 |
remembered | -0.047 |
put | -0.045 |
Token | his |
Token ID | 465 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
Today | +0.029 |
This | +0.025 |
Nice | +0.024 |
These | +0.022 |
ummy | +0.022 |
Neg logit contributions | |
forgot | -0.031 |
waited | -0.028 |
remembered | -0.028 |
stayed | -0.028 |
managed | -0.026 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
forgot | +0.033 |
managed | +0.029 |
waited | +0.029 |
stayed | +0.028 |
remembered | +0.028 |
Neg logit contributions | |
Today | -0.045 |
Nice | -0.037 |
This | -0.037 |
ummy | -0.035 |
These | -0.034 |
Token | again |
Token ID | 757 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
Today | +0.021 |
This | +0.017 |
Nice | +0.017 |
These | +0.015 |
ummy | +0.014 |
Neg logit contributions | |
forgot | -0.027 |
waited | -0.025 |
stayed | -0.024 |
remembered | -0.024 |
dug | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +5.06e-02 |
Pos logit contributions | |
Today | +0.033 |
Nice | +0.026 |
This | +0.026 |
These | +0.023 |
ummy | +0.022 |
Neg logit contributions | |
forgot | -0.045 |
waited | -0.041 |
stayed | -0.041 |
remembered | -0.040 |
put | -0.039 |
Token | So |
Token ID | 1406 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
Today | +0.084 |
Nice | +0.071 |
uttering | +0.069 |
oky | +0.064 |
owers | +0.063 |
Neg logit contributions | |
forgot | -0.123 |
waited | -0.110 |
remembered | -0.110 |
put | -0.108 |
never | -0.108 |
Token | , |
Token ID | 11 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
Today | +0.040 |
This | +0.033 |
Nice | +0.031 |
Of | +0.027 |
These | +0.027 |
Neg logit contributions | |
forgot | -0.057 |
waited | -0.053 |
dug | -0.053 |
stayed | -0.052 |
ts | -0.051 |
Token | he |
Token ID | 339 |
Feature activation | -9.82e-02 |
Pos logit contributions | |
Today | +0.058 |
Nice | +0.048 |
This | +0.048 |
These | +0.043 |
Of | +0.041 |
Neg logit contributions | |
forgot | -0.066 |
waited | -0.060 |
stayed | -0.059 |
remembered | -0.059 |
put | -0.057 |
Token | age |
Token ID | 496 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
Today | +0.033 |
Nice | +0.027 |
This | +0.027 |
These | +0.024 |
ummy | +0.023 |
Neg logit contributions | |
forgot | -0.035 |
waited | -0.031 |
stayed | -0.031 |
remembered | -0.031 |
put | -0.030 |
Token | for |
Token ID | 329 |
Feature activation | -6.20e-04 |
Pos logit contributions | |
Today | +0.049 |
Nice | +0.041 |
This | +0.041 |
These | +0.036 |
ummy | +0.035 |
Neg logit contributions | |
forgot | -0.056 |
waited | -0.050 |
remembered | -0.050 |
stayed | -0.049 |
put | -0.047 |
Token | the |
Token ID | 262 |
Feature activation | +5.31e-03 |
Pos logit contributions | |
forgot | +0.001 |
remembered | +0.001 |
waited | +0.001 |
managed | +0.001 |
stayed | +0.001 |
Neg logit contributions | |
Today | -0.001 |
This | -0.001 |
Nice | -0.001 |
These | -0.001 |
ummy | -0.001 |
Token | red |
Token ID | 2266 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
Today | +0.012 |
Nice | +0.010 |
This | +0.010 |
These | +0.009 |
ummy | +0.009 |
Neg logit contributions | |
forgot | -0.011 |
waited | -0.009 |
remembered | -0.009 |
stayed | -0.009 |
managed | -0.009 |
Token | bird |
Token ID | 6512 |
Feature activation | +1.30e-04 |
Pos logit contributions | |
Today | +0.047 |
Nice | +0.041 |
This | +0.040 |
These | +0.037 |
Of | +0.036 |
Neg logit contributions | |
forgot | -0.032 |
waited | -0.028 |
stayed | -0.028 |
remembered | -0.028 |
put | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | -5.96e-04 |
Pos logit contributions | |
Today | +0.000 |
Nice | +0.000 |
This | +0.000 |
These | +0.000 |
Of | +0.000 |
Neg logit contributions | |
forgot | -0.000 |
waited | -0.000 |
stayed | -0.000 |
remembered | -0.000 |
put | -0.000 |
Token | filled |
Token ID | 5901 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
forgot | +0.001 |
waited | +0.001 |
punished | +0.001 |
dug | +0.001 |
cleaned | +0.001 |
Neg logit contributions | |
Today | -0.001 |
Nice | -0.001 |
This | -0.001 |
Of | -0.001 |
These | -0.001 |
Token | it |
Token ID | 340 |
Feature activation | -5.71e-03 |
Pos logit contributions | |
Today | +0.045 |
Nice | +0.039 |
This | +0.039 |
These | +0.036 |
Of | +0.034 |
Neg logit contributions | |
forgot | -0.036 |
waited | -0.031 |
stayed | -0.031 |
remembered | -0.031 |
put | -0.030 |
Token | with |
Token ID | 351 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
forgot | +0.013 |
waited | +0.012 |
stayed | +0.012 |
remembered | +0.012 |
put | +0.012 |
Neg logit contributions | |
Today | -0.011 |
Nice | -0.009 |
This | -0.009 |
These | -0.008 |
Of | -0.008 |
Token | plenty |
Token ID | 6088 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
forgot | +0.024 |
waited | +0.020 |
remembered | +0.020 |
stayed | +0.020 |
managed | +0.019 |
Neg logit contributions | |
Today | -0.025 |
This | -0.022 |
Nice | -0.021 |
These | -0.019 |
ummy | -0.019 |
Token | of |
Token ID | 286 |
Feature activation | +3.20e-03 |
Pos logit contributions | |
Today | +0.054 |
Nice | +0.044 |
This | +0.043 |
These | +0.038 |
Of | +0.036 |
Neg logit contributions | |
forgot | -0.079 |
waited | -0.071 |
stayed | -0.071 |
remembered | -0.070 |
put | -0.069 |
Token | with |
Token ID | 351 |
Feature activation | -5.23e-03 |
Pos logit contributions | |
Today | +0.065 |
Nice | +0.058 |
This | +0.053 |
These | +0.050 |
Everywhere | +0.047 |
Neg logit contributions | |
forgot | -0.056 |
put | -0.053 |
waited | -0.053 |
stayed | -0.050 |
remembered | -0.049 |
Token | her |
Token ID | 607 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
forgot | +0.011 |
stayed | +0.009 |
remembered | +0.009 |
waited | +0.009 |
managed | +0.009 |
Neg logit contributions | |
Today | -0.012 |
This | -0.010 |
Nice | -0.010 |
These | -0.009 |
Of | -0.009 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
forgot | +0.039 |
waited | +0.034 |
stayed | +0.033 |
remembered | +0.033 |
put | +0.032 |
Neg logit contributions | |
Today | -0.072 |
Nice | -0.064 |
This | -0.062 |
These | -0.058 |
anes | -0.056 |
Token | and |
Token ID | 290 |
Feature activation | -6.75e-03 |
Pos logit contributions | |
forgot | +0.031 |
waited | +0.027 |
put | +0.027 |
stayed | +0.027 |
remembered | +0.026 |
Neg logit contributions | |
Today | -0.052 |
Nice | -0.047 |
This | -0.045 |
These | -0.042 |
Of | -0.041 |
Token | was |
Token ID | 373 |
Feature activation | -4.79e-02 |
Pos logit contributions | |
forgot | +0.012 |
ts | +0.012 |
ode | +0.011 |
wed | +0.011 |
managed | +0.011 |
Neg logit contributions | |
Today | -0.013 |
This | -0.012 |
Of | -0.011 |
She | -0.010 |
These | -0.010 |
Token | excited |
Token ID | 6568 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
forgot | +0.096 |
waited | +0.084 |
stayed | +0.084 |
remembered | +0.083 |
put | +0.080 |
Neg logit contributions | |
Today | -0.109 |
Nice | -0.092 |
This | -0.092 |
These | -0.084 |
Of | -0.080 |
Token | to |
Token ID | 284 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
Today | +0.027 |
Nice | +0.024 |
This | +0.023 |
These | +0.022 |
anes | +0.022 |
Neg logit contributions | |
forgot | -0.020 |
put | -0.018 |
waited | -0.018 |
stayed | -0.018 |
never | -0.017 |
Token | see |
Token ID | 766 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
forgot | +0.045 |
remembered | +0.038 |
stayed | +0.038 |
waited | +0.037 |
managed | +0.036 |
Neg logit contributions | |
Today | -0.061 |
This | -0.054 |
Nice | -0.051 |
These | -0.049 |
On | -0.046 |
Token | all |
Token ID | 477 |
Feature activation | +2.01e-03 |
Pos logit contributions | |
Today | +0.056 |
Nice | +0.049 |
This | +0.048 |
These | +0.045 |
Of | +0.043 |
Neg logit contributions | |
forgot | -0.033 |
waited | -0.029 |
stayed | -0.029 |
put | -0.028 |
remembered | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | +4.42e-04 |
Pos logit contributions | |
Today | +0.005 |
Nice | +0.005 |
This | +0.004 |
These | +0.004 |
Right | +0.004 |
Neg logit contributions | |
forgot | -0.003 |
put | -0.003 |
waited | -0.003 |
stayed | -0.003 |
cleaned | -0.003 |
Token | delicious |
Token ID | 12625 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
Today | +0.001 |
Nice | +0.001 |
This | +0.001 |
These | +0.001 |
Of | +0.001 |
Neg logit contributions | |
forgot | -0.001 |
waited | -0.001 |
put | -0.001 |
stayed | -0.001 |
remembered | -0.001 |
Token | hoping |
Token ID | 7725 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
Today | +0.037 |
This | +0.031 |
Nice | +0.031 |
These | +0.026 |
On | +0.026 |
Neg logit contributions | |
forgot | -0.042 |
remembered | -0.037 |
waited | -0.037 |
stayed | -0.036 |
ts | -0.036 |
Token | he |
Token ID | 339 |
Feature activation | -7.20e-02 |
Pos logit contributions | |
Today | +0.047 |
This | +0.040 |
Nice | +0.039 |
These | +0.034 |
ummy | +0.033 |
Neg logit contributions | |
forgot | -0.056 |
waited | -0.050 |
remembered | -0.050 |
stayed | -0.049 |
managed | -0.048 |
Token | could |
Token ID | 714 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
forgot | +0.093 |
waited | +0.079 |
cleaned | +0.075 |
remembered | +0.074 |
punished | +0.074 |
Neg logit contributions | |
Today | -0.208 |
Nice | -0.186 |
This | -0.183 |
These | -0.167 |
On | -0.162 |
Token | find |
Token ID | 1064 |
Feature activation | -6.07e-03 |
Pos logit contributions | |
forgot | +0.056 |
remembered | +0.049 |
waited | +0.047 |
cleaned | +0.045 |
stayed | +0.045 |
Neg logit contributions | |
Today | -0.089 |
This | -0.078 |
Nice | -0.074 |
On | -0.069 |
These | -0.067 |
Token | something |
Token ID | 1223 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
forgot | +0.014 |
waited | +0.012 |
stayed | +0.012 |
remembered | +0.012 |
punished | +0.012 |
Neg logit contributions | |
Today | -0.012 |
This | -0.010 |
Nice | -0.010 |
Of | -0.008 |
These | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
Today | +0.041 |
Nice | +0.035 |
This | +0.035 |
These | +0.032 |
Of | +0.030 |
Neg logit contributions | |
forgot | -0.037 |
waited | -0.033 |
stayed | -0.032 |
remembered | -0.032 |
put | -0.031 |
Token | eat |
Token ID | 4483 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
forgot | +0.066 |
remembered | +0.058 |
waited | +0.057 |
stayed | +0.055 |
managed | +0.055 |
Neg logit contributions | |
Today | -0.090 |
This | -0.078 |
Nice | -0.074 |
These | -0.069 |
On | -0.067 |
Token | . |
Token ID | 13 |
Feature activation | +6.95e-02 |
Pos logit contributions | |
Today | +0.054 |
Nice | +0.045 |
This | +0.044 |
These | +0.042 |
Of | +0.039 |
Neg logit contributions | |
forgot | -0.059 |
stayed | -0.054 |
waited | -0.054 |
put | -0.054 |
remembered | -0.052 |
Token | After |
Token ID | 2293 |
Feature activation | -8.18e-04 |
Pos logit contributions | |
Today | +0.090 |
Nice | +0.072 |
This | +0.062 |
ummy | +0.058 |
These | +0.057 |
Neg logit contributions | |
forgot | -0.200 |
waited | -0.188 |
remembered | -0.184 |
stayed | -0.182 |
put | -0.181 |
Token | a |
Token ID | 257 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
forgot | +0.002 |
stayed | +0.002 |
waited | +0.002 |
remembered | +0.001 |
punished | +0.001 |
Neg logit contributions | |
Today | -0.002 |
This | -0.001 |
Nice | -0.001 |
These | -0.001 |
Of | -0.001 |
Token | while |
Token ID | 981 |
Feature activation | +4.44e-02 |
Pos logit contributions | |
forgot | +0.043 |
waited | +0.039 |
stayed | +0.039 |
remembered | +0.039 |
put | +0.038 |
Neg logit contributions | |
Today | -0.032 |
Nice | -0.026 |
This | -0.026 |
These | -0.023 |
Of | -0.022 |
Token | discovering |
Token ID | 21611 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
forgot | +0.077 |
waited | +0.067 |
stayed | +0.066 |
remembered | +0.065 |
dug | +0.063 |
Neg logit contributions | |
Today | -0.084 |
This | -0.074 |
Nice | -0.067 |
These | -0.064 |
anes | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
Today | +0.034 |
Nice | +0.028 |
This | +0.028 |
These | +0.025 |
Of | +0.024 |
Neg logit contributions | |
forgot | -0.034 |
waited | -0.030 |
stayed | -0.030 |
remembered | -0.030 |
put | -0.029 |
Token | Henry |
Token ID | 8616 |
Feature activation | -8.60e-02 |
Pos logit contributions | |
Today | +0.069 |
uttering | +0.061 |
Nice | +0.061 |
oky | +0.057 |
ower | +0.053 |
Neg logit contributions | |
forgot | -0.102 |
waited | -0.095 |
put | -0.094 |
never | -0.092 |
tried | -0.092 |
Token | thought |
Token ID | 1807 |
Feature activation | -8.48e-03 |
Pos logit contributions | |
forgot | +0.134 |
punished | +0.132 |
ts | +0.129 |
ode | +0.111 |
cleaned | +0.110 |
Neg logit contributions | |
Today | -0.180 |
This | -0.158 |
Nice | -0.150 |
The | -0.141 |
On | -0.137 |
Token | this |
Token ID | 428 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
forgot | +0.020 |
waited | +0.018 |
remembered | +0.018 |
stayed | +0.017 |
punished | +0.017 |
Neg logit contributions | |
Today | -0.016 |
This | -0.014 |
Nice | -0.014 |
These | -0.012 |
ummy | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | -4.47e-02 |
Pos logit contributions | |
forgot | +0.026 |
waited | +0.021 |
remembered | +0.021 |
punished | +0.021 |
stayed | +0.020 |
Neg logit contributions | |
Today | -0.040 |
This | -0.034 |
Nice | -0.034 |
Of | -0.031 |
These | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
forgot | +0.089 |
waited | +0.078 |
remembered | +0.077 |
stayed | +0.076 |
dug | +0.074 |
Neg logit contributions | |
Today | -0.101 |
This | -0.087 |
Nice | -0.087 |
These | -0.076 |
Of | -0.075 |
Token | great |
Token ID | 1049 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
forgot | +0.043 |
stayed | +0.039 |
waited | +0.039 |
ts | +0.038 |
dug | +0.038 |
Neg logit contributions | |
Today | -0.038 |
Nice | -0.031 |
This | -0.030 |
These | -0.026 |
Of | -0.025 |
Token | idea |
Token ID | 2126 |
Feature activation | +8.69e-03 |
Pos logit contributions | |
Today | +0.021 |
This | +0.016 |
Nice | +0.016 |
Of | +0.014 |
These | +0.014 |
Neg logit contributions | |
forgot | -0.024 |
stayed | -0.022 |
waited | -0.021 |
remembered | -0.021 |
ts | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
Today | +0.018 |
Nice | +0.015 |
This | +0.015 |
These | +0.013 |
Of | +0.013 |
Neg logit contributions | |
forgot | -0.019 |
waited | -0.017 |
remembered | -0.017 |
stayed | -0.017 |
put | -0.017 |
Token | so |
Token ID | 523 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
Today | +0.044 |
Nice | +0.038 |
This | +0.037 |
These | +0.033 |
Of | +0.033 |
Neg logit contributions | |
forgot | -0.036 |
waited | -0.031 |
remembered | -0.031 |
stayed | -0.031 |
punished | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | -4.33e-02 |
Pos logit contributions | |
forgot | +0.029 |
waited | +0.026 |
stayed | +0.026 |
remembered | +0.026 |
put | +0.025 |
Neg logit contributions | |
Today | -0.031 |
Nice | -0.026 |
This | -0.026 |
These | -0.024 |
Of | -0.023 |
Token | keep |
Token ID | 1394 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
forgot | +0.079 |
remembered | +0.069 |
stayed | +0.068 |
waited | +0.067 |
managed | +0.067 |
Neg logit contributions | |
Today | -0.105 |
This | -0.092 |
Nice | -0.083 |
These | -0.082 |
Of | -0.077 |
Token | our |
Token ID | 674 |
Feature activation | -7.72e-03 |
Pos logit contributions | |
Today | +0.037 |
This | +0.032 |
Nice | +0.031 |
These | +0.029 |
ummy | +0.028 |
Neg logit contributions | |
forgot | -0.032 |
stayed | -0.027 |
waited | -0.027 |
remembered | -0.027 |
managed | -0.026 |
Token | games |
Token ID | 1830 |
Feature activation | +5.57e-02 |
Pos logit contributions | |
forgot | +0.013 |
waited | +0.012 |
stayed | +0.011 |
remembered | +0.011 |
put | +0.011 |
Neg logit contributions | |
Today | -0.020 |
Nice | -0.017 |
This | -0.017 |
These | -0.016 |
Of | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +6.27e-02 |
Pos logit contributions | |
Today | +0.094 |
This | +0.073 |
Nice | +0.069 |
These | +0.061 |
ummy | +0.061 |
Neg logit contributions | |
forgot | -0.142 |
remembered | -0.130 |
waited | -0.129 |
stayed | -0.129 |
managed | -0.125 |
Token | They |
Token ID | 1119 |
Feature activation | -6.28e-02 |
Pos logit contributions | |
Today | +0.090 |
Nice | +0.080 |
uttering | +0.077 |
opl | +0.072 |
ore | +0.070 |
Neg logit contributions | |
forgot | -0.149 |
waited | -0.147 |
put | -0.146 |
stayed | -0.142 |
never | -0.139 |
Token | are |
Token ID | 389 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
forgot | +0.118 |
remembered | +0.118 |
managed | +0.108 |
dug | +0.106 |
imagined | +0.105 |
Neg logit contributions | |
Today | -0.119 |
This | -0.108 |
These | -0.099 |
ay | -0.082 |
free | -0.081 |
Token | fun |
Token ID | 1257 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
forgot | +0.067 |
remembered | +0.059 |
stayed | +0.059 |
waited | +0.059 |
managed | +0.058 |
Neg logit contributions | |
Today | -0.069 |
This | -0.060 |
Nice | -0.055 |
These | -0.051 |
Right | -0.049 |
Token | and |
Token ID | 290 |
Feature activation | +5.84e-03 |
Pos logit contributions | |
Today | +0.051 |
This | +0.041 |
Nice | +0.040 |
These | +0.037 |
ummy | +0.035 |
Neg logit contributions | |
forgot | -0.065 |
stayed | -0.058 |
remembered | -0.058 |
waited | -0.057 |
managed | -0.056 |
Token | playful |
Token ID | 34264 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
Today | +0.012 |
This | +0.011 |
Nice | +0.010 |
These | +0.009 |
Of | +0.009 |
Neg logit contributions | |
forgot | -0.011 |
remembered | -0.011 |
dug | -0.010 |
managed | -0.010 |
stayed | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +6.41e-02 |
Pos logit contributions | |
Today | +0.049 |
Nice | +0.040 |
This | +0.040 |
These | +0.036 |
Of | +0.033 |
Neg logit contributions | |
forgot | -0.061 |
waited | -0.055 |
stayed | -0.055 |
remembered | -0.055 |
put | -0.053 |
Token | e |
Token ID | 68 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
Today | +0.017 |
This | +0.015 |
Nice | +0.014 |
These | +0.013 |
ore | +0.013 |
Neg logit contributions | |
forgot | -0.013 |
remembered | -0.010 |
waited | -0.010 |
managed | -0.010 |
stayed | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
Today | +0.062 |
Nice | +0.052 |
This | +0.051 |
These | +0.046 |
Of | +0.044 |
Neg logit contributions | |
forgot | -0.065 |
waited | -0.059 |
stayed | -0.058 |
remembered | -0.058 |
put | -0.056 |
Token | Rex |
Token ID | 17853 |
Feature activation | -4.74e-03 |
Pos logit contributions | |
Today | +0.078 |
Nice | +0.064 |
This | +0.061 |
These | +0.053 |
Of | +0.051 |
Neg logit contributions | |
forgot | -0.100 |
waited | -0.090 |
remembered | -0.088 |
managed | -0.088 |
punished | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | +5.30e-02 |
Pos logit contributions | |
forgot | +0.012 |
waited | +0.011 |
remembered | +0.011 |
stayed | +0.011 |
dug | +0.011 |
Neg logit contributions | |
Today | -0.008 |
This | -0.006 |
Nice | -0.006 |
These | -0.005 |
ummy | -0.005 |
Token | See |
Token ID | 4091 |
Feature activation | -7.52e-03 |
Pos logit contributions | |
Today | +0.081 |
uttering | +0.072 |
oky | +0.065 |
anes | +0.064 |
int | +0.062 |
Neg logit contributions | |
forgot | -0.125 |
stayed | -0.117 |
waited | -0.113 |
never | -0.112 |
remembered | -0.111 |
Token | you |
Token ID | 345 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
forgot | +0.014 |
waited | +0.013 |
stayed | +0.013 |
remembered | +0.012 |
put | +0.012 |
Neg logit contributions | |
Today | -0.018 |
Nice | -0.015 |
This | -0.015 |
These | -0.014 |
Of | -0.013 |
Token | tomorrow |
Token ID | 9439 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
forgot | +0.043 |
waited | +0.037 |
stayed | +0.037 |
remembered | +0.036 |
managed | +0.035 |
Neg logit contributions | |
Today | -0.061 |
Nice | -0.052 |
This | -0.051 |
These | -0.047 |
ummy | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +5.66e-02 |
Pos logit contributions | |
Today | +0.043 |
Nice | +0.036 |
This | +0.035 |
These | +0.032 |
Of | +0.031 |
Neg logit contributions | |
forgot | -0.048 |
waited | -0.044 |
stayed | -0.043 |
remembered | -0.042 |
put | -0.042 |
Token | And |
Token ID | 843 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
uttering | +0.077 |
Today | +0.076 |
ower | +0.069 |
oky | +0.065 |
anes | +0.064 |
Neg logit contributions | |
forgot | -0.132 |
stayed | -0.125 |
waited | -0.124 |
never | -0.122 |
put | -0.120 |
Token | don |
Token ID | 836 |
Feature activation | +1.79e-03 |
Pos logit contributions | |
Today | +0.019 |
Nice | +0.016 |
This | +0.016 |
Of | +0.014 |
These | +0.013 |
Neg logit contributions | |
forgot | -0.025 |
punished | -0.022 |
remembered | -0.022 |
waited | -0.022 |
managed | -0.021 |
Token | 't |
Token ID | 470 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
Today | +0.004 |
Nice | +0.003 |
oky | +0.003 |
Of | +0.003 |
uttering | +0.003 |
Neg logit contributions | |
forgot | -0.004 |
never | -0.003 |
stayed | -0.003 |
put | -0.003 |
waited | -0.003 |
Token | he |
Token ID | 339 |
Feature activation | -8.95e-02 |
Pos logit contributions | |
Today | +0.013 |
Nice | +0.011 |
This | +0.011 |
These | +0.010 |
Of | +0.010 |
Neg logit contributions | |
forgot | -0.012 |
waited | -0.011 |
stayed | -0.011 |
remembered | -0.011 |
put | -0.010 |
Token | taught |
Token ID | 7817 |
Feature activation | +7.27e-03 |
Pos logit contributions | |
forgot | +0.098 |
ts | +0.088 |
cleaned | +0.080 |
waited | +0.077 |
stayed | +0.077 |
Neg logit contributions | |
Today | -0.246 |
This | -0.217 |
Nice | -0.211 |
These | -0.193 |
On | -0.193 |
Token | everyone |
Token ID | 2506 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
Today | +0.016 |
This | +0.014 |
Nice | +0.014 |
These | +0.012 |
Of | +0.012 |
Neg logit contributions | |
forgot | -0.015 |
waited | -0.013 |
remembered | -0.013 |
stayed | -0.013 |
managed | -0.013 |
Token | that |
Token ID | 326 |
Feature activation | -6.36e-03 |
Pos logit contributions | |
forgot | +0.046 |
waited | +0.040 |
stayed | +0.039 |
remembered | +0.039 |
put | +0.037 |
Neg logit contributions | |
Today | -0.068 |
Nice | -0.060 |
This | -0.059 |
These | -0.055 |
Of | -0.052 |
Token | generosity |
Token ID | 31569 |
Feature activation | +9.17e-03 |
Pos logit contributions | |
forgot | +0.014 |
waited | +0.012 |
remembered | +0.012 |
stayed | +0.012 |
punished | +0.012 |
Neg logit contributions | |
Today | -0.013 |
Nice | -0.011 |
This | -0.011 |
These | -0.010 |
Of | -0.010 |
Token | can |
Token ID | 460 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
Today | +0.022 |
This | +0.020 |
Nice | +0.019 |
These | +0.018 |
Of | +0.017 |
Neg logit contributions | |
forgot | -0.016 |
waited | -0.014 |
remembered | -0.014 |
stayed | -0.013 |
dug | -0.013 |
Token | help |
Token ID | 1037 |
Feature activation | +1.82e-03 |
Pos logit contributions | |
forgot | +0.050 |
waited | +0.043 |
remembered | +0.042 |
stayed | +0.040 |
hid | +0.040 |
Neg logit contributions | |
Today | -0.086 |
This | -0.077 |
Nice | -0.074 |
These | -0.071 |
ummy | -0.068 |
Token | make |
Token ID | 787 |
Feature activation | +4.59e-04 |
Pos logit contributions | |
Today | +0.004 |
This | +0.004 |
Nice | +0.004 |
These | +0.003 |
ummy | +0.003 |
Neg logit contributions | |
forgot | -0.004 |
waited | -0.003 |
remembered | -0.003 |
stayed | -0.003 |
managed | -0.003 |
Token | life |
Token ID | 1204 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
Today | +0.001 |
This | +0.001 |
Nice | +0.001 |
These | +0.001 |
ummy | +0.001 |
Neg logit contributions | |
forgot | -0.001 |
waited | -0.001 |
remembered | -0.001 |
stayed | -0.001 |
managed | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
Today | +0.058 |
Nice | +0.049 |
This | +0.049 |
These | +0.044 |
Of | +0.042 |
Neg logit contributions | |
forgot | -0.051 |
waited | -0.046 |
stayed | -0.045 |
remembered | -0.045 |
put | -0.043 |
Token | bit |
Token ID | 1643 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
forgot | +0.052 |
waited | +0.048 |
stayed | +0.047 |
hid | +0.046 |
remembered | +0.045 |
Neg logit contributions | |
Today | -0.051 |
Nice | -0.043 |
This | -0.041 |
ummy | -0.037 |
These | -0.037 |
Token | gave |
Token ID | 2921 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
ode | +0.006 |
ts | +0.006 |
ppy | +0.005 |
ep | +0.005 |
dug | +0.005 |
Neg logit contributions | |
This | -0.007 |
Today | -0.007 |
Of | -0.007 |
She | -0.006 |
Nice | -0.006 |
Token | her |
Token ID | 607 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
Today | +0.032 |
This | +0.029 |
Nice | +0.027 |
Of | +0.025 |
These | +0.025 |
Neg logit contributions | |
forgot | -0.036 |
remembered | -0.031 |
waited | -0.031 |
stayed | -0.031 |
dug | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
forgot | +0.057 |
waited | +0.050 |
stayed | +0.050 |
remembered | +0.050 |
dug | +0.048 |
Neg logit contributions | |
Today | -0.055 |
This | -0.048 |
Nice | -0.045 |
Of | -0.041 |
These | -0.041 |
Token | sticker |
Token ID | 27735 |
Feature activation | +3.64e-02 |
Pos logit contributions | |
forgot | +0.038 |
waited | +0.034 |
stayed | +0.034 |
remembered | +0.033 |
ts | +0.032 |
Neg logit contributions | |
Today | -0.041 |
This | -0.034 |
Nice | -0.034 |
These | -0.030 |
Of | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +5.72e-02 |
Pos logit contributions | |
Today | +0.072 |
Nice | +0.059 |
This | +0.059 |
These | +0.052 |
Of | +0.050 |
Neg logit contributions | |
forgot | -0.084 |
waited | -0.075 |
stayed | -0.075 |
remembered | -0.075 |
put | -0.072 |
Token | Lily |
Token ID | 20037 |
Feature activation | -8.62e-02 |
Pos logit contributions | |
Today | +0.125 |
Nice | +0.113 |
uttering | +0.111 |
anes | +0.108 |
owers | +0.106 |
Neg logit contributions | |
forgot | -0.106 |
put | -0.095 |
cleaned | -0.094 |
learned | -0.091 |
waited | -0.091 |
Token | was |
Token ID | 373 |
Feature activation | -5.25e-02 |
Pos logit contributions | |
mate | +0.152 |
ts | +0.148 |
plank | +0.145 |
ode | +0.143 |
thieves | +0.140 |
Neg logit contributions | |
The | -0.126 |
Today | -0.124 |
This | -0.122 |
| -0.111 |
With | -0.109 |
Token | so |
Token ID | 523 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
forgot | +0.110 |
waited | +0.098 |
stayed | +0.096 |
dug | +0.095 |
remembered | +0.095 |
Neg logit contributions | |
Today | -0.110 |
This | -0.093 |
Nice | -0.091 |
These | -0.079 |
Of | -0.078 |
Token | happy |
Token ID | 3772 |
Feature activation | +9.84e-03 |
Pos logit contributions | |
forgot | +0.055 |
waited | +0.049 |
stayed | +0.049 |
remembered | +0.048 |
put | +0.047 |
Neg logit contributions | |
Today | -0.052 |
This | -0.043 |
Nice | -0.043 |
These | -0.039 |
Of | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | -4.97e-03 |
Pos logit contributions | |
Today | +0.021 |
Nice | +0.018 |
This | +0.018 |
These | +0.016 |
ummy | +0.016 |
Neg logit contributions | |
forgot | -0.020 |
waited | -0.018 |
stayed | -0.018 |
remembered | -0.018 |
managed | -0.017 |
Token | proud |
Token ID | 6613 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
ts | +0.008 |
ode | +0.007 |
dug | +0.007 |
forgot | +0.007 |
wed | +0.007 |
Neg logit contributions | |
Today | -0.011 |
This | -0.010 |
Nice | -0.010 |
Of | -0.009 |
She | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +5.87e-02 |
Pos logit contributions | |
Today | +0.085 |
Nice | +0.074 |
This | +0.070 |
These | +0.066 |
Of | +0.064 |
Neg logit contributions | |
forgot | -0.062 |
stayed | -0.055 |
waited | -0.054 |
never | -0.053 |
put | -0.053 |
Token | He |
Token ID | 679 |
Feature activation | -9.17e-02 |
Pos logit contributions | |
Today | +0.091 |
Nice | +0.073 |
This | +0.062 |
uttering | +0.058 |
These | +0.057 |
Neg logit contributions | |
forgot | -0.157 |
waited | -0.145 |
stayed | -0.141 |
remembered | -0.141 |
put | -0.140 |
Token | said |
Token ID | 531 |
Feature activation | -2.52e-03 |
Pos logit contributions | |
ts | +0.147 |
plank | +0.129 |
ode | +0.122 |
ptions | +0.118 |
eking | +0.104 |
Neg logit contributions | |
Today | -0.151 |
He | -0.148 |
The | -0.145 |
On | -0.144 |
Every | -0.141 |
Token | that |
Token ID | 326 |
Feature activation | +7.02e-03 |
Pos logit contributions | |
forgot | +0.005 |
waited | +0.005 |
stayed | +0.005 |
remembered | +0.005 |
put | +0.004 |
Neg logit contributions | |
Today | -0.005 |
This | -0.005 |
Nice | -0.005 |
These | -0.004 |
Of | -0.004 |
Token | if |
Token ID | 611 |
Feature activation | +2.30e-03 |
Pos logit contributions | |
Today | +0.014 |
This | +0.012 |
Nice | +0.012 |
These | +0.011 |
Of | +0.011 |
Neg logit contributions | |
forgot | -0.015 |
waited | -0.013 |
remembered | -0.013 |
stayed | -0.013 |
managed | -0.013 |
Token | he |
Token ID | 339 |
Feature activation | -8.47e-02 |
Pos logit contributions | |
Today | +0.004 |
This | +0.003 |
Nice | +0.003 |
Of | +0.003 |
These | +0.003 |
Neg logit contributions | |
forgot | -0.006 |
waited | -0.005 |
managed | -0.005 |
remembered | -0.005 |
dug | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | -5.83e-02 |
Pos logit contributions | |
forgot | +0.089 |
ts | +0.088 |
scar | +0.083 |
waited | +0.073 |
dug | +0.072 |
Neg logit contributions | |
Today | -0.215 |
This | -0.199 |
Nice | -0.186 |
ore | -0.182 |
These | -0.177 |
Token | careful |
Token ID | 8161 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
forgot | +0.109 |
waited | +0.098 |
stayed | +0.093 |
dug | +0.092 |
remembered | +0.091 |
Neg logit contributions | |
Today | -0.125 |
This | -0.109 |
Nice | -0.104 |
These | -0.094 |
Of | -0.091 |
Token | and |
Token ID | 290 |
Feature activation | -6.52e-03 |
Pos logit contributions | |
Today | +0.077 |
Nice | +0.066 |
This | +0.064 |
These | +0.060 |
Of | +0.057 |
Neg logit contributions | |
forgot | -0.063 |
stayed | -0.056 |
waited | -0.055 |
remembered | -0.055 |
put | -0.054 |
Token | respectful |
Token ID | 25923 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
forgot | +0.011 |
waited | +0.009 |
imagined | +0.009 |
pretended | +0.009 |
dug | +0.009 |
Neg logit contributions | |
Today | -0.014 |
This | -0.013 |
Nice | -0.012 |
Of | -0.011 |
These | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
Today | +0.066 |
Nice | +0.055 |
This | +0.055 |
These | +0.049 |
Of | +0.047 |
Neg logit contributions | |
forgot | -0.071 |
waited | -0.064 |
remembered | -0.063 |
stayed | -0.062 |
dug | -0.060 |
Token | it |
Token ID | 340 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
Today | +0.012 |
This | +0.010 |
Nice | +0.009 |
These | +0.009 |
Of | +0.009 |
Neg logit contributions | |
forgot | -0.012 |
punished | -0.010 |
waited | -0.010 |
stayed | -0.010 |
remembered | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
forgot | +0.038 |
ts | +0.035 |
remembered | +0.034 |
punished | +0.034 |
waited | +0.034 |
Neg logit contributions | |
Today | -0.053 |
This | -0.047 |
Nice | -0.045 |
ummy | -0.043 |
Right | -0.042 |
Token | not |
Token ID | 407 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
forgot | +0.076 |
waited | +0.065 |
stayed | +0.065 |
remembered | +0.065 |
hid | +0.062 |
Neg logit contributions | |
Today | -0.090 |
This | -0.076 |
Nice | -0.074 |
ummy | -0.068 |
oky | -0.066 |
Token | there |
Token ID | 612 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
forgot | +0.085 |
remembered | +0.074 |
stayed | +0.074 |
waited | +0.074 |
dug | +0.070 |
Neg logit contributions | |
Today | -0.085 |
This | -0.071 |
Nice | -0.068 |
ummy | -0.063 |
oky | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | +6.13e-02 |
Pos logit contributions | |
forgot | +0.035 |
stayed | +0.032 |
waited | +0.032 |
put | +0.031 |
never | +0.031 |
Neg logit contributions | |
Today | -0.033 |
Nice | -0.027 |
This | -0.027 |
These | -0.025 |
anes | -0.024 |
Token | She |
Token ID | 1375 |
Feature activation | -8.88e-02 |
Pos logit contributions | |
Today | +0.085 |
opl | +0.080 |
Nice | +0.080 |
uttering | +0.070 |
anes | +0.067 |
Neg logit contributions | |
waited | -0.142 |
forgot | -0.140 |
put | -0.139 |
tried | -0.139 |
stayed | -0.133 |
Token | searched |
Token ID | 16499 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
ode | +0.115 |
plank | +0.114 |
forgot | +0.113 |
mate | +0.110 |
ts | +0.105 |
Neg logit contributions | |
Today | -0.169 |
She | -0.146 |
On | -0.146 |
This | -0.143 |
The | -0.143 |
Token | the |
Token ID | 262 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
forgot | +0.032 |
waited | +0.028 |
stayed | +0.028 |
remembered | +0.028 |
managed | +0.027 |
Neg logit contributions | |
Today | -0.032 |
Nice | -0.026 |
This | -0.025 |
These | -0.023 |
ummy | -0.022 |
Token | kitchen |
Token ID | 9592 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
forgot | +0.024 |
waited | +0.021 |
stayed | +0.021 |
remembered | +0.021 |
put | +0.020 |
Neg logit contributions | |
Today | -0.028 |
Nice | -0.024 |
This | -0.024 |
These | -0.022 |
ummy | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
Today | +0.052 |
This | +0.043 |
Nice | +0.039 |
ummy | +0.039 |
These | +0.037 |
Neg logit contributions | |
forgot | -0.060 |
remembered | -0.054 |
stayed | -0.053 |
waited | -0.051 |
punished | -0.051 |
Token | looked |
Token ID | 3114 |
Feature activation | +6.91e-03 |
Pos logit contributions | |
forgot | +0.018 |
punished | +0.014 |
stayed | +0.014 |
remembered | +0.014 |
managed | +0.013 |
Neg logit contributions | |
Today | -0.038 |
This | -0.035 |
Nice | -0.033 |
Right | -0.032 |
Of | -0.032 |
Token | Ruby |
Token ID | 10888 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
Today | +0.031 |
This | +0.026 |
Nice | +0.025 |
These | +0.023 |
Of | +0.023 |
Neg logit contributions | |
forgot | -0.029 |
stayed | -0.026 |
waited | -0.025 |
remembered | -0.025 |
managed | -0.024 |
Token | from |
Token ID | 422 |
Feature activation | +2.44e-03 |
Pos logit contributions | |
Today | +0.043 |
This | +0.038 |
Nice | +0.037 |
These | +0.034 |
Of | +0.033 |
Neg logit contributions | |
forgot | -0.026 |
waited | -0.022 |
stayed | -0.022 |
remembered | -0.022 |
managed | -0.020 |
Token | her |
Token ID | 607 |
Feature activation | -5.17e-03 |
Pos logit contributions | |
Today | +0.006 |
Nice | +0.005 |
This | +0.005 |
These | +0.004 |
Of | +0.004 |
Neg logit contributions | |
forgot | -0.005 |
waited | -0.004 |
stayed | -0.004 |
remembered | -0.004 |
put | -0.004 |
Token | hands |
Token ID | 2832 |
Feature activation | +6.90e-02 |
Pos logit contributions | |
forgot | +0.010 |
waited | +0.008 |
managed | +0.008 |
remembered | +0.008 |
stayed | +0.008 |
Neg logit contributions | |
Today | -0.013 |
This | -0.011 |
Nice | -0.010 |
ummy | -0.010 |
These | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +6.36e-02 |
Pos logit contributions | |
Today | +0.156 |
Nice | +0.137 |
This | +0.130 |
These | +0.124 |
Of | +0.118 |
Neg logit contributions | |
forgot | -0.135 |
waited | -0.122 |
stayed | -0.121 |
put | -0.121 |
remembered | -0.118 |
Token | She |
Token ID | 1375 |
Feature activation | -9.18e-02 |
Pos logit contributions | |
Today | +0.088 |
opl | +0.068 |
anes | +0.067 |
Nice | +0.066 |
uttering | +0.062 |
Neg logit contributions | |
forgot | -0.170 |
waited | -0.157 |
hid | -0.157 |
put | -0.156 |
tried | -0.156 |
Token | said |
Token ID | 531 |
Feature activation | +3.43e-03 |
Pos logit contributions | |
ode | +0.165 |
permission | +0.141 |
mate | +0.140 |
least | +0.136 |
ptions | +0.132 |
Neg logit contributions | |
She | -0.118 |
The | -0.110 |
| -0.110 |
A | -0.109 |
He | -0.108 |
Token | , |
Token ID | 11 |
Feature activation | +7.23e-03 |
Pos logit contributions | |
Today | +0.008 |
Nice | +0.007 |
This | +0.006 |
These | +0.006 |
oky | +0.006 |
Neg logit contributions | |
forgot | -0.007 |
remembered | -0.006 |
stayed | -0.006 |
waited | -0.006 |
put | -0.006 |
Token | " |
Token ID | 366 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
Today | +0.013 |
Nice | +0.010 |
oky | +0.010 |
This | +0.009 |
ummy | +0.009 |
Neg logit contributions | |
forgot | -0.018 |
waited | -0.017 |
remembered | -0.017 |
stayed | -0.017 |
put | -0.016 |
Token | No |
Token ID | 2949 |
Feature activation | -1.51e-03 |
Pos logit contributions | |
Today | +0.025 |
Nice | +0.020 |
This | +0.020 |
These | +0.018 |
Of | +0.017 |
Neg logit contributions | |
forgot | -0.033 |
waited | -0.030 |
stayed | -0.029 |
remembered | -0.029 |
put | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
forgot | +0.004 |
waited | +0.004 |
stayed | +0.004 |
managed | +0.003 |
dug | +0.003 |
Neg logit contributions | |
Today | -0.003 |
Nice | -0.002 |
This | -0.002 |
These | -0.002 |
ummy | -0.002 |
Token | Tom |
Token ID | 13787 |
Feature activation | -7.70e-02 |
Pos logit contributions | |
Today | +0.102 |
Nice | +0.093 |
This | +0.086 |
These | +0.080 |
Of | +0.080 |
Neg logit contributions | |
forgot | -0.080 |
waited | -0.071 |
remembered | -0.071 |
never | -0.071 |
put | -0.070 |
Token | and |
Token ID | 290 |
Feature activation | -7.23e-03 |
Pos logit contributions | |
ts | +0.141 |
forgot | +0.130 |
ils | +0.128 |
punished | +0.121 |
inations | +0.117 |
Neg logit contributions | |
Today | -0.127 |
She | -0.115 |
The | -0.114 |
This | -0.111 |
Nice | -0.109 |
Token | Lily |
Token ID | 20037 |
Feature activation | -7.36e-02 |
Pos logit contributions | |
forgot | +0.016 |
waited | +0.015 |
stayed | +0.014 |
remembered | +0.014 |
managed | +0.014 |
Neg logit contributions | |
Today | -0.015 |
This | -0.012 |
Nice | -0.012 |
These | -0.011 |
Of | -0.011 |
Token | laughed |
Token ID | 13818 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
forgot | +0.092 |
ts | +0.092 |
ils | +0.086 |
inations | +0.086 |
icians | +0.086 |
Neg logit contributions | |
Today | -0.130 |
She | -0.127 |
The | -0.125 |
On | -0.120 |
This | -0.120 |
Token | . |
Token ID | 13 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
Today | +0.072 |
These | +0.067 |
Nice | +0.067 |
This | +0.066 |
anes | +0.063 |
Neg logit contributions | |
forgot | -0.028 |
put | -0.027 |
remembered | -0.027 |
stayed | -0.026 |
learned | -0.026 |
Token | They |
Token ID | 1119 |
Feature activation | -8.67e-02 |
Pos logit contributions | |
Today | +0.092 |
ore | +0.090 |
Nice | +0.086 |
uttering | +0.085 |
ummy | +0.083 |
Neg logit contributions | |
forgot | -0.111 |
waited | -0.106 |
put | -0.103 |
learned | -0.098 |
pretended | -0.098 |
Token | played |
Token ID | 2826 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
ode | +0.126 |
plank | +0.116 |
ts | +0.116 |
mistake | +0.107 |
icians | +0.106 |
Neg logit contributions | |
She | -0.153 |
The | -0.148 |
Today | -0.145 |
On | -0.142 |
| -0.135 |
Token | with |
Token ID | 351 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
Today | +0.032 |
Nice | +0.026 |
This | +0.026 |
These | +0.023 |
Of | +0.022 |
Neg logit contributions | |
forgot | -0.041 |
waited | -0.036 |
stayed | -0.036 |
remembered | -0.036 |
managed | -0.035 |
Token | their |
Token ID | 511 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
Today | +0.040 |
This | +0.034 |
Nice | +0.033 |
These | +0.030 |
Of | +0.029 |
Neg logit contributions | |
forgot | -0.046 |
waited | -0.040 |
remembered | -0.040 |
managed | -0.039 |
stayed | -0.039 |
Token | toys |
Token ID | 14958 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
forgot | +0.042 |
managed | +0.037 |
waited | +0.036 |
dug | +0.034 |
remembered | +0.034 |
Neg logit contributions | |
Today | -0.063 |
Nice | -0.055 |
This | -0.053 |
ummy | -0.051 |
These | -0.051 |
Token | in |
Token ID | 287 |
Feature activation | +8.18e-03 |
Pos logit contributions | |
Today | +0.054 |
This | +0.043 |
Nice | +0.042 |
These | +0.038 |
ummy | +0.037 |
Neg logit contributions | |
forgot | -0.072 |
remembered | -0.064 |
waited | -0.063 |
punished | -0.062 |
stayed | -0.062 |