TOP ACTIVATIONS
MAX = 0.110

<|endoftext|> Anna and Ben are brother and sister . They like
<|endoftext|> Tim and Sue are brother and sister . They like
Jack and Lily hugged their son and said , " We
<|endoftext|> Tom and Lily are brother and sister . They like
L ily and Ben are brother and sister . They like
Lisa hugged her son . She was angry and
<|endoftext|> Tom and Lily are brother and sister . They like
L ily and Ben are brother and sister . They like
<|endoftext|> Tim and Mia are brother and sister . They live
S ara and Tom are brother and sister . They like
<|endoftext|> Tom and Lily are brother and sister . They like
<|endoftext|> Tom and Lily are brother and sister . They like
<|endoftext|> Tom and Lily are brother and sister . They like
S ara and Ben are brother and sister . They are
decided to take his little grandson to the hardware store .
<|endoftext|> Tom and Lily were brother and sister . They liked
<|endoftext|> Tom and Lily were brother and sister . They liked
<|endoftext|> Tom and Anna are brother and sister . They like
Her mom my was heart broken and missed her little girl
<|endoftext|> Tom and Lily were brother and sister . They lived

MIN ACTIVATIONS
MIN = -0.172

did something special . On Wed nes days she liked to
river . When Sil via arrived at the river
chose both vendors . The frag rant flowers for the sweet
another wand . " A br ac ad ab ra !"
. They see many sh rim ps and fish and crabs
the air . " A br ac ad ab ra !"
and said , " A br ac ad ab ra !"
and said , " A br ac ad ab ra !
and said , " A br ac ad ab ra !
there were other long sh rim ps in the ocean .
and said , " A br ac ad ab ra !
She said , " A br ac ad ab ra !"
around and said " A br ac ad ab ra !"
it around . " A br ac ad ab ra !"
there was a girl named Sil via . She was 3
and said , " A br ac ad ab ra ,
Pete had ever seen sh rim ps and his dad was
and said , " A br ac ad ab ra !"
stove - two more sh rim ps ! His dad had
before . " Sil v ie ," he called

INTERVAL 0.039 - 0.110
CONTAINS 7.288%

day , he went to the park to play with his
was so excited that he decided to join them and start
. Ben and Tom are scared . They want to stop
time . They learned their lesson . They were happy and
into a wonderful adventure ! <|endoftext|> One day , Joe went

INTERVAL -0.031 - 0.039
CONTAINS 81.438%

the little bird filled his wings with tw igs , the
their broken blocks . They felt sorry and scared .
opened it and saw inside it were lots of photos .
replied . L ily smelled the pepper and made
showed that the rock was very heavy . Daisy was amazed

INTERVAL -0.102 - -0.031
CONTAINS 11.230%

. I wish I could be as strong as you ."
. Lily was so excited because she loved going down the
was bright red and it made a loud noise . He
, " I 'm glad you had fun , but be
Finally , the ear had counted all the way to 10

INTERVAL -0.172 - -0.102
CONTAINS 0.044%

more cartoons . L ily was amazed and said
exciting ! P olly 's mom my let
groceries . P ete took his groceries home
place where she could find tast ier leaves to eat .
Her mom had a black pr une in a bowl on
Token<|endoftext|>
Token ID50256
Feature activation+7.33e-02

Pos logit contributions
 theirs+0.029
ash+0.029
 yours+0.027
uries+0.027
uggets+0.027
Neg logit contributions
 sky-0.022
 hawk-0.021
 poster-0.021
-0.021
 voice-0.021
TokenAnna
Token ID31160
Feature activation+2.02e-02

Pos logit contributions
 voice+0.067
 hawk+0.063
 poster+0.060
 sky+0.059
 devastated+0.055
Neg logit contributions
ash-0.163
 theirs-0.144
aghetti-0.143
 yours-0.143
 organize-0.142
Token and
Token ID290
Feature activation+3.81e-02

Pos logit contributions
 sky+0.024
 voice+0.021
+0.021
't+0.019
 poster+0.019
Neg logit contributions
ash-0.043
 theirs-0.040
uries-0.040
 yours-0.039
iding-0.038
Token Ben
Token ID3932
Feature activation+2.46e-02

Pos logit contributions
 sky+0.068
 voice+0.064
+0.063
't+0.060
 hawk+0.060
Neg logit contributions
ash-0.057
uries-0.051
 theirs-0.051
 yours-0.050
iding-0.049
Token are
Token ID389
Feature activation+1.57e-02

Pos logit contributions
 sky+0.033
 voice+0.029
+0.029
 bird+0.027
't+0.027
Neg logit contributions
ash-0.050
iding-0.046
uries-0.046
uggets-0.045
 theirs-0.044
Token brother
Token ID3956
Feature activation+1.10e-01

Pos logit contributions
 sky+0.026
 voice+0.024
+0.024
't+0.023
 poster+0.022
Neg logit contributions
ash-0.026
 theirs-0.023
uries-0.023
 yours-0.023
wn-0.022
Token and
Token ID290
Feature activation+4.06e-02

Pos logit contributions
 sky+0.129
 voice+0.117
+0.108
 bird+0.105
 cage+0.102
Neg logit contributions
ash-0.235
uries-0.220
 theirs-0.219
wn-0.217
 yours-0.216
Token sister
Token ID6621
Feature activation+7.77e-02

Pos logit contributions
 sky+0.052
 voice+0.051
't+0.051
 bird+0.050
+0.049
Neg logit contributions
ash-0.086
iding-0.076
uries-0.075
ust-0.074
wn-0.074
Token.
Token ID13
Feature activation+1.05e-02

Pos logit contributions
 sky+0.097
 voice+0.088
+0.079
 bird+0.079
 crying+0.076
Neg logit contributions
ash-0.163
wn-0.155
uries-0.152
 theirs-0.150
 yours-0.149
Token They
Token ID1119
Feature activation-3.65e-03

Pos logit contributions
 sky+0.014
 voice+0.013
+0.013
't+0.012
 cage+0.011
Neg logit contributions
ash-0.021
wn-0.020
 yours-0.020
iding-0.020
uries-0.020
Token like
Token ID588
Feature activation-2.53e-02

Pos logit contributions
ash+0.006
iding+0.005
uggets+0.005
 kil+0.005
uries+0.005
Neg logit contributions
 sky-0.007
't-0.006
 voice-0.006
-0.006
 bird-0.006
Token<|endoftext|>
Token ID50256
Feature activation+7.38e-02

Pos logit contributions
ash+0.034
uries+0.032
 theirs+0.032
 yours+0.032
 organize+0.031
Neg logit contributions
 sky-0.019
-0.018
 hawk-0.018
 poster-0.018
 voice-0.018
TokenTim
Token ID14967
Feature activation+5.36e-03

Pos logit contributions
 voice+0.061
 hawk+0.056
 sky+0.056
 poster+0.053
+0.051
Neg logit contributions
ash-0.171
 yours-0.152
 theirs-0.151
 organize-0.150
aghetti-0.149
Token and
Token ID290
Feature activation+3.46e-02

Pos logit contributions
 sky+0.006
 voice+0.006
+0.005
't+0.005
 bird+0.005
Neg logit contributions
ash-0.011
 theirs-0.011
uries-0.011
iding-0.010
 yours-0.010
Token Sue
Token ID26089
Feature activation-1.49e-03

Pos logit contributions
 sky+0.053
 voice+0.051
 bird+0.049
't+0.047
 hawk+0.045
Neg logit contributions
ash-0.067
iding-0.061
uries-0.059
aghetti-0.057
wn-0.057
Token are
Token ID389
Feature activation+1.22e-02

Pos logit contributions
ash+0.003
iding+0.003
uries+0.003
uggets+0.003
 theirs+0.003
Neg logit contributions
 sky-0.002
 voice-0.002
 bird-0.002
-0.002
't-0.002
Token brother
Token ID3956
Feature activation+1.08e-01

Pos logit contributions
 sky+0.024
+0.023
 voice+0.023
 hawk+0.023
 poster+0.022
Neg logit contributions
ash-0.015
 theirs-0.015
 yours-0.014
asty-0.013
uries-0.013
Token and
Token ID290
Feature activation+3.99e-02

Pos logit contributions
 sky+0.117
 voice+0.103
 bird+0.094
+0.093
 cage+0.089
Neg logit contributions
ash-0.243
uries-0.232
wn-0.229
 yours-0.226
 theirs-0.225
Token sister
Token ID6621
Feature activation+7.21e-02

Pos logit contributions
't+0.052
 bird+0.051
 sky+0.051
 voice+0.051
+0.047
Neg logit contributions
ash-0.086
iding-0.078
aghetti-0.075
wn-0.075
rated-0.074
Token.
Token ID13
Feature activation+8.41e-03

Pos logit contributions
 sky+0.084
 voice+0.077
 bird+0.068
 crying+0.067
+0.066
Neg logit contributions
ash-0.157
wn-0.152
uries-0.149
 yours-0.145
iding-0.145
Token They
Token ID1119
Feature activation-6.29e-03

Pos logit contributions
 sky+0.012
+0.012
 voice+0.011
't+0.010
 bird+0.010
Neg logit contributions
ash-0.016
uries-0.015
 yours-0.015
wn-0.015
iding-0.014
Token like
Token ID588
Feature activation-3.00e-02

Pos logit contributions
ash+0.011
iding+0.009
uggets+0.009
aghetti+0.009
uries+0.009
Neg logit contributions
 sky-0.011
't-0.010
 voice-0.010
 bird-0.009
-0.009
Token Jack
Token ID3619
Feature activation+8.01e-03

Pos logit contributions
 sky+0.069
+0.065
 voice+0.064
 hawk+0.064
 poster+0.062
Neg logit contributions
ash-0.055
 theirs-0.051
uries-0.049
 yours-0.048
 organize-0.047
Token and
Token ID290
Feature activation+2.41e-02

Pos logit contributions
 sky+0.012
+0.011
 hawk+0.011
 poster+0.010
't+0.010
Neg logit contributions
ash-0.013
uries-0.012
 organize-0.012
 theirs-0.012
asting-0.012
Token Lily
Token ID20037
Feature activation+4.14e-03

Pos logit contributions
 sky+0.038
 voice+0.038
 crying+0.034
 bird+0.033
't+0.033
Neg logit contributions
ash-0.043
uries-0.040
iding-0.039
wn-0.038
 yours-0.036
Token hugged
Token ID41130
Feature activation+7.95e-03

Pos logit contributions
 sky+0.006
 voice+0.006
+0.006
 hawk+0.005
't+0.005
Neg logit contributions
ash-0.007
 theirs-0.007
uries-0.007
 yours-0.006
asty-0.006
Token their
Token ID511
Feature activation+2.64e-02

Pos logit contributions
 sky+0.014
 voice+0.013
+0.013
't+0.012
 poster+0.012
Neg logit contributions
ash-0.012
 theirs-0.011
uries-0.011
 yours-0.011
wn-0.010
Token son
Token ID3367
Feature activation+1.07e-01

Pos logit contributions
 sky+0.040
+0.037
 voice+0.037
't+0.036
 hawk+0.035
Neg logit contributions
ash-0.045
 theirs-0.043
uries-0.042
 yours-0.041
 organize-0.040
Token and
Token ID290
Feature activation+3.86e-02

Pos logit contributions
 sky+0.120
 voice+0.114
+0.103
 cage+0.099
 bird+0.099
Neg logit contributions
ash-0.229
 yours-0.216
uries-0.213
 theirs-0.211
wn-0.209
Token said
Token ID531
Feature activation+5.23e-02

Pos logit contributions
 sky+0.039
 voice+0.036
+0.033
 bird+0.032
 crying+0.031
Neg logit contributions
ash-0.091
uries-0.084
iding-0.083
wn-0.082
 yours-0.082
Token,
Token ID11
Feature activation-1.21e-03

Pos logit contributions
 sky+0.046
 voice+0.041
+0.039
't+0.036
 poster+0.034
Neg logit contributions
ash-0.125
uries-0.118
 theirs-0.118
 yours-0.115
wn-0.114
Token "
Token ID366
Feature activation-4.75e-05

Pos logit contributions
ash+0.002
 theirs+0.002
uries+0.002
 yours+0.002
asty+0.002
Neg logit contributions
 sky-0.002
 voice-0.002
-0.002
 hawk-0.001
 poster-0.001
TokenWe
Token ID1135
Feature activation-2.05e-02

Pos logit contributions
ash+0.000
 theirs+0.000
uries+0.000
 yours+0.000
iding+0.000
Neg logit contributions
 sky-0.000
 voice-0.000
-0.000
't-0.000
 hawk-0.000
Token<|endoftext|>
Token ID50256
Feature activation+7.64e-02

Pos logit contributions
ash+0.026
 theirs+0.025
uries+0.024
 yours+0.024
asty+0.023
Neg logit contributions
 sky-0.016
 voice-0.015
 hawk-0.014
 poster-0.014
-0.014
TokenTom
Token ID13787
Feature activation+2.05e-02

Pos logit contributions
 voice+0.067
 hawk+0.062
 poster+0.060
 sky+0.059
 devastated+0.055
Neg logit contributions
ash-0.171
 theirs-0.153
 yours-0.152
 organize-0.150
aghetti-0.149
Token and
Token ID290
Feature activation+3.87e-02

Pos logit contributions
 sky+0.022
 voice+0.018
 bird+0.017
't+0.017
 crying+0.016
Neg logit contributions
ash-0.046
uries-0.045
iding-0.044
 theirs-0.044
ust-0.043
Token Lily
Token ID20037
Feature activation+1.20e-02

Pos logit contributions
 sky+0.056
 voice+0.053
 bird+0.052
't+0.049
 hawk+0.047
Neg logit contributions
ash-0.079
iding-0.073
uries-0.071
aghetti-0.069
ust-0.067
Token are
Token ID389
Feature activation+1.10e-02

Pos logit contributions
 sky+0.015
 tree+0.012
 bird+0.012
 voice+0.011
+0.011
Neg logit contributions
ash-0.026
uggets-0.025
uries-0.025
iding-0.025
 theirs-0.024
Token brother
Token ID3956
Feature activation+1.07e-01

Pos logit contributions
 sky+0.020
 voice+0.019
+0.019
 hawk+0.018
 poster+0.018
Neg logit contributions
ash-0.016
 theirs-0.015
 yours-0.014
uries-0.014
asty-0.014
Token and
Token ID290
Feature activation+3.93e-02

Pos logit contributions
 sky+0.119
 voice+0.106
+0.098
 bird+0.096
 cage+0.093
Neg logit contributions
ash-0.235
uries-0.221
wn-0.218
 theirs-0.217
 yours-0.217
Token sister
Token ID6621
Feature activation+7.22e-02

Pos logit contributions
 voice+0.048
't+0.048
 sky+0.048
 bird+0.047
 crying+0.045
Neg logit contributions
ash-0.085
iding-0.077
ust-0.075
uries-0.075
wn-0.073
Token.
Token ID13
Feature activation+1.01e-02

Pos logit contributions
 sky+0.088
 voice+0.081
 bird+0.071
+0.071
 crying+0.071
Neg logit contributions
ash-0.152
wn-0.146
uries-0.143
 yours-0.140
iding-0.140
Token They
Token ID1119
Feature activation-7.15e-03

Pos logit contributions
 sky+0.014
+0.013
 voice+0.011
't+0.011
 +0.010
Neg logit contributions
ash-0.020
iding-0.019
 yours-0.019
wn-0.019
uries-0.018
Token like
Token ID588
Feature activation-2.83e-02

Pos logit contributions
ash+0.013
iding+0.012
uggets+0.011
aghetti+0.011
uries+0.011
Neg logit contributions
 sky-0.011
't-0.011
 voice-0.010
 bird-0.010
-0.009
TokenL
Token ID43
Feature activation-8.16e-02

Pos logit contributions
 voice+0.066
 hawk+0.061
 poster+0.060
 devastated+0.057
 sky+0.057
Neg logit contributions
ash-0.157
 yours-0.139
 theirs-0.139
 organize-0.137
aghetti-0.137
Tokenily
Token ID813
Feature activation+4.31e-03

Pos logit contributions
ash+0.112
 theirs+0.102
 yours+0.098
uries+0.097
asty+0.094
Neg logit contributions
 sky-0.156
-0.148
 voice-0.147
 hawk-0.140
 poster-0.139
Token and
Token ID290
Feature activation+3.04e-02

Pos logit contributions
 sky+0.005
 voice+0.003
 bird+0.003
 tree+0.003
 cage+0.003
Neg logit contributions
ash-0.010
uries-0.010
 theirs-0.010
iding-0.010
ust-0.010
Token Ben
Token ID3932
Feature activation+1.46e-02

Pos logit contributions
 sky+0.047
 voice+0.045
't+0.042
+0.042
 bird+0.042
Neg logit contributions
ash-0.056
uries-0.050
iding-0.050
wn-0.048
aghetti-0.048
Token are
Token ID389
Feature activation+1.12e-02

Pos logit contributions
 sky+0.017
 bird+0.014
 tree+0.014
 voice+0.014
+0.013
Neg logit contributions
ash-0.033
uggets-0.032
iding-0.031
uries-0.030
ust-0.030
Token brother
Token ID3956
Feature activation+1.06e-01

Pos logit contributions
 sky+0.019
 voice+0.018
+0.017
 hawk+0.016
't+0.016
Neg logit contributions
ash-0.018
 theirs-0.017
uries-0.016
 yours-0.016
asty-0.016
Token and
Token ID290
Feature activation+3.81e-02

Pos logit contributions
 sky+0.108
 voice+0.096
 bird+0.088
+0.084
 cage+0.083
Neg logit contributions
ash-0.243
uries-0.232
wn-0.230
 yours-0.227
 theirs-0.225
Token sister
Token ID6621
Feature activation+7.26e-02

Pos logit contributions
 voice+0.048
 bird+0.047
 sky+0.047
't+0.047
+0.044
Neg logit contributions
ash-0.082
iding-0.075
uries-0.073
ust-0.071
wn-0.070
Token.
Token ID13
Feature activation+1.21e-02

Pos logit contributions
 sky+0.083
 voice+0.076
 bird+0.067
 crying+0.065
+0.064
Neg logit contributions
ash-0.158
wn-0.154
uries-0.151
 yours-0.147
iding-0.147
Token They
Token ID1119
Feature activation-4.55e-03

Pos logit contributions
 sky+0.015
+0.014
 voice+0.014
't+0.012
 crying+0.011
Neg logit contributions
ash-0.025
iding-0.024
 yours-0.024
wn-0.024
uries-0.024
Token like
Token ID588
Feature activation-2.71e-02

Pos logit contributions
ash+0.007
iding+0.006
uggets+0.006
 kil+0.006
uries+0.006
Neg logit contributions
 sky-0.008
't-0.008
 voice-0.008
-0.007
 bird-0.007
Token
Token ID198
Feature activation-5.82e-03

Pos logit contributions
 theirs+0.006
 organize+0.006
ash+0.006
 Jill+0.006
uries+0.006
Neg logit contributions
-0.004
 sky-0.004
 hawk-0.004
 cage-0.004
 poster-0.004
Token
Token ID198
Feature activation-8.42e-03

Pos logit contributions
ash+0.010
 organize+0.010
 theirs+0.010
 yours+0.010
iding+0.010
Neg logit contributions
 sky-0.008
 hawk-0.007
-0.007
 poster-0.007
 cage-0.006
TokenLisa
Token ID44203
Feature activation+1.39e-02

Pos logit contributions
ash+0.013
 theirs+0.012
 organize+0.012
uries+0.012
 yours+0.012
Neg logit contributions
 sky-0.014
-0.013
 hawk-0.012
 voice-0.012
 cage-0.012
Token hugged
Token ID41130
Feature activation+6.83e-03

Pos logit contributions
+0.023
 sky+0.022
 hawk+0.022
 poster+0.021
't+0.020
Neg logit contributions
ash-0.019
 organize-0.018
 remember-0.018
ackers-0.017
 like-0.017
Token her
Token ID607
Feature activation+1.67e-02

Pos logit contributions
 sky+0.013
+0.013
 hawk+0.012
 voice+0.012
 cage+0.012
Neg logit contributions
ash-0.009
 theirs-0.008
 yours-0.008
asty-0.008
 organize-0.008
Token son
Token ID3367
Feature activation+1.05e-01

Pos logit contributions
 sky+0.025
 voice+0.023
+0.023
't+0.022
 hawk+0.021
Neg logit contributions
ash-0.030
 theirs-0.028
uries-0.027
 yours-0.027
asty-0.026
Token.
Token ID13
Feature activation-6.04e-03

Pos logit contributions
 sky+0.151
 voice+0.141
+0.136
't+0.128
 poster+0.127
Neg logit contributions
ash-0.193
 theirs-0.180
uries-0.178
 yours-0.176
wn-0.171
Token She
Token ID1375
Feature activation+8.59e-03

Pos logit contributions
ash+0.011
 theirs+0.011
 yours+0.010
uries+0.010
 organize+0.010
Neg logit contributions
 sky-0.008
-0.007
 hawk-0.007
 voice-0.007
 poster-0.007
Token was
Token ID373
Feature activation+1.20e-02

Pos logit contributions
 sky+0.013
+0.012
 voice+0.012
 hawk+0.011
 poster+0.011
Neg logit contributions
ash-0.014
 theirs-0.013
 organize-0.013
uries-0.013
asty-0.013
Token angry
Token ID7954
Feature activation+5.28e-02

Pos logit contributions
 sky+0.017
+0.016
 poster+0.015
 voice+0.015
 hawk+0.014
Neg logit contributions
ash-0.022
 theirs-0.021
 yours-0.021
asty-0.020
uries-0.020
Token and
Token ID290
Feature activation+2.78e-02

Pos logit contributions
 sky+0.075
+0.070
 voice+0.069
 hawk+0.065
 poster+0.065
Neg logit contributions
ash-0.096
 theirs-0.090
uries-0.088
 yours-0.088
asty-0.085
Token<|endoftext|>
Token ID50256
Feature activation+7.55e-02

Pos logit contributions
ash+0.025
 theirs+0.023
uries+0.023
 yours+0.022
asty+0.022
Neg logit contributions
 sky-0.018
 voice-0.016
-0.016
 poster-0.015
't-0.015
TokenTom
Token ID13787
Feature activation+1.81e-02

Pos logit contributions
 voice+0.071
 hawk+0.065
 sky+0.062
 poster+0.061
 devastated+0.060
Neg logit contributions
ash-0.165
 yours-0.148
 theirs-0.147
aghetti-0.145
 organize-0.144
Token and
Token ID290
Feature activation+3.66e-02

Pos logit contributions
 sky+0.018
 voice+0.014
 cage+0.014
 bird+0.013
 tree+0.013
Neg logit contributions
ash-0.042
uries-0.041
iding-0.040
 theirs-0.040
uggets-0.040
Token Lily
Token ID20037
Feature activation+1.00e-02

Pos logit contributions
 sky+0.058
 voice+0.057
 bird+0.053
't+0.052
 hawk+0.050
Neg logit contributions
ash-0.067
iding-0.061
uries-0.060
aghetti-0.057
wn-0.057
Token are
Token ID389
Feature activation+1.09e-02

Pos logit contributions
 sky+0.013
 tree+0.012
 voice+0.011
 bird+0.011
 cage+0.011
Neg logit contributions
uggets-0.021
ash-0.021
iding-0.020
uries-0.020
 theirs-0.019
Token brother
Token ID3956
Feature activation+1.05e-01

Pos logit contributions
 sky+0.021
 hawk+0.020
 voice+0.020
+0.020
 poster+0.019
Neg logit contributions
ash-0.015
 theirs-0.014
 yours-0.014
uggets-0.013
asty-0.013
Token and
Token ID290
Feature activation+4.03e-02

Pos logit contributions
 sky+0.121
 voice+0.109
+0.102
 bird+0.097
 cage+0.095
Neg logit contributions
ash-0.227
uries-0.213
 theirs-0.210
wn-0.209
 yours-0.209
Token sister
Token ID6621
Feature activation+7.05e-02

Pos logit contributions
 voice+0.052
 bird+0.050
't+0.050
 sky+0.050
 crying+0.048
Neg logit contributions
ash-0.086
iding-0.078
uries-0.075
ust-0.075
aghetti-0.073
Token.
Token ID13
Feature activation+1.13e-02

Pos logit contributions
 sky+0.085
 voice+0.079
 bird+0.070
+0.070
't+0.069
Neg logit contributions
ash-0.148
wn-0.141
uries-0.140
iding-0.136
 yours-0.136
Token They
Token ID1119
Feature activation-7.25e-03

Pos logit contributions
 sky+0.015
+0.014
 voice+0.013
't+0.012
 +0.011
Neg logit contributions
ash-0.023
iding-0.022
wn-0.021
 yours-0.021
uries-0.021
Token like
Token ID588
Feature activation-2.93e-02

Pos logit contributions
ash+0.013
uggets+0.012
iding+0.012
aghetti+0.011
 kil+0.011
Neg logit contributions
 sky-0.011
't-0.011
 voice-0.011
-0.010
 bird-0.010
TokenL
Token ID43
Feature activation-7.82e-02

Pos logit contributions
 voice+0.068
 hawk+0.062
 poster+0.060
 devastated+0.058
 sky+0.057
Neg logit contributions
ash-0.158
 yours-0.139
 theirs-0.139
aghetti-0.137
asting-0.135
Tokenily
Token ID813
Feature activation+5.82e-03

Pos logit contributions
ash+0.113
 theirs+0.104
 yours+0.100
asty+0.095
uries+0.093
Neg logit contributions
 sky-0.146
-0.142
 voice-0.139
 hawk-0.135
 poster-0.131
Token and
Token ID290
Feature activation+3.03e-02

Pos logit contributions
 sky+0.007
 voice+0.005
 bird+0.005
 tree+0.005
 poster+0.005
Neg logit contributions
ash-0.013
uries-0.013
 theirs-0.013
iding-0.013
ust-0.012
Token Ben
Token ID3932
Feature activation+1.46e-02

Pos logit contributions
 sky+0.050
 voice+0.048
+0.046
't+0.045
 bird+0.044
Neg logit contributions
ash-0.052
uries-0.046
iding-0.045
wn-0.045
 theirs-0.044
Token are
Token ID389
Feature activation+1.09e-02

Pos logit contributions
 sky+0.017
 bird+0.014
 tree+0.014
 voice+0.014
't+0.013
Neg logit contributions
ash-0.033
iding-0.032
uggets-0.031
uries-0.030
ust-0.030
Token brother
Token ID3956
Feature activation+1.05e-01

Pos logit contributions
 sky+0.019
 voice+0.018
+0.018
 hawk+0.017
 poster+0.017
Neg logit contributions
ash-0.017
 theirs-0.015
 yours-0.015
uries-0.015
asty-0.014
Token and
Token ID290
Feature activation+3.67e-02

Pos logit contributions
 sky+0.096
 voice+0.083
 bird+0.075
+0.071
 cage+0.070
Neg logit contributions
ash-0.254
uries-0.242
wn-0.242
 yours-0.238
 theirs-0.237
Token sister
Token ID6621
Feature activation+7.12e-02

Pos logit contributions
 voice+0.047
 sky+0.046
't+0.046
 bird+0.045
+0.043
Neg logit contributions
ash-0.077
iding-0.070
uries-0.069
wn-0.068
ust-0.067
Token.
Token ID13
Feature activation+8.81e-03

Pos logit contributions
 sky+0.080
 voice+0.073
 bird+0.064
 crying+0.063
+0.061
Neg logit contributions
ash-0.157
wn-0.153
uries-0.148
 yours-0.146
asty-0.146
Token They
Token ID1119
Feature activation-4.85e-03

Pos logit contributions
 sky+0.011
+0.011
 voice+0.010
't+0.009
 crying+0.008
Neg logit contributions
ash-0.018
 yours-0.017
iding-0.017
wn-0.017
asting-0.017
Token like
Token ID588
Feature activation-2.70e-02

Pos logit contributions
ash+0.008
iding+0.007
uggets+0.007
aghetti+0.007
uries+0.007
Neg logit contributions
 sky-0.009
't-0.008
 voice-0.008
 bird-0.007
-0.007
Token<|endoftext|>
Token ID50256
Feature activation+7.11e-02

Pos logit contributions
ash+0.010
uries+0.009
wn+0.009
 theirs+0.009
iding+0.009
Neg logit contributions
 sky-0.003
 voice-0.002
-0.002
't-0.002
 bird-0.001
TokenTim
Token ID14967
Feature activation-2.35e-03

Pos logit contributions
 voice+0.063
 hawk+0.061
 poster+0.056
+0.055
 sky+0.055
Neg logit contributions
ash-0.157
 yours-0.139
 theirs-0.138
 organize-0.137
aghetti-0.137
Token and
Token ID290
Feature activation+3.13e-02

Pos logit contributions
ash+0.005
uries+0.005
 theirs+0.005
iding+0.005
 yours+0.005
Neg logit contributions
 sky-0.003
 voice-0.002
-0.002
't-0.002
 poster-0.002
Token Mia
Token ID32189
Feature activation-1.02e-02

Pos logit contributions
 sky+0.048
 voice+0.047
 bird+0.043
't+0.043
 hawk+0.042
Neg logit contributions
ash-0.059
uries-0.053
iding-0.053
aghetti-0.051
wn-0.050
Token are
Token ID389
Feature activation+1.26e-02

Pos logit contributions
ash+0.021
uggets+0.021
uries+0.020
iding+0.020
 theirs+0.020
Neg logit contributions
 sky-0.013
 voice-0.011
 bird-0.011
 tree-0.011
't-0.011
Token brother
Token ID3956
Feature activation+1.05e-01

Pos logit contributions
 sky+0.023
 voice+0.022
+0.022
 hawk+0.022
 poster+0.021
Neg logit contributions
ash-0.018
 theirs-0.017
 yours-0.016
asty-0.016
uggets-0.015
Token and
Token ID290
Feature activation+3.76e-02

Pos logit contributions
 sky+0.105
 voice+0.092
+0.084
 bird+0.082
 cage+0.079
Neg logit contributions
ash-0.243
uries-0.231
wn-0.228
 theirs-0.227
 yours-0.226
Token sister
Token ID6621
Feature activation+7.10e-02

Pos logit contributions
 sky+0.048
 voice+0.048
't+0.047
 bird+0.046
+0.045
Neg logit contributions
ash-0.080
iding-0.071
uries-0.071
ust-0.069
wn-0.069
Token.
Token ID13
Feature activation+1.02e-02

Pos logit contributions
 sky+0.086
 voice+0.078
 bird+0.069
+0.069
 crying+0.066
Neg logit contributions
ash-0.152
wn-0.145
uries-0.143
 yours-0.140
 theirs-0.140
Token They
Token ID1119
Feature activation-5.18e-03

Pos logit contributions
 sky+0.015
+0.014
 voice+0.014
't+0.013
 cage+0.012
Neg logit contributions
ash-0.019
wn-0.018
uries-0.018
 yours-0.018
iding-0.017
Token live
Token ID2107
Feature activation-3.98e-02

Pos logit contributions
ash+0.009
iding+0.008
uggets+0.007
uries+0.007
 theirs+0.007
Neg logit contributions
 sky-0.009
't-0.009
 voice-0.008
-0.008
 bird-0.008
TokenS
Token ID50
Feature activation-6.13e-02

Pos logit contributions
 voice+0.073
 hawk+0.070
 devastated+0.069
 poster+0.067
+0.063
Neg logit contributions
ash-0.148
 yours-0.130
 theirs-0.129
aghetti-0.129
 tim-0.128
Tokenara
Token ID3301
Feature activation-1.12e-03

Pos logit contributions
ash+0.091
 theirs+0.080
 yours+0.080
ackers+0.079
asting+0.076
Neg logit contributions
 voice-0.107
 hawk-0.104
 sky-0.098
 crying-0.095
 devastated-0.091
Token and
Token ID290
Feature activation+3.40e-02

Pos logit contributions
ash+0.003
uries+0.002
 theirs+0.002
iding+0.002
ust+0.002
Neg logit contributions
 sky-0.001
 voice-0.001
-0.001
 cage-0.001
 bird-0.001
Token Tom
Token ID4186
Feature activation+2.66e-02

Pos logit contributions
 sky+0.054
 voice+0.050
+0.049
't+0.047
 hawk+0.046
Neg logit contributions
ash-0.059
uries-0.054
 theirs-0.053
 yours-0.052
iding-0.051
Token are
Token ID389
Feature activation+1.09e-02

Pos logit contributions
 sky+0.035
 bird+0.029
 tree+0.028
 voice+0.028
 cage+0.028
Neg logit contributions
ash-0.055
uries-0.052
iding-0.052
uggets-0.052
ust-0.050
Token brother
Token ID3956
Feature activation+1.05e-01

Pos logit contributions
 sky+0.020
 voice+0.019
+0.018
 hawk+0.018
 poster+0.017
Neg logit contributions
ash-0.016
 theirs-0.015
 yours-0.015
asty-0.014
uggets-0.014
Token and
Token ID290
Feature activation+3.80e-02

Pos logit contributions
 sky+0.117
 voice+0.103
 bird+0.095
+0.093
 cage+0.091
Neg logit contributions
ash-0.231
wn-0.220
uries-0.220
asty-0.213
 yours-0.213
Token sister
Token ID6621
Feature activation+7.20e-02

Pos logit contributions
 sky+0.049
't+0.048
 bird+0.048
 voice+0.047
+0.046
Neg logit contributions
ash-0.081
iding-0.074
uries-0.071
ust-0.071
wn-0.070
Token.
Token ID13
Feature activation+1.25e-02

Pos logit contributions
 sky+0.082
 voice+0.074
 bird+0.066
 crying+0.063
 cage+0.062
Neg logit contributions
ash-0.159
wn-0.155
uries-0.151
iding-0.148
 yours-0.146
Token They
Token ID1119
Feature activation-5.82e-03

Pos logit contributions
 sky+0.016
+0.015
 voice+0.014
't+0.013
 cage+0.012
Neg logit contributions
ash-0.026
wn-0.025
iding-0.025
uries-0.024
 yours-0.024
Token like
Token ID588
Feature activation-2.89e-02

Pos logit contributions
ash+0.010
iding+0.009
uggets+0.008
aghetti+0.008
uries+0.008
Neg logit contributions
 sky-0.010
't-0.009
 voice-0.009
-0.009
 bird-0.009
Token<|endoftext|>
Token ID50256
Feature activation+7.19e-02

Pos logit contributions
ash+0.036
 theirs+0.034
uries+0.034
 yours+0.033
wn+0.033
Neg logit contributions
 sky-0.016
 voice-0.014
-0.014
't-0.013
 poster-0.012
TokenTom
Token ID13787
Feature activation+1.35e-02

Pos logit contributions
 voice+0.062
 hawk+0.057
 poster+0.055
 sky+0.055
+0.051
Neg logit contributions
ash-0.162
 theirs-0.145
 yours-0.144
 organize-0.142
aghetti-0.142
Token and
Token ID290
Feature activation+3.33e-02

Pos logit contributions
 sky+0.017
 voice+0.014
 bird+0.013
 cage+0.013
't+0.013
Neg logit contributions
ash-0.028
uries-0.027
 theirs-0.027
iding-0.027
ust-0.026
Token Lily
Token ID20037
Feature activation+6.42e-03

Pos logit contributions
 sky+0.050
 voice+0.050
 bird+0.048
 hawk+0.044
't+0.043
Neg logit contributions
ash-0.066
iding-0.060
uries-0.059
aghetti-0.057
wn-0.055
Token are
Token ID389
Feature activation+7.89e-03

Pos logit contributions
 sky+0.008
 bird+0.007
 tree+0.006
 voice+0.006
 cage+0.006
Neg logit contributions
ash-0.014
uggets-0.013
uries-0.013
iding-0.013
 theirs-0.013
Token brother
Token ID3956
Feature activation+1.04e-01

Pos logit contributions
 sky+0.014
 voice+0.013
+0.013
 hawk+0.013
 poster+0.012
Neg logit contributions
ash-0.012
 theirs-0.011
 yours-0.011
asty-0.011
uries-0.010
Token and
Token ID290
Feature activation+3.75e-02

Pos logit contributions
 sky+0.092
 voice+0.081
 bird+0.071
+0.070
 cage+0.067
Neg logit contributions
ash-0.253
uries-0.239
wn-0.239
 theirs-0.237
 yours-0.236
Token sister
Token ID6621
Feature activation+7.02e-02

Pos logit contributions
 voice+0.045
 sky+0.044
 bird+0.044
't+0.044
 crying+0.041
Neg logit contributions
ash-0.083
iding-0.075
uries-0.073
ust-0.072
wn-0.071
Token.
Token ID13
Feature activation+8.30e-03

Pos logit contributions
 sky+0.084
 voice+0.076
 bird+0.067
+0.066
 crying+0.066
Neg logit contributions
ash-0.150
wn-0.145
uries-0.142
 theirs-0.139
 yours-0.139
Token They
Token ID1119
Feature activation-9.52e-03

Pos logit contributions
 sky+0.011
+0.011
 voice+0.010
't+0.009
 crying+0.008
Neg logit contributions
ash-0.017
iding-0.015
 yours-0.015
wn-0.015
asting-0.015
Token like
Token ID588
Feature activation-2.94e-02

Pos logit contributions
ash+0.016
iding+0.015
uggets+0.014
uries+0.014
aghetti+0.014
Neg logit contributions
 sky-0.016
't-0.015
 voice-0.015
 bird-0.014
-0.013
Token<|endoftext|>
Token ID50256
Feature activation+6.72e-02

Pos logit contributions
ash+0.024
 theirs+0.023
uries+0.023
 yours+0.023
wn+0.022
Neg logit contributions
 sky-0.008
 voice-0.007
-0.007
't-0.006
 hawk-0.006
TokenTom
Token ID13787
Feature activation+1.51e-02

Pos logit contributions
 voice+0.056
 hawk+0.053
 poster+0.051
 sky+0.050
+0.048
Neg logit contributions
ash-0.152
 theirs-0.136
 yours-0.134
 organize-0.133
asting-0.133
Token and
Token ID290
Feature activation+3.40e-02

Pos logit contributions
 sky+0.016
 voice+0.013
 bird+0.012
+0.012
't+0.012
Neg logit contributions
ash-0.034
uries-0.033
iding-0.033
 theirs-0.033
uggets-0.032
Token Lily
Token ID20037
Feature activation+9.25e-03

Pos logit contributions
 sky+0.052
 voice+0.051
 bird+0.048
't+0.047
 hawk+0.045
Neg logit contributions
ash-0.065
iding-0.059
uries-0.059
aghetti-0.056
ust-0.056
Token are
Token ID389
Feature activation+8.69e-03

Pos logit contributions
 sky+0.012
 bird+0.009
 tree+0.009
+0.009
 voice+0.009
Neg logit contributions
ash-0.020
uggets-0.019
iding-0.019
uries-0.019
 theirs-0.019
Token brother
Token ID3956
Feature activation+1.04e-01

Pos logit contributions
 sky+0.016
+0.015
 hawk+0.015
 voice+0.015
 poster+0.014
Neg logit contributions
ash-0.012
 theirs-0.011
 yours-0.011
asty-0.011
uggets-0.010
Token and
Token ID290
Feature activation+3.81e-02

Pos logit contributions
 sky+0.125
 voice+0.113
 bird+0.104
+0.103
 cage+0.100
Neg logit contributions
ash-0.220
uries-0.209
wn-0.206
 yours-0.204
 theirs-0.202
Token sister
Token ID6621
Feature activation+7.07e-02

Pos logit contributions
 voice+0.048
't+0.047
 bird+0.047
 sky+0.047
 crying+0.043
Neg logit contributions
ash-0.083
iding-0.076
ust-0.073
uries-0.073
aghetti-0.070
Token.
Token ID13
Feature activation+8.61e-03

Pos logit contributions
 sky+0.087
 voice+0.080
 bird+0.071
+0.071
 crying+0.070
Neg logit contributions
ash-0.149
wn-0.142
uries-0.140
 yours-0.136
iding-0.136
Token They
Token ID1119
Feature activation-8.14e-03

Pos logit contributions
 sky+0.011
+0.010
 voice+0.010
't+0.009
 +0.008
Neg logit contributions
ash-0.018
iding-0.017
wn-0.017
asting-0.016
uries-0.016
Token like
Token ID588
Feature activation-3.06e-02

Pos logit contributions
ash+0.014
iding+0.013
uggets+0.013
aghetti+0.012
uries+0.012
Neg logit contributions
 sky-0.013
't-0.013
 voice-0.012
-0.012
 bird-0.011
Token<|endoftext|>
Token ID50256
Feature activation+7.01e-02

Pos logit contributions
ash+0.015
uries+0.014
wn+0.014
iding+0.014
 theirs+0.014
Neg logit contributions
 sky-0.006
 voice-0.005
-0.005
't-0.005
 bird-0.004
TokenTom
Token ID13787
Feature activation+1.40e-02

Pos logit contributions
 voice+0.064
 hawk+0.061
+0.057
 poster+0.057
 devastated+0.057
Neg logit contributions
ash-0.152
 yours-0.135
 theirs-0.134
aghetti-0.132
 organize-0.131
Token and
Token ID290
Feature activation+3.10e-02

Pos logit contributions
 sky+0.014
 voice+0.011
 bird+0.010
 cage+0.010
 tree+0.010
Neg logit contributions
ash-0.032
uries-0.032
iding-0.031
 theirs-0.031
ust-0.031
Token Lily
Token ID20037
Feature activation+7.30e-03

Pos logit contributions
 sky+0.049
 voice+0.048
 bird+0.045
't+0.045
 hawk+0.044
Neg logit contributions
ash-0.056
uries-0.050
iding-0.050
aghetti-0.048
wn-0.048
Token are
Token ID389
Feature activation+7.46e-03

Pos logit contributions
 sky+0.009
 tree+0.008
 bird+0.008
 voice+0.007
+0.007
Neg logit contributions
ash-0.016
uggets-0.016
uries-0.015
iding-0.015
 theirs-0.015
Token brother
Token ID3956
Feature activation+1.03e-01

Pos logit contributions
 sky+0.014
 voice+0.013
+0.013
 hawk+0.013
 poster+0.012
Neg logit contributions
ash-0.011
 theirs-0.010
 yours-0.010
asty-0.009
uggets-0.009
Token and
Token ID290
Feature activation+3.72e-02

Pos logit contributions
 sky+0.107
 voice+0.094
+0.086
 bird+0.085
 cage+0.081
Neg logit contributions
ash-0.235
uries-0.222
wn-0.219
 yours-0.218
 theirs-0.218
Token sister
Token ID6621
Feature activation+6.95e-02

Pos logit contributions
 voice+0.047
't+0.046
 sky+0.046
 bird+0.046
+0.042
Neg logit contributions
ash-0.080
iding-0.072
uries-0.070
ust-0.069
aghetti-0.068
Token.
Token ID13
Feature activation+1.02e-02

Pos logit contributions
 sky+0.085
 voice+0.078
 bird+0.070
+0.069
 crying+0.068
Neg logit contributions
ash-0.146
wn-0.139
uries-0.138
 yours-0.134
iding-0.134
Token They
Token ID1119
Feature activation-8.70e-03

Pos logit contributions
 sky+0.013
+0.012
 voice+0.010
't+0.010
 +0.009
Neg logit contributions
ash-0.022
iding-0.021
wn-0.021
asting-0.020
 yours-0.020
Token like
Token ID588
Feature activation-2.97e-02

Pos logit contributions
ash+0.015
iding+0.013
uggets+0.013
aghetti+0.012
uries+0.012
Neg logit contributions
 sky-0.015
't-0.014
 voice-0.014
-0.013
 bird-0.013
TokenS
Token ID50
Feature activation-6.08e-02

Pos logit contributions
 voice+0.069
 hawk+0.066
 poster+0.062
 devastated+0.061
+0.058
Neg logit contributions
ash-0.150
 yours-0.133
 theirs-0.132
 organize-0.130
aghetti-0.128
Tokenara
Token ID3301
Feature activation-1.31e-03

Pos logit contributions
ash+0.086
 theirs+0.077
 yours+0.077
ackers+0.070
asty+0.070
Neg logit contributions
 voice-0.106
 hawk-0.103
 sky-0.102
 crying-0.098
-0.094
Token and
Token ID290
Feature activation+3.27e-02

Pos logit contributions
ash+0.003
uries+0.003
 theirs+0.003
ust+0.003
iding+0.003
Neg logit contributions
 sky-0.001
 voice-0.001
 cage-0.001
 bird-0.001
 poster-0.001
Token Ben
Token ID3932
Feature activation+1.82e-02

Pos logit contributions
 sky+0.050
 voice+0.048
't+0.044
 bird+0.044
+0.043
Neg logit contributions
ash-0.061
uries-0.055
iding-0.054
wn-0.053
aghetti-0.052
Token are
Token ID389
Feature activation+9.13e-03

Pos logit contributions
 sky+0.023
 voice+0.019
 bird+0.019
 tree+0.019
't+0.018
Neg logit contributions
ash-0.040
iding-0.037
uggets-0.037
uries-0.036
ust-0.036
Token brother
Token ID3956
Feature activation+1.03e-01

Pos logit contributions
 sky+0.016
 voice+0.015
+0.015
 hawk+0.014
 poster+0.014
Neg logit contributions
ash-0.014
 theirs-0.013
 yours-0.013
uries-0.013
asty-0.012
Token and
Token ID290
Feature activation+3.82e-02

Pos logit contributions
 sky+0.110
 voice+0.098
 bird+0.089
+0.088
 cage+0.085
Neg logit contributions
ash-0.232
uries-0.219
wn-0.218
 yours-0.215
 theirs-0.215
Token sister
Token ID6621
Feature activation+7.03e-02

Pos logit contributions
 voice+0.050
 sky+0.050
't+0.048
 bird+0.048
+0.045
Neg logit contributions
ash-0.079
iding-0.071
uries-0.070
ust-0.069
wn-0.069
Token.
Token ID13
Feature activation+1.11e-02

Pos logit contributions
 sky+0.084
 voice+0.078
 bird+0.069
 crying+0.067
+0.066
Neg logit contributions
ash-0.151
wn-0.146
uries-0.142
iding-0.139
 yours-0.139
Token They
Token ID1119
Feature activation-5.62e-03

Pos logit contributions
 sky+0.015
+0.014
 voice+0.013
't+0.012
 cage+0.011
Neg logit contributions
ash-0.022
wn-0.021
uries-0.021
iding-0.021
 yours-0.021
Token are
Token ID389
Feature activation-4.64e-03

Pos logit contributions
ash+0.010
iding+0.009
uggets+0.008
 kil+0.008
uries+0.008
Neg logit contributions
 sky-0.009
't-0.009
 voice-0.009
-0.008
 bird-0.008
Token decided
Token ID3066
Feature activation+4.57e-02

Pos logit contributions
 sky+0.065
 voice+0.058
 bird+0.056
't+0.054
 cage+0.051
Neg logit contributions
ash-0.106
 theirs-0.100
uries-0.099
 yours-0.098
iding-0.098
Token to
Token ID284
Feature activation+4.27e-02

Pos logit contributions
 sky+0.053
 voice+0.050
't+0.046
 bird+0.043
 poster+0.043
Neg logit contributions
ash-0.101
uries-0.090
iding-0.089
 theirs-0.089
wn-0.089
Token take
Token ID1011
Feature activation-3.81e-02

Pos logit contributions
 voice+0.079
 sky+0.076
't+0.075
+0.070
 bird+0.070
Neg logit contributions
ash-0.068
 theirs-0.057
uries-0.056
iding-0.056
uggets-0.056
Token his
Token ID465
Feature activation+1.70e-02

Pos logit contributions
iding+0.076
ust+0.076
ash+0.075
uries+0.074
 yours+0.072
Neg logit contributions
 sky-0.046
 voice-0.043
't-0.038
-0.037
 bird-0.037
Token little
Token ID1310
Feature activation+5.79e-02

Pos logit contributions
 sky+0.025
 voice+0.023
+0.023
't+0.022
 hawk+0.022
Neg logit contributions
ash-0.030
 theirs-0.028
uries-0.027
 yours-0.027
wn-0.026
Token grandson
Token ID31845
Feature activation+1.02e-01

Pos logit contributions
 sky+0.073
 voice+0.068
+0.062
 bird+0.060
 poster+0.060
Neg logit contributions
ash-0.118
 theirs-0.111
uries-0.109
 yours-0.108
asty-0.107
Token to
Token ID284
Feature activation+3.95e-02

Pos logit contributions
 voice+0.127
 sky+0.124
 crying+0.115
 bird+0.114
 cage+0.112
Neg logit contributions
ash-0.196
ust-0.184
asty-0.183
aghetti-0.179
 yours-0.179
Token the
Token ID262
Feature activation+4.73e-02

Pos logit contributions
 sky+0.045
 voice+0.045
't+0.041
+0.039
 poster+0.038
Neg logit contributions
ash-0.087
ust-0.080
iding-0.078
uries-0.078
aghetti-0.076
Token hardware
Token ID6890
Feature activation+5.30e-02

Pos logit contributions
 sky+0.049
+0.046
 voice+0.044
 hawk+0.041
't+0.041
Neg logit contributions
ash-0.101
uries-0.096
 theirs-0.095
 organize-0.095
 yours-0.095
Token store
Token ID3650
Feature activation+5.55e-02

Pos logit contributions
 sky+0.043
 voice+0.036
+0.033
 poster+0.031
 cage+0.031
Neg logit contributions
ash-0.131
 theirs-0.125
uries-0.124
iding-0.123
 yours-0.122
Token.
Token ID13
Feature activation-3.45e-03

Pos logit contributions
 sky+0.075
 voice+0.069
+0.065
't+0.064
 cage+0.061
Neg logit contributions
ash-0.108
uries-0.099
 yours-0.097
iding-0.096
 theirs-0.096
Token<|endoftext|>
Token ID50256
Feature activation+7.63e-02

Pos logit contributions
ash+0.024
 theirs+0.024
 yours+0.023
uries+0.023
asty+0.022
Neg logit contributions
 sky-0.019
 voice-0.018
-0.017
 poster-0.017
 hawk-0.017
TokenTom
Token ID13787
Feature activation+1.89e-02

Pos logit contributions
 voice+0.061
 hawk+0.057
 sky+0.056
 poster+0.053
 cage+0.049
Neg logit contributions
ash-0.178
 theirs-0.163
 yours-0.160
 organize-0.158
asting-0.157
Token and
Token ID290
Feature activation+3.76e-02

Pos logit contributions
 sky+0.021
 voice+0.018
+0.016
't+0.016
 bird+0.016
Neg logit contributions
ash-0.041
uries-0.040
 theirs-0.039
iding-0.039
ust-0.038
Token Lily
Token ID20037
Feature activation+9.85e-03

Pos logit contributions
 sky+0.052
 voice+0.052
 bird+0.049
't+0.045
 hawk+0.044
Neg logit contributions
ash-0.078
iding-0.072
uries-0.070
aghetti-0.068
ust-0.067
Token were
Token ID547
Feature activation+1.32e-02

Pos logit contributions
 sky+0.013
 bird+0.010
 tree+0.010
 voice+0.010
+0.010
Neg logit contributions
ash-0.021
uggets-0.020
uries-0.020
iding-0.019
 theirs-0.019
Token brother
Token ID3956
Feature activation+1.02e-01

Pos logit contributions
 sky+0.023
 voice+0.022
+0.022
 hawk+0.021
 poster+0.021
Neg logit contributions
ash-0.020
 theirs-0.018
 yours-0.018
uries-0.017
asty-0.017
Token and
Token ID290
Feature activation+3.86e-02

Pos logit contributions
 sky+0.102
 voice+0.090
+0.083
 bird+0.078
 cage+0.076
Neg logit contributions
ash-0.236
 theirs-0.221
uries-0.221
 yours-0.220
wn-0.219
Token sister
Token ID6621
Feature activation+7.06e-02

Pos logit contributions
 voice+0.043
't+0.043
 bird+0.042
 sky+0.042
 crying+0.040
Neg logit contributions
ash-0.089
iding-0.080
ust-0.079
uries-0.079
aghetti-0.077
Token.
Token ID13
Feature activation+9.79e-03

Pos logit contributions
 sky+0.090
 voice+0.083
+0.076
 bird+0.073
't+0.073
Neg logit contributions
ash-0.144
wn-0.135
 theirs-0.134
uries-0.134
 yours-0.133
Token They
Token ID1119
Feature activation-8.31e-03

Pos logit contributions
 sky+0.013
+0.012
 voice+0.011
't+0.010
 +0.010
Neg logit contributions
ash-0.020
iding-0.019
 yours-0.018
wn-0.018
asting-0.018
Token liked
Token ID8288
Feature activation+2.65e-02

Pos logit contributions
ash+0.017
iding+0.016
uries+0.016
wn+0.015
 theirs+0.015
Neg logit contributions
 sky-0.011
 voice-0.010
't-0.010
-0.009
 bird-0.009
Token<|endoftext|>
Token ID50256
Feature activation+7.51e-02

Pos logit contributions
 sky+0.039
 hawk+0.038
 voice+0.038
+0.037
 poster+0.037
Neg logit contributions
ash-0.038
 theirs-0.036
 yours-0.034
uries-0.033
uggets-0.033
TokenTom
Token ID13787
Feature activation+2.66e-02

Pos logit contributions
 voice+0.064
 hawk+0.060
 poster+0.058
 sky+0.057
+0.053
Neg logit contributions
ash-0.172
 theirs-0.151
aghetti-0.150
 yours-0.150
asting-0.150
Token and
Token ID290
Feature activation+3.59e-02

Pos logit contributions
 sky+0.027
 voice+0.023
+0.021
 bird+0.020
't+0.020
Neg logit contributions
ash-0.061
 theirs-0.059
uries-0.058
iding-0.057
 yours-0.057
Token Lily
Token ID20037
Feature activation+1.03e-02

Pos logit contributions
 sky+0.055
 voice+0.053
 bird+0.050
't+0.049
 hawk+0.048
Neg logit contributions
ash-0.067
uries-0.061
iding-0.060
aghetti-0.058
wn-0.058
Token were
Token ID547
Feature activation+1.58e-02

Pos logit contributions
 sky+0.014
+0.012
 bird+0.012
 voice+0.012
 tree+0.011
Neg logit contributions
ash-0.021
uries-0.020
uggets-0.019
 theirs-0.019
 yours-0.019
Token brother
Token ID3956
Feature activation+1.02e-01

Pos logit contributions
 sky+0.030
 voice+0.028
 hawk+0.028
+0.028
 poster+0.027
Neg logit contributions
ash-0.022
 theirs-0.020
 yours-0.020
uggets-0.019
asty-0.019
Token and
Token ID290
Feature activation+3.89e-02

Pos logit contributions
 sky+0.108
 voice+0.097
+0.092
't+0.085
 bird+0.084
Neg logit contributions
ash-0.226
 theirs-0.212
uries-0.211
 yours-0.210
wn-0.206
Token sister
Token ID6621
Feature activation+7.07e-02

Pos logit contributions
 voice+0.046
't+0.046
 sky+0.046
+0.044
 bird+0.043
Neg logit contributions
ash-0.085
iding-0.075
uries-0.075
ust-0.074
wn-0.073
Token.
Token ID13
Feature activation+1.10e-02

Pos logit contributions
 sky+0.101
 voice+0.094
+0.090
't+0.085
 poster+0.084
Neg logit contributions
ash-0.131
 theirs-0.121
uries-0.120
 yours-0.119
wn-0.117
Token They
Token ID1119
Feature activation-6.96e-03

Pos logit contributions
 sky+0.014
+0.014
 voice+0.013
't+0.012
 crying+0.011
Neg logit contributions
ash-0.023
 yours-0.021
iding-0.021
wn-0.021
asting-0.021
Token liked
Token ID8288
Feature activation+2.65e-02

Pos logit contributions
ash+0.014
uries+0.012
iding+0.012
 theirs+0.012
 yours+0.012
Neg logit contributions
 sky-0.010
 voice-0.009
-0.009
't-0.009
 bird-0.008
Token<|endoftext|>
Token ID50256
Feature activation+6.23e-02

Pos logit contributions
ash+0.043
 theirs+0.043
uries+0.041
 yours+0.041
uggets+0.040
Neg logit contributions
 sky-0.024
 voice-0.023
-0.023
 poster-0.022
 hawk-0.021
TokenTom
Token ID13787
Feature activation+1.14e-02

Pos logit contributions
 voice+0.046
 sky+0.044
 hawk+0.042
+0.039
 poster+0.038
Neg logit contributions
ash-0.150
 theirs-0.138
 yours-0.137
 organize-0.134
asting-0.133
Token and
Token ID290
Feature activation+3.10e-02

Pos logit contributions
 sky+0.014
 voice+0.012
+0.012
't+0.011
 bird+0.011
Neg logit contributions
ash-0.023
uries-0.022
 theirs-0.022
iding-0.022
 yours-0.021
Token Anna
Token ID11735
Feature activation+1.35e-03

Pos logit contributions
 sky+0.047
 voice+0.046
 bird+0.043
't+0.042
 hawk+0.040
Neg logit contributions
ash-0.060
iding-0.054
uries-0.054
aghetti-0.052
wn-0.051
Token are
Token ID389
Feature activation+8.13e-03

Pos logit contributions
 sky+0.002
 voice+0.001
+0.001
 bird+0.001
't+0.001
Neg logit contributions
ash-0.003
iding-0.003
uggets-0.003
 yours-0.003
 theirs-0.003
Token brother
Token ID3956
Feature activation+1.02e-01

Pos logit contributions
 sky+0.014
+0.014
 voice+0.013
 hawk+0.013
 poster+0.013
Neg logit contributions
ash-0.012
 theirs-0.011
 yours-0.011
asty-0.011
uries-0.011
Token and
Token ID290
Feature activation+3.55e-02

Pos logit contributions
 sky+0.123
 voice+0.110
+0.102
 bird+0.100
 cage+0.096
Neg logit contributions
ash-0.216
uries-0.203
wn-0.201
 theirs-0.200
 yours-0.198
Token sister
Token ID6621
Feature activation+6.73e-02

Pos logit contributions
 sky+0.046
 voice+0.046
't+0.045
 bird+0.044
 crying+0.042
Neg logit contributions
ash-0.075
iding-0.067
uries-0.065
ust-0.064
wn-0.064
Token.
Token ID13
Feature activation+4.70e-03

Pos logit contributions
 sky+0.081
 voice+0.073
+0.065
 bird+0.065
't+0.063
Neg logit contributions
ash-0.145
wn-0.139
uries-0.135
 theirs-0.134
iding-0.133
Token They
Token ID1119
Feature activation-9.93e-03

Pos logit contributions
 sky+0.006
+0.006
 voice+0.006
't+0.005
 poster+0.005
Neg logit contributions
ash-0.010
wn-0.009
iding-0.009
asting-0.009
asty-0.009
Token like
Token ID588
Feature activation-3.09e-02

Pos logit contributions
ash+0.017
iding+0.015
uggets+0.015
aghetti+0.014
 theirs+0.014
Neg logit contributions
 sky-0.017
't-0.016
 voice-0.016
 bird-0.015
-0.015
Token Her
Token ID2332
Feature activation-7.65e-03

Pos logit contributions
ash+0.012
 proper+0.012
asty+0.012
 theirs+0.011
 organize+0.011
Neg logit contributions
 hawk-0.012
 poster-0.011
 voice-0.010
 cage-0.010
 sky-0.010
Token mom
Token ID1995
Feature activation+2.81e-02

Pos logit contributions
 theirs+0.008
 yours+0.008
 proper+0.008
 remember+0.007
 organize+0.007
Neg logit contributions
-0.014
iren-0.014
't-0.013
 sky-0.013
 hawk-0.013
Tokenmy
Token ID1820
Feature activation+2.64e-02

Pos logit contributions
+0.075
 sky+0.070
 hawk+0.069
 poster+0.068
 skies+0.064
Neg logit contributions
ash-0.017
asting-0.014
 allowed-0.013
wed-0.013
ac-0.013
Token was
Token ID373
Feature activation+3.41e-02

Pos logit contributions
+0.051
 sky+0.050
 poster+0.049
 skies+0.044
 hawk+0.043
Neg logit contributions
 allowed-0.029
 let-0.028
 remember-0.027
 even-0.027
asting-0.026
Token heart
Token ID2612
Feature activation+4.12e-02

Pos logit contributions
 sky+0.057
+0.056
 poster+0.052
 skies+0.049
eros+0.048
Neg logit contributions
 theirs-0.050
asting-0.048
asty-0.047
 organize-0.047
 like-0.047
Tokenbroken
Token ID25826
Feature activation+1.02e-01

Pos logit contributions
 sky+0.058
+0.053
 voice+0.051
 hawk+0.051
 poster+0.050
Neg logit contributions
ash-0.074
iding-0.070
 theirs-0.070
uries-0.069
asting-0.068
Token and
Token ID290
Feature activation+3.01e-02

Pos logit contributions
 sky+0.136
+0.126
 voice+0.124
 poster+0.120
 hawk+0.118
Neg logit contributions
ash-0.188
 theirs-0.178
 yours-0.172
uries-0.171
asty-0.169
Token missed
Token ID6825
Feature activation+5.80e-02

Pos logit contributions
+0.046
 sky+0.045
 poster+0.041
 voice+0.040
 hawk+0.039
Neg logit contributions
 theirs-0.050
ash-0.048
 yours-0.048
asty-0.046
 organize-0.046
Token her
Token ID607
Feature activation+1.05e-02

Pos logit contributions
 sky+0.104
 voice+0.098
+0.097
 poster+0.092
 hawk+0.092
Neg logit contributions
ash-0.085
 theirs-0.079
uries-0.076
 yours-0.076
asty-0.074
Token little
Token ID1310
Feature activation+6.35e-02

Pos logit contributions
 sky+0.017
+0.016
't+0.015
 poster+0.015
 hawk+0.015
Neg logit contributions
 theirs-0.016
ash-0.016
 yours-0.015
uries-0.015
 enjoyable-0.015
Token girl
Token ID2576
Feature activation+6.69e-02

Pos logit contributions
 sky+0.074
+0.070
't+0.067
 voice+0.063
 hawk+0.062
Neg logit contributions
ash-0.125
 theirs-0.122
 yours-0.119
uries-0.116
 organize-0.116
Token<|endoftext|>
Token ID50256
Feature activation+6.95e-02

Pos logit contributions
ash+0.036
 theirs+0.034
uries+0.034
 yours+0.033
uggets+0.033
Neg logit contributions
 sky-0.017
-0.015
 poster-0.014
 voice-0.014
 hawk-0.014
TokenTom
Token ID13787
Feature activation+1.44e-02

Pos logit contributions
 voice+0.063
 hawk+0.060
 sky+0.057
 devastated+0.056
 poster+0.056
Neg logit contributions
ash-0.154
 yours-0.136
 organize-0.134
aghetti-0.134
 theirs-0.134
Token and
Token ID290
Feature activation+3.18e-02

Pos logit contributions
 sky+0.016
 voice+0.013
 cage+0.012
't+0.012
 bird+0.012
Neg logit contributions
ash-0.031
uries-0.031
 theirs-0.030
iding-0.030
uggets-0.029
Token Lily
Token ID20037
Feature activation+8.99e-03

Pos logit contributions
 sky+0.051
 voice+0.050
't+0.047
 bird+0.047
 hawk+0.045
Neg logit contributions
ash-0.056
iding-0.050
uries-0.050
wn-0.047
aghetti-0.047
Token were
Token ID547
Feature activation+1.21e-02

Pos logit contributions
 sky+0.013
 voice+0.011
 tree+0.010
 bird+0.010
 poster+0.010
Neg logit contributions
ash-0.018
uggets-0.018
uries-0.017
iding-0.017
 theirs-0.017
Token brother
Token ID3956
Feature activation+1.01e-01

Pos logit contributions
 sky+0.022
 hawk+0.021
 voice+0.021
+0.021
 poster+0.020
Neg logit contributions
ash-0.017
 theirs-0.016
 yours-0.015
asty-0.014
uggets-0.014
Token and
Token ID290
Feature activation+3.88e-02

Pos logit contributions
 sky+0.120
 voice+0.109
+0.101
 bird+0.098
 cage+0.095
Neg logit contributions
ash-0.215
uries-0.201
 theirs-0.199
wn-0.198
 yours-0.198
Token sister
Token ID6621
Feature activation+7.05e-02

Pos logit contributions
 voice+0.046
't+0.046
 sky+0.045
 bird+0.044
+0.042
Neg logit contributions
ash-0.087
iding-0.078
uries-0.076
ust-0.075
wn-0.073
Token.
Token ID13
Feature activation+9.08e-03

Pos logit contributions
 sky+0.092
 voice+0.086
+0.078
 bird+0.076
't+0.075
Neg logit contributions
ash-0.142
wn-0.132
uries-0.131
 yours-0.130
 theirs-0.130
Token They
Token ID1119
Feature activation-7.42e-03

Pos logit contributions
 sky+0.012
+0.012
 voice+0.011
't+0.010
 cage+0.009
Neg logit contributions
ash-0.018
iding-0.017
wn-0.017
 yours-0.017
uries-0.017
Token lived
Token ID5615
Feature activation-3.14e-03

Pos logit contributions
ash+0.015
iding+0.014
uries+0.013
 theirs+0.013
 yours+0.013
Neg logit contributions
 sky-0.010
 voice-0.009
't-0.009
-0.009
 bird-0.008
Token did
Token ID750
Feature activation+3.44e-02

Pos logit contributions
 theirs+0.068
ash+0.067
iding+0.065
uries+0.064
 yours+0.064
Neg logit contributions
 sky-0.044
't-0.038
 voice-0.038
-0.036
 bird-0.035
Token something
Token ID1223
Feature activation-1.75e-02

Pos logit contributions
 sky+0.042
't+0.041
 voice+0.041
 poster+0.035
+0.034
Neg logit contributions
ash-0.075
uggets-0.066
uries-0.066
aghetti-0.065
 theirs-0.064
Token special
Token ID2041
Feature activation-1.79e-02

Pos logit contributions
ash+0.040
uries+0.039
iding+0.039
ales+0.039
uggets+0.039
Neg logit contributions
 voice-0.017
 sky-0.016
't-0.015
 that-0.014
 bird-0.014
Token.
Token ID13
Feature activation-1.30e-02

Pos logit contributions
ash+0.039
ackers+0.039
iding+0.039
wn+0.038
uries+0.038
Neg logit contributions
 sky-0.020
 voice-0.016
't-0.016
 bird-0.014
 tree-0.014
Token On
Token ID1550
Feature activation-3.62e-02

Pos logit contributions
ash+0.030
 theirs+0.028
uries+0.028
 yours+0.028
asty+0.027
Neg logit contributions
 sky-0.013
 voice-0.011
-0.011
't-0.010
 poster-0.010
Token Wed
Token ID3300
Feature activation-1.72e-01

Pos logit contributions
ash+0.051
 yours+0.049
 theirs+0.049
 organize+0.046
asty+0.046
Neg logit contributions
 sky-0.060
 hawk-0.060
 voice-0.059
-0.059
 cage-0.056
Tokennes
Token ID2516
Feature activation-7.79e-02

Pos logit contributions
ash+0.166
 theirs+0.144
 yours+0.134
uries+0.130
asty+0.128
Neg logit contributions
 sky-0.393
-0.372
 voice-0.369
't-0.369
 poster-0.357
Tokendays
Token ID12545
Feature activation-2.73e-02

Pos logit contributions
 theirs+0.100
ash+0.100
 yours+0.097
uries+0.094
uggets+0.089
Neg logit contributions
 sky-0.145
 voice-0.139
-0.135
't-0.132
 cage-0.128
Token she
Token ID673
Feature activation-4.26e-02

Pos logit contributions
 theirs+0.062
uries+0.060
 yours+0.059
wn+0.059
ash+0.059
Neg logit contributions
 sky-0.029
 voice-0.023
-0.023
't-0.022
 bird-0.020
Token liked
Token ID8288
Feature activation+1.43e-02

Pos logit contributions
ash+0.075
 theirs+0.075
iding+0.072
uggets+0.071
uries+0.071
Neg logit contributions
 sky-0.065
 voice-0.057
't-0.055
-0.055
 bird-0.054
Token to
Token ID284
Feature activation+1.91e-02

Pos logit contributions
 sky+0.017
 voice+0.015
't+0.014
 bird+0.014
 crying+0.013
Neg logit contributions
ash-0.031
uries-0.029
iding-0.029
wn-0.029
 theirs-0.028
Token river
Token ID7850
Feature activation+7.25e-03

Pos logit contributions
 sky+0.031
 voice+0.028
+0.028
't+0.026
 poster+0.026
Neg logit contributions
ash-0.057
 theirs-0.053
uries-0.053
 yours-0.052
wn-0.051
Token.
Token ID13
Feature activation-2.32e-02

Pos logit contributions
 sky+0.011
 voice+0.010
+0.010
't+0.009
 cage+0.009
Neg logit contributions
ash-0.013
 theirs-0.012
uries-0.012
 yours-0.012
asty-0.012
Token
Token ID198
Feature activation-3.60e-03

Pos logit contributions
ash+0.046
asty+0.043
uries+0.043
 theirs+0.042
 organize+0.041
Neg logit contributions
 hawk-0.025
 voice-0.025
 poster-0.024
 sky-0.024
 cage-0.023
Token
Token ID198
Feature activation-4.38e-03

Pos logit contributions
ash+0.006
 organize+0.006
asting+0.006
 theirs+0.006
asty+0.006
Neg logit contributions
 sky-0.005
-0.005
 hawk-0.005
 poster-0.004
 voice-0.004
TokenWhen
Token ID2215
Feature activation-2.01e-03

Pos logit contributions
ash+0.007
uries+0.007
iding+0.007
 organize+0.007
asting+0.007
Neg logit contributions
 sky-0.007
-0.006
 voice-0.006
 poster-0.006
 hawk-0.006
Token Sil
Token ID4243
Feature activation-1.65e-01

Pos logit contributions
 theirs+0.003
ash+0.003
asty+0.003
 yours+0.003
 organize+0.003
Neg logit contributions
 sky-0.003
 voice-0.003
-0.003
 cage-0.003
 poster-0.003
Tokenvia
Token ID8869
Feature activation-2.79e-02

Pos logit contributions
ash+0.190
uries+0.166
 theirs+0.165
 yours+0.156
iding+0.154
Neg logit contributions
 sky-0.359
-0.343
 voice-0.341
 hawk-0.322
't-0.322
Token arrived
Token ID5284
Feature activation+5.66e-03

Pos logit contributions
ash+0.049
 theirs+0.045
uries+0.045
 yours+0.044
asty+0.043
Neg logit contributions
 sky-0.041
 voice-0.038
-0.038
 poster-0.036
 hawk-0.036
Token at
Token ID379
Feature activation-1.35e-02

Pos logit contributions
 sky+0.012
+0.011
 voice+0.011
't+0.011
 hawk+0.011
Neg logit contributions
ash-0.006
 theirs-0.006
 yours-0.006
uries-0.005
asty-0.005
Token the
Token ID262
Feature activation+2.85e-02

Pos logit contributions
 theirs+0.019
 yours+0.018
ash+0.018
asty+0.017
 organize+0.017
Neg logit contributions
-0.024
 sky-0.023
 voice-0.023
 hawk-0.022
't-0.022
Token river
Token ID7850
Feature activation+1.09e-02

Pos logit contributions
+0.039
 voice+0.037
 poster+0.037
't+0.036
 sky+0.036
Neg logit contributions
ash-0.049
asting-0.046
 organize-0.045
 theirs-0.045
 yours-0.044
Token chose
Token ID7690
Feature activation-4.10e-03

Pos logit contributions
ash+0.056
 theirs+0.052
uries+0.052
 yours+0.051
asty+0.049
Neg logit contributions
 sky-0.050
 voice-0.046
-0.046
't-0.043
 poster-0.043
Token both
Token ID1111
Feature activation-2.31e-02

Pos logit contributions
ash+0.008
uries+0.007
 theirs+0.007
iding+0.007
 yours+0.007
Neg logit contributions
 sky-0.006
 voice-0.005
-0.005
't-0.005
 bird-0.005
Token vendors
Token ID17192
Feature activation-1.28e-02

Pos logit contributions
ash+0.041
uries+0.038
 theirs+0.038
 yours+0.037
iding+0.037
Neg logit contributions
 sky-0.035
 voice-0.032
-0.031
 cage-0.029
 bird-0.029
Token.
Token ID13
Feature activation-1.73e-02

Pos logit contributions
ash+0.026
uries+0.024
asty+0.023
wn+0.023
 yours+0.023
Neg logit contributions
 sky-0.016
 voice-0.015
-0.014
 bird-0.013
 cage-0.013
Token The
Token ID383
Feature activation+1.90e-02

Pos logit contributions
ash+0.037
 theirs+0.034
uries+0.034
 yours+0.033
asty+0.033
Neg logit contributions
 sky-0.019
 voice-0.018
 hawk-0.017
 poster-0.016
-0.016
Token frag
Token ID7956
Feature activation-1.62e-01

Pos logit contributions
 sky+0.024
+0.021
 voice+0.021
't+0.020
 hawk+0.020
Neg logit contributions
ash-0.038
 theirs-0.035
uries-0.035
 yours-0.034
 organize-0.034
Tokenrant
Token ID5250
Feature activation-2.30e-02

Pos logit contributions
ash+0.158
uries+0.148
 theirs+0.146
 yours+0.140
 organize+0.137
Neg logit contributions
 sky-0.353
 voice-0.328
-0.325
't-0.318
 poster-0.313
Token flowers
Token ID12734
Feature activation-4.37e-02

Pos logit contributions
ash+0.049
 yours+0.045
 theirs+0.044
iding+0.044
uries+0.044
Neg logit contributions
 sky-0.030
 voice-0.027
-0.024
 bird-0.024
't-0.023
Token for
Token ID329
Feature activation-3.06e-02

Pos logit contributions
ash+0.082
 theirs+0.076
uries+0.075
 yours+0.074
asty+0.073
Neg logit contributions
 sky-0.059
 voice-0.055
-0.054
't-0.050
 poster-0.050
Token the
Token ID262
Feature activation+1.82e-02

Pos logit contributions
ash+0.047
 theirs+0.044
uries+0.043
 yours+0.042
asty+0.041
Neg logit contributions
 sky-0.052
 voice-0.049
-0.048
't-0.046
 poster-0.046
Token sweet
Token ID6029
Feature activation-2.88e-02

Pos logit contributions
 sky+0.022
 voice+0.020
+0.019
 poster+0.018
't+0.018
Neg logit contributions
ash-0.038
 theirs-0.035
uries-0.035
 yours-0.034
iding-0.034
Token another
Token ID1194
Feature activation+1.27e-02

Pos logit contributions
ash+0.103
aghetti+0.102
ust+0.101
iding+0.100
uries+0.098
Neg logit contributions
 voice-0.068
 sky-0.067
 bird-0.059
't-0.057
 cage-0.055
Token wand
Token ID11569
Feature activation-1.35e-02

Pos logit contributions
 sky+0.019
+0.017
 voice+0.017
't+0.016
 hawk+0.016
Neg logit contributions
ash-0.023
 theirs-0.021
uries-0.021
 yours-0.021
wn-0.020
Token.
Token ID13
Feature activation-2.55e-02

Pos logit contributions
ash+0.024
 theirs+0.022
uries+0.022
 yours+0.022
asty+0.022
Neg logit contributions
 sky-0.020
 voice-0.018
-0.018
't-0.017
 cage-0.017
Token "
Token ID366
Feature activation-1.87e-02

Pos logit contributions
ash+0.059
 theirs+0.056
uries+0.055
 yours+0.055
asty+0.054
Neg logit contributions
 sky-0.023
 voice-0.021
-0.020
 hawk-0.019
 poster-0.019
TokenA
Token ID32
Feature activation-1.56e-02

Pos logit contributions
ash+0.038
 theirs+0.036
 yours+0.035
uries+0.035
iding+0.035
Neg logit contributions
 sky-0.024
 voice-0.021
-0.020
't-0.019
 hawk-0.019
Tokenbr
Token ID1671
Feature activation-1.61e-01

Pos logit contributions
ash+0.026
 theirs+0.025
uries+0.024
 yours+0.023
asty+0.023
Neg logit contributions
 sky-0.025
 voice-0.024
-0.022
't-0.022
 poster-0.022
Tokenac
Token ID330
Feature activation-5.42e-02

Pos logit contributions
ash+0.087
 theirs+0.073
uries+0.070
 yours+0.065
asty+0.060
Neg logit contributions
 sky-0.429
 voice-0.413
-0.405
't-0.396
 poster-0.395
Tokenad
Token ID324
Feature activation-7.37e-02

Pos logit contributions
ash+0.089
 yours+0.082
 theirs+0.080
wn+0.078
asty+0.078
Neg logit contributions
 sky-0.091
-0.089
 voice-0.080
 poster-0.079
't-0.078
Tokenab
Token ID397
Feature activation-6.21e-02

Pos logit contributions
ash+0.098
 theirs+0.090
uries+0.088
 yours+0.085
asty+0.083
Neg logit contributions
 sky-0.142
 voice-0.134
-0.131
't-0.127
 poster-0.126
Tokenra
Token ID430
Feature activation-1.88e-02

Pos logit contributions
ash+0.116
 theirs+0.109
uries+0.108
 enjoyable+0.105
asting+0.104
Neg logit contributions
 sky-0.085
 voice-0.084
-0.078
't-0.077
 poster-0.076
Token!"
Token ID2474
Feature activation+1.74e-02

Pos logit contributions
ash+0.033
 theirs+0.031
uries+0.031
 enjoyable+0.030
ust+0.030
Neg logit contributions
 sky-0.027
 voice-0.026
't-0.026
-0.025
 poster-0.024
Token.
Token ID13
Feature activation-6.64e-03

Pos logit contributions
 sky+0.011
 voice+0.011
 bird+0.010
 poster+0.010
+0.010
Neg logit contributions
ash-0.014
uries-0.013
 yours-0.013
wn-0.013
 theirs-0.012
Token They
Token ID1119
Feature activation-1.09e-02

Pos logit contributions
ash+0.011
 theirs+0.010
uries+0.010
 yours+0.010
iding+0.010
Neg logit contributions
 sky-0.011
 voice-0.010
-0.010
't-0.009
 poster-0.009
Token see
Token ID766
Feature activation-2.27e-02

Pos logit contributions
ash+0.016
 theirs+0.015
uries+0.015
 yours+0.014
iding+0.014
Neg logit contributions
 sky-0.020
 voice-0.018
-0.018
't-0.017
 poster-0.017
Token many
Token ID867
Feature activation+4.38e-03

Pos logit contributions
ash+0.037
 theirs+0.036
 yours+0.034
uries+0.033
asty+0.033
Neg logit contributions
 sky-0.035
-0.034
 voice-0.033
't-0.032
 poster-0.031
Token sh
Token ID427
Feature activation-5.32e-02

Pos logit contributions
 sky+0.006
 voice+0.006
 bird+0.005
 poster+0.005
 hawk+0.005
Neg logit contributions
uries-0.009
ash-0.009
wn-0.008
iding-0.008
asty-0.008
Tokenrim
Token ID3036
Feature activation-1.61e-01

Pos logit contributions
ash+0.056
 theirs+0.046
uries+0.044
asting+0.044
iding+0.044
Neg logit contributions
 sky-0.121
 voice-0.114
-0.113
 hawk-0.110
 poster-0.110
Tokenps
Token ID862
Feature activation+9.46e-03

Pos logit contributions
ash+0.298
 enjoyable+0.287
uries+0.285
 theirs+0.278
 organize+0.277
Neg logit contributions
 sky-0.195
 voice-0.188
't-0.176
 cage-0.164
 poster-0.162
Token and
Token ID290
Feature activation+1.34e-02

Pos logit contributions
 sky+0.012
 voice+0.010
 bird+0.009
 crying+0.009
 cage+0.008
Neg logit contributions
uries-0.021
ash-0.020
uggets-0.019
wn-0.019
 yours-0.019
Token fish
Token ID5916
Feature activation-2.36e-02

Pos logit contributions
 sky+0.023
 voice+0.022
 poster+0.019
 bird+0.019
 cage+0.019
Neg logit contributions
ash-0.023
uries-0.020
iding-0.020
wn-0.020
ust-0.020
Token and
Token ID290
Feature activation+1.62e-02

Pos logit contributions
ash+0.042
 theirs+0.039
uries+0.039
 yours+0.038
wn+0.037
Neg logit contributions
 sky-0.035
 voice-0.032
-0.031
't-0.030
 poster-0.029
Token crabs
Token ID49172
Feature activation-4.10e-02

Pos logit contributions
 sky+0.026
 voice+0.024
 bird+0.022
 poster+0.021
 hawk+0.021
Neg logit contributions
ash-0.030
uries-0.027
iding-0.027
wn-0.027
ust-0.026
Token the
Token ID262
Feature activation+3.42e-02

Pos logit contributions
ash+0.037
uries+0.034
 theirs+0.033
 yours+0.032
iding+0.032
Neg logit contributions
 sky-0.035
 voice-0.033
-0.031
't-0.030
 poster-0.029
Token air
Token ID1633
Feature activation+9.48e-03

Pos logit contributions
+0.030
 sky+0.029
't+0.028
 voice+0.027
 hawk+0.026
Neg logit contributions
ash-0.076
wn-0.072
 yours-0.072
 theirs-0.072
uries-0.072
Token.
Token ID13
Feature activation-1.59e-02

Pos logit contributions
 sky+0.013
 voice+0.012
+0.011
 cage+0.011
 poster+0.011
Neg logit contributions
ash-0.018
uries-0.017
 theirs-0.016
 yours-0.016
wn-0.016
Token "
Token ID366
Feature activation-1.72e-02

Pos logit contributions
ash+0.031
 theirs+0.029
uries+0.029
 yours+0.028
wn+0.028
Neg logit contributions
 sky-0.021
 voice-0.019
-0.019
't-0.018
 poster-0.017
TokenA
Token ID32
Feature activation-1.65e-02

Pos logit contributions
ash+0.035
 theirs+0.034
uries+0.033
 yours+0.033
iding+0.032
Neg logit contributions
 sky-0.022
 voice-0.019
-0.018
't-0.018
 bird-0.017
Tokenbr
Token ID1671
Feature activation-1.60e-01

Pos logit contributions
ash+0.029
 theirs+0.027
uries+0.027
 yours+0.026
asty+0.026
Neg logit contributions
 sky-0.025
 voice-0.023
-0.023
 poster-0.022
't-0.022
Tokenac
Token ID330
Feature activation-5.25e-02

Pos logit contributions
ash+0.087
 theirs+0.071
uries+0.068
 yours+0.064
asty+0.058
Neg logit contributions
 sky-0.431
 voice-0.413
-0.408
't-0.397
 poster-0.396
Tokenad
Token ID324
Feature activation-7.21e-02

Pos logit contributions
ash+0.082
 yours+0.073
 theirs+0.071
wn+0.071
asting+0.069
Neg logit contributions
-0.094
 sky-0.093
 poster-0.082
 voice-0.082
't-0.081
Tokenab
Token ID397
Feature activation-6.08e-02

Pos logit contributions
ash+0.099
 theirs+0.090
uries+0.089
 yours+0.086
asty+0.084
Neg logit contributions
 sky-0.136
 voice-0.127
-0.125
't-0.121
 poster-0.120
Tokenra
Token ID430
Feature activation-1.75e-02

Pos logit contributions
ash+0.108
 theirs+0.100
uries+0.099
 yours+0.096
wn+0.095
Neg logit contributions
 sky-0.090
 voice-0.086
-0.083
't-0.080
 poster-0.079
Token!"
Token ID2474
Feature activation+2.68e-02

Pos logit contributions
ash+0.030
 theirs+0.029
uries+0.028
uggets+0.028
ust+0.028
Neg logit contributions
 sky-0.026
 voice-0.025
't-0.025
 poster-0.024
-0.024
Token and
Token ID290
Feature activation+8.97e-03

Pos logit contributions
 sky+0.021
+0.019
 voice+0.019
 hawk+0.018
 poster+0.017
Neg logit contributions
ash-0.032
 theirs-0.031
 yours-0.030
uries-0.030
asty-0.029
Token said
Token ID531
Feature activation+2.91e-02

Pos logit contributions
 sky+0.013
 voice+0.012
 poster+0.011
 bird+0.011
+0.011
Neg logit contributions
ash-0.018
uries-0.016
iding-0.016
 theirs-0.016
ust-0.015
Token,
Token ID11
Feature activation-1.57e-02

Pos logit contributions
 sky+0.031
+0.027
 voice+0.026
 hawk+0.024
 poster+0.024
Neg logit contributions
ash-0.063
 theirs-0.061
 yours-0.060
uries-0.059
asty-0.059
Token "
Token ID366
Feature activation-9.40e-03

Pos logit contributions
ash+0.022
 theirs+0.022
asty+0.022
uries+0.022
 yours+0.021
Neg logit contributions
 sky-0.026
 voice-0.024
 hawk-0.024
 cage-0.024
-0.023
TokenA
Token ID32
Feature activation-1.57e-02

Pos logit contributions
ash+0.017
uries+0.016
 theirs+0.016
 yours+0.016
wn+0.016
Neg logit contributions
 sky-0.013
 voice-0.012
-0.012
 poster-0.011
 cage-0.011
Tokenbr
Token ID1671
Feature activation-1.60e-01

Pos logit contributions
ash+0.026
 theirs+0.024
uries+0.024
 yours+0.024
iding+0.023
Neg logit contributions
 sky-0.025
-0.023
 voice-0.023
't-0.021
 hawk-0.021
Tokenac
Token ID330
Feature activation-5.50e-02

Pos logit contributions
ash+0.076
 theirs+0.061
uries+0.060
 yours+0.054
asty+0.048
Neg logit contributions
 sky-0.435
 voice-0.419
-0.411
't-0.402
 poster-0.402
Tokenad
Token ID324
Feature activation-7.42e-02

Pos logit contributions
ash+0.084
 yours+0.078
asty+0.075
asting+0.074
ac+0.074
Neg logit contributions
-0.101
 sky-0.096
 poster-0.087
 voice-0.083
't-0.083
Tokenab
Token ID397
Feature activation-6.22e-02

Pos logit contributions
ash+0.106
 theirs+0.101
uries+0.100
uggets+0.095
wn+0.093
Neg logit contributions
 sky-0.132
 voice-0.124
-0.120
't-0.119
 poster-0.119
Tokenra
Token ID430
Feature activation-1.67e-02

Pos logit contributions
ash+0.115
 theirs+0.108
uries+0.106
asting+0.102
wn+0.102
Neg logit contributions
 sky-0.087
 voice-0.085
-0.081
't-0.078
 poster-0.077
Token!"
Token ID2474
Feature activation+2.19e-02

Pos logit contributions
ash+0.030
 theirs+0.029
uries+0.028
 enjoyable+0.028
uggets+0.027
Neg logit contributions
 sky-0.023
't-0.022
 voice-0.022
-0.022
 poster-0.021
Token and
Token ID290
Feature activation+1.89e-02

Pos logit contributions
+0.034
 sky+0.033
 hawk+0.032
 voice+0.031
't+0.031
Neg logit contributions
ash-0.025
 theirs-0.024
asty-0.022
 yours-0.022
 organize-0.022
Token said
Token ID531
Feature activation+3.07e-02

Pos logit contributions
 sky+0.027
 voice+0.024
 poster+0.022
't+0.022
 bird+0.022
Neg logit contributions
ash-0.037
 theirs-0.034
uries-0.033
 yours-0.033
iding-0.033
Token,
Token ID11
Feature activation-1.17e-02

Pos logit contributions
 sky+0.026
 voice+0.024
+0.021
't+0.021
 poster+0.020
Neg logit contributions
ash-0.075
uries-0.070
 theirs-0.070
wn-0.068
 yours-0.068
Token "
Token ID366
Feature activation-9.98e-03

Pos logit contributions
ash+0.018
 theirs+0.017
uries+0.017
iding+0.017
asty+0.017
Neg logit contributions
 sky-0.018
-0.017
 voice-0.017
 hawk-0.017
 cage-0.016
TokenA
Token ID32
Feature activation-2.23e-02

Pos logit contributions
ash+0.021
 theirs+0.021
 yours+0.020
asty+0.019
iding+0.019
Neg logit contributions
 sky-0.013
 voice-0.010
't-0.010
-0.010
 bird-0.009
Tokenbr
Token ID1671
Feature activation-1.59e-01

Pos logit contributions
ash+0.044
 theirs+0.043
uries+0.041
 yours+0.040
asty+0.040
Neg logit contributions
 sky-0.029
 voice-0.027
-0.026
 poster-0.024
 bird-0.024
Tokenac
Token ID330
Feature activation-5.66e-02

Pos logit contributions
ash+0.071
 theirs+0.052
uries+0.049
 yours+0.045
asty+0.039
Neg logit contributions
 sky-0.447
 voice-0.429
-0.426
't-0.414
 poster-0.412
Tokenad
Token ID324
Feature activation-7.67e-02

Pos logit contributions
ash+0.090
 yours+0.081
ams+0.077
ac+0.077
wn+0.076
Neg logit contributions
-0.101
 sky-0.096
 poster-0.087
 crying-0.084
't-0.084
Tokenab
Token ID397
Feature activation-6.27e-02

Pos logit contributions
ash+0.108
 theirs+0.104
uries+0.103
uggets+0.098
asty+0.096
Neg logit contributions
 sky-0.138
 voice-0.128
 poster-0.125
't-0.124
-0.124
Tokenra
Token ID430
Feature activation-2.08e-02

Pos logit contributions
ash+0.122
 theirs+0.116
uries+0.113
 enjoyable+0.113
asting+0.112
Neg logit contributions
 sky-0.081
 voice-0.081
-0.078
't-0.074
 poster-0.073
Token!
Token ID0
Feature activation-3.36e-02

Pos logit contributions
ash+0.035
 theirs+0.033
uries+0.032
uggets+0.032
 enjoyable+0.032
Neg logit contributions
 sky-0.032
 voice-0.031
't-0.031
-0.029
 poster-0.029
Token and
Token ID290
Feature activation+9.40e-03

Pos logit contributions
 sky+0.027
+0.025
 voice+0.024
 poster+0.023
 hawk+0.023
Neg logit contributions
ash-0.035
 theirs-0.034
 yours-0.033
asty-0.033
uries-0.032
Token said
Token ID531
Feature activation+2.92e-02

Pos logit contributions
 sky+0.012
 voice+0.011
 poster+0.010
 bird+0.010
't+0.010
Neg logit contributions
ash-0.020
uries-0.018
iding-0.017
 theirs-0.017
 yours-0.017
Token,
Token ID11
Feature activation-1.55e-02

Pos logit contributions
 sky+0.033
+0.029
 voice+0.028
 hawk+0.026
 poster+0.026
Neg logit contributions
ash-0.061
 theirs-0.059
 yours-0.059
asty-0.058
iding-0.057
Token "
Token ID366
Feature activation-1.06e-02

Pos logit contributions
 theirs+0.021
asty+0.021
ash+0.021
uries+0.020
iding+0.020
Neg logit contributions
 sky-0.026
 hawk-0.025
 voice-0.025
 cage-0.024
-0.024
TokenA
Token ID32
Feature activation-1.67e-02

Pos logit contributions
ash+0.020
uries+0.019
 yours+0.018
wn+0.018
 theirs+0.018
Neg logit contributions
 sky-0.014
 voice-0.013
-0.013
 poster-0.012
 cage-0.012
Tokenbr
Token ID1671
Feature activation-1.58e-01

Pos logit contributions
ash+0.027
 yours+0.026
uries+0.025
 theirs+0.024
 organize+0.024
Neg logit contributions
 sky-0.026
-0.025
 voice-0.024
't-0.023
 hawk-0.022
Tokenac
Token ID330
Feature activation-5.47e-02

Pos logit contributions
ash+0.074
 theirs+0.054
uries+0.050
 yours+0.046
asty+0.040
Neg logit contributions
 sky-0.444
 voice-0.426
-0.423
't-0.411
 poster-0.409
Tokenad
Token ID324
Feature activation-7.33e-02

Pos logit contributions
ash+0.078
 yours+0.075
ac+0.071
ams+0.069
asty+0.069
Neg logit contributions
-0.108
 sky-0.098
 poster-0.091
 crying-0.086
't-0.085
Tokenab
Token ID397
Feature activation-6.13e-02

Pos logit contributions
ash+0.100
 theirs+0.093
uries+0.092
uggets+0.086
 yours+0.086
Neg logit contributions
 sky-0.137
 voice-0.129
-0.126
't-0.123
 poster-0.123
Tokenra
Token ID430
Feature activation-1.51e-02

Pos logit contributions
ash+0.107
 theirs+0.099
uries+0.098
 yours+0.095
wn+0.093
Neg logit contributions
 sky-0.093
 voice-0.087
-0.085
't-0.081
 poster-0.080
Token!
Token ID0
Feature activation-2.92e-02

Pos logit contributions
ash+0.026
 theirs+0.025
uries+0.024
 enjoyable+0.023
uggets+0.023
Neg logit contributions
 sky-0.023
 voice-0.022
't-0.021
-0.021
 poster-0.020
Token there
Token ID612
Feature activation+2.52e-02

Pos logit contributions
 sky+0.065
 voice+0.060
't+0.056
+0.055
 bird+0.055
Neg logit contributions
ash-0.107
uries-0.098
iding-0.096
wn-0.095
 theirs-0.093
Token were
Token ID547
Feature activation+1.25e-02

Pos logit contributions
 sky+0.024
 voice+0.020
 bird+0.019
't+0.019
 hawk+0.018
Neg logit contributions
ash-0.062
wn-0.058
uries-0.058
iding-0.058
uggets-0.056
Token other
Token ID584
Feature activation+1.67e-02

Pos logit contributions
 sky+0.018
 voice+0.016
 bird+0.016
 hawk+0.015
 cage+0.015
Neg logit contributions
ash-0.025
iding-0.022
uries-0.022
aghetti-0.022
wn-0.022
Token long
Token ID890
Feature activation-1.41e-02

Pos logit contributions
 sky+0.020
 voice+0.020
 bird+0.019
 cage+0.016
 crying+0.015
Neg logit contributions
ash-0.036
iding-0.035
wn-0.034
asty-0.033
aghetti-0.033
Token sh
Token ID427
Feature activation-4.88e-02

Pos logit contributions
ash+0.026
uries+0.024
 theirs+0.024
iding+0.024
asty+0.024
Neg logit contributions
 sky-0.021
 voice-0.019
-0.017
 bird-0.017
 cage-0.017
Tokenrim
Token ID3036
Feature activation-1.58e-01

Pos logit contributions
ash+0.056
 theirs+0.053
uries+0.051
 yours+0.051
wn+0.047
Neg logit contributions
 sky-0.101
 voice-0.096
-0.096
't-0.092
 hawk-0.090
Tokenps
Token ID862
Feature activation+7.52e-03

Pos logit contributions
ash+0.294
 enjoyable+0.290
 organize+0.275
uries+0.274
 theirs+0.272
Neg logit contributions
 sky-0.188
 voice-0.182
't-0.175
-0.158
 bird-0.156
Token in
Token ID287
Feature activation-8.69e-03

Pos logit contributions
 sky+0.010
 voice+0.009
 bird+0.008
 crying+0.008
't+0.008
Neg logit contributions
uries-0.014
ash-0.014
uggets-0.014
wn-0.014
aghetti-0.014
Token the
Token ID262
Feature activation+3.29e-02

Pos logit contributions
ash+0.016
 theirs+0.014
uries+0.014
 yours+0.014
iding+0.014
Neg logit contributions
 sky-0.013
 voice-0.012
-0.012
't-0.011
 hawk-0.011
Token ocean
Token ID9151
Feature activation+1.47e-02

Pos logit contributions
 sky+0.045
 voice+0.041
+0.040
't+0.038
 poster+0.038
Neg logit contributions
ash-0.063
 theirs-0.059
uries-0.058
 yours-0.057
iding-0.056
Token.
Token ID13
Feature activation-6.40e-03

Pos logit contributions
 sky+0.019
 voice+0.017
 bird+0.015
 cage+0.015
+0.015
Neg logit contributions
ash-0.030
uries-0.028
wn-0.028
 theirs-0.028
 yours-0.028
Token and
Token ID290
Feature activation+2.12e-02

Pos logit contributions
 sky+0.048
 voice+0.044
+0.043
't+0.041
 poster+0.041
Neg logit contributions
ash-0.054
 theirs-0.050
uries-0.050
 yours-0.049
wn-0.048
Token said
Token ID531
Feature activation+3.81e-02

Pos logit contributions
 sky+0.028
 voice+0.025
 bird+0.023
 poster+0.023
 crying+0.022
Neg logit contributions
ash-0.044
uries-0.041
iding-0.041
 theirs-0.040
aghetti-0.040
Token,
Token ID11
Feature activation-9.98e-03

Pos logit contributions
 sky+0.029
 voice+0.027
't+0.023
 bird+0.022
+0.021
Neg logit contributions
ash-0.098
uries-0.092
 theirs-0.090
wn-0.090
asting-0.088
Token "
Token ID366
Feature activation-7.02e-03

Pos logit contributions
ash+0.017
 theirs+0.016
uries+0.016
asty+0.015
 yours+0.015
Neg logit contributions
 sky-0.015
 voice-0.014
-0.014
 hawk-0.013
 cage-0.013
TokenA
Token ID32
Feature activation-1.65e-02

Pos logit contributions
ash+0.015
 theirs+0.015
uries+0.014
 yours+0.013
iding+0.013
Neg logit contributions
 sky-0.009
 voice-0.007
-0.007
't-0.007
 bird-0.007
Tokenbr
Token ID1671
Feature activation-1.58e-01

Pos logit contributions
ash+0.031
 theirs+0.030
uries+0.028
uggets+0.027
asty+0.027
Neg logit contributions
 sky-0.024
 voice-0.022
-0.021
 poster-0.021
 bird-0.021
Tokenac
Token ID330
Feature activation-5.57e-02

Pos logit contributions
ash+0.086
 theirs+0.072
uries+0.068
 yours+0.063
asty+0.058
Neg logit contributions
 sky-0.424
 voice-0.407
-0.402
 poster-0.390
't-0.390
Tokenad
Token ID324
Feature activation-7.30e-02

Pos logit contributions
ash+0.092
 yours+0.083
asty+0.080
 theirs+0.080
uries+0.079
Neg logit contributions
-0.093
 sky-0.091
 poster-0.081
 voice-0.080
 hawk-0.080
Tokenab
Token ID397
Feature activation-6.21e-02

Pos logit contributions
ash+0.100
 theirs+0.094
uries+0.092
uggets+0.086
 yours+0.086
Neg logit contributions
 sky-0.137
 voice-0.128
-0.124
't-0.122
 poster-0.122
Tokenra
Token ID430
Feature activation-1.80e-02

Pos logit contributions
ash+0.119
 theirs+0.113
uries+0.109
 enjoyable+0.108
asting+0.108
Neg logit contributions
 sky-0.083
 voice-0.083
-0.078
't-0.075
 poster-0.075
Token!
Token ID0
Feature activation-3.21e-02

Pos logit contributions
ash+0.029
 theirs+0.028
uries+0.027
uggets+0.026
 enjoyable+0.026
Neg logit contributions
 sky-0.029
 voice-0.028
't-0.027
-0.026
 poster-0.026
Token She
Token ID1375
Feature activation-4.17e-03

Pos logit contributions
ash+0.051
 theirs+0.049
asty+0.048
 organize+0.047
uggets+0.046
Neg logit contributions
 hawk-0.031
 sky-0.030
 poster-0.029
 voice-0.029
 cage-0.028
Token said
Token ID531
Feature activation+1.94e-02

Pos logit contributions
ash+0.007
 theirs+0.006
uries+0.006
 yours+0.006
wn+0.006
Neg logit contributions
 sky-0.007
-0.006
 voice-0.006
 poster-0.006
't-0.006
Token,
Token ID11
Feature activation-1.82e-02

Pos logit contributions
 sky+0.026
+0.025
 voice+0.023
 poster+0.022
 cage+0.022
Neg logit contributions
ash-0.035
 theirs-0.035
 yours-0.034
asty-0.033
iding-0.032
Token "
Token ID366
Feature activation-1.62e-02

Pos logit contributions
ash+0.027
 theirs+0.026
asty+0.025
 yours+0.025
uries+0.025
Neg logit contributions
 sky-0.029
-0.028
 voice-0.027
 poster-0.026
 cage-0.026
TokenA
Token ID32
Feature activation-2.21e-02

Pos logit contributions
ash+0.027
uries+0.024
 theirs+0.024
 yours+0.024
wn+0.023
Neg logit contributions
 sky-0.025
-0.023
 voice-0.023
 cage-0.022
 poster-0.022
Tokenbr
Token ID1671
Feature activation-1.57e-01

Pos logit contributions
ash+0.041
 theirs+0.038
uries+0.038
 yours+0.037
asty+0.036
Neg logit contributions
 sky-0.032
 voice-0.030
-0.029
't-0.027
 poster-0.027
Tokenac
Token ID330
Feature activation-5.47e-02

Pos logit contributions
ash+0.079
 theirs+0.065
uries+0.063
 yours+0.059
asty+0.053
Neg logit contributions
 sky-0.424
 voice-0.411
-0.403
't-0.393
 poster-0.393
Tokenad
Token ID324
Feature activation-7.56e-02

Pos logit contributions
ash+0.087
 yours+0.078
 theirs+0.075
ac+0.074
ams+0.074
Neg logit contributions
 sky-0.096
-0.095
 poster-0.083
 crying-0.080
 voice-0.080
Tokenab
Token ID397
Feature activation-6.08e-02

Pos logit contributions
ash+0.111
 theirs+0.105
uries+0.104
uggets+0.099
asty+0.098
Neg logit contributions
 sky-0.133
 voice-0.125
-0.120
't-0.119
 poster-0.119
Tokenra
Token ID430
Feature activation-1.71e-02

Pos logit contributions
ash+0.116
 theirs+0.108
uries+0.108
 enjoyable+0.104
asting+0.103
Neg logit contributions
 voice-0.081
 sky-0.081
-0.076
't-0.074
 poster-0.072
Token!"
Token ID2474
Feature activation+1.19e-02

Pos logit contributions
ash+0.035
 theirs+0.034
uries+0.034
 enjoyable+0.033
uggets+0.033
Neg logit contributions
 sky-0.019
't-0.019
 voice-0.018
-0.018
 poster-0.017
Token around
Token ID1088
Feature activation+2.59e-02

Pos logit contributions
+0.003
 sky+0.003
 hawk+0.003
 voice+0.003
 poster+0.003
Neg logit contributions
ash-0.002
wn-0.001
 theirs-0.001
iding-0.001
 yours-0.001
Token and
Token ID290
Feature activation+1.75e-02

Pos logit contributions
+0.043
 sky+0.042
 hawk+0.041
't+0.038
 voice+0.038
Neg logit contributions
 theirs-0.036
ash-0.035
 like-0.035
 organize-0.034
 yours-0.033
Token said
Token ID531
Feature activation+2.80e-02

Pos logit contributions
 sky+0.023
 voice+0.021
+0.019
't+0.019
 poster+0.019
Neg logit contributions
ash-0.035
 theirs-0.032
uries-0.032
 yours-0.032
iding-0.032
Token "
Token ID366
Feature activation-6.89e-03

Pos logit contributions
 sky+0.029
+0.026
 voice+0.025
 hawk+0.023
 poster+0.023
Neg logit contributions
ash-0.061
 theirs-0.059
 yours-0.058
uries-0.057
asty-0.057
TokenA
Token ID32
Feature activation-2.45e-02

Pos logit contributions
ash+0.013
 theirs+0.012
uries+0.012
 yours+0.012
asty+0.012
Neg logit contributions
 sky-0.009
 voice-0.009
-0.009
't-0.008
 poster-0.008
Tokenbr
Token ID1671
Feature activation-1.57e-01

Pos logit contributions
ash+0.039
 yours+0.037
uries+0.036
 theirs+0.035
 organize+0.035
Neg logit contributions
 sky-0.039
-0.037
 voice-0.035
't-0.034
 hawk-0.034
Tokenac
Token ID330
Feature activation-5.59e-02

Pos logit contributions
ash+0.071
 theirs+0.050
uries+0.046
 yours+0.043
wn+0.037
Neg logit contributions
 sky-0.446
 voice-0.426
-0.426
't-0.412
 hawk-0.411
Tokenad
Token ID324
Feature activation-7.70e-02

Pos logit contributions
ash+0.085
 yours+0.079
ac+0.075
wn+0.074
 theirs+0.074
Neg logit contributions
-0.107
 sky-0.099
 poster-0.088
 hawk-0.085
 crying-0.085
Tokenab
Token ID397
Feature activation-6.09e-02

Pos logit contributions
ash+0.108
 theirs+0.101
uries+0.100
uggets+0.095
asty+0.093
Neg logit contributions
 sky-0.140
 voice-0.131
-0.127
't-0.127
 poster-0.127
Tokenra
Token ID430
Feature activation-2.11e-02

Pos logit contributions
ash+0.110
 theirs+0.102
uries+0.101
 yours+0.098
wn+0.097
Neg logit contributions
 sky-0.089
 voice-0.084
-0.081
't-0.078
 poster-0.077
Token!"
Token ID2474
Feature activation+2.07e-02

Pos logit contributions
ash+0.035
 theirs+0.033
uries+0.032
 enjoyable+0.031
uggets+0.031
Neg logit contributions
 sky-0.033
 voice-0.032
't-0.032
-0.030
 poster-0.030
Token it
Token ID340
Feature activation-1.35e-03

Pos logit contributions
ash+0.051
aghetti+0.048
uries+0.048
asting+0.047
ust+0.045
Neg logit contributions
 voice-0.025
 sky-0.023
 bird-0.021
't-0.018
 crying-0.018
Token around
Token ID1088
Feature activation+1.87e-02

Pos logit contributions
ash+0.002
 theirs+0.002
uries+0.002
 yours+0.002
asty+0.002
Neg logit contributions
 sky-0.002
 voice-0.002
-0.002
't-0.002
 poster-0.002
Token.
Token ID13
Feature activation-2.00e-02

Pos logit contributions
 sky+0.030
 voice+0.028
+0.027
't+0.026
 poster+0.026
Neg logit contributions
ash-0.031
uries-0.029
 theirs-0.029
 yours-0.028
iding-0.027
Token "
Token ID366
Feature activation-1.87e-02

Pos logit contributions
ash+0.043
 theirs+0.040
uries+0.040
asty+0.039
 yours+0.039
Neg logit contributions
 sky-0.021
 voice-0.020
 hawk-0.019
 poster-0.018
 cage-0.018
TokenA
Token ID32
Feature activation-1.77e-02

Pos logit contributions
ash+0.037
 theirs+0.036
 yours+0.035
uries+0.034
iding+0.034
Neg logit contributions
 sky-0.025
 voice-0.022
-0.021
't-0.020
 hawk-0.019
Tokenbr
Token ID1671
Feature activation-1.57e-01

Pos logit contributions
ash+0.029
 theirs+0.026
uries+0.026
 yours+0.025
asty+0.025
Neg logit contributions
 sky-0.030
 voice-0.027
-0.027
't-0.026
 poster-0.026
Tokenac
Token ID330
Feature activation-5.01e-02

Pos logit contributions
ash+0.092
 theirs+0.077
uries+0.074
 yours+0.071
asty+0.065
Neg logit contributions
 sky-0.413
 voice-0.396
-0.390
't-0.380
 poster-0.380
Tokenad
Token ID324
Feature activation-7.35e-02

Pos logit contributions
ash+0.083
 yours+0.074
 theirs+0.073
wn+0.071
uries+0.071
Neg logit contributions
-0.085
 sky-0.084
 poster-0.073
 voice-0.073
't-0.073
Tokenab
Token ID397
Feature activation-6.11e-02

Pos logit contributions
ash+0.099
 theirs+0.091
uries+0.089
 yours+0.085
asty+0.084
Neg logit contributions
 sky-0.140
 voice-0.132
-0.128
't-0.125
 poster-0.125
Tokenra
Token ID430
Feature activation-2.06e-02

Pos logit contributions
ash+0.114
 theirs+0.107
uries+0.105
 enjoyable+0.103
asting+0.102
Neg logit contributions
 sky-0.084
 voice-0.084
-0.077
't-0.076
 poster-0.075
Token!"
Token ID2474
Feature activation+1.83e-02

Pos logit contributions
ash+0.035
 theirs+0.034
uries+0.033
uggets+0.032
 enjoyable+0.032
Neg logit contributions
 sky-0.030
 voice-0.029
't-0.029
-0.028
 poster-0.027
Token there
Token ID612
Feature activation+3.06e-02

Pos logit contributions
 theirs+0.001
ash+0.001
 yours+0.001
ust+0.001
iding+0.001
Neg logit contributions
-0.002
 sky-0.002
 hawk-0.002
 voice-0.002
 poster-0.002
Token was
Token ID373
Feature activation-9.99e-04

Pos logit contributions
 sky+0.037
 voice+0.034
+0.034
 poster+0.033
 hawk+0.033
Neg logit contributions
ash-0.060
 theirs-0.057
 yours-0.055
asty-0.054
uries-0.054
Token a
Token ID257
Feature activation+3.35e-03

Pos logit contributions
ash+0.002
 theirs+0.002
 yours+0.002
asty+0.002
uries+0.002
Neg logit contributions
 sky-0.001
 voice-0.001
-0.001
 poster-0.001
 hawk-0.001
Token girl
Token ID2576
Feature activation+1.84e-02

Pos logit contributions
 sky+0.003
 voice+0.003
+0.003
't+0.003
 poster+0.003
Neg logit contributions
ash-0.008
 theirs-0.007
uries-0.007
 yours-0.007
asty-0.007
Token named
Token ID3706
Feature activation-5.51e-03

Pos logit contributions
 sky+0.028
+0.026
 voice+0.026
't+0.024
 poster+0.024
Neg logit contributions
ash-0.032
 theirs-0.029
uries-0.029
 yours-0.028
asty-0.028
Token Sil
Token ID4243
Feature activation-1.57e-01

Pos logit contributions
ash+0.008
 theirs+0.008
uries+0.008
wn+0.007
iding+0.007
Neg logit contributions
 sky-0.010
 voice-0.009
't-0.009
-0.009
 cage-0.008
Tokenvia
Token ID8869
Feature activation-2.94e-02

Pos logit contributions
ash+0.172
 theirs+0.151
uries+0.149
 yours+0.142
iding+0.138
Neg logit contributions
 sky-0.348
 voice-0.331
-0.330
 hawk-0.313
't-0.312
Token.
Token ID13
Feature activation-3.41e-03

Pos logit contributions
ash+0.049
 theirs+0.045
uries+0.045
 yours+0.044
asty+0.043
Neg logit contributions
 sky-0.047
-0.043
 voice-0.043
't-0.041
 poster-0.040
Token She
Token ID1375
Feature activation-2.28e-02

Pos logit contributions
ash+0.006
 theirs+0.006
uries+0.006
 yours+0.006
asty+0.006
Neg logit contributions
 sky-0.004
-0.004
 voice-0.004
 hawk-0.004
 poster-0.004
Token was
Token ID373
Feature activation-6.61e-03

Pos logit contributions
ash+0.033
 theirs+0.030
uries+0.030
 yours+0.030
asty+0.029
Neg logit contributions
 sky-0.040
 voice-0.038
-0.038
 poster-0.036
 hawk-0.036
Token 3
Token ID513
Feature activation+2.22e-02

Pos logit contributions
ash+0.012
 theirs+0.011
 yours+0.011
uries+0.011
asty+0.011
Neg logit contributions
 sky-0.009
-0.009
 voice-0.009
 poster-0.008
 hawk-0.008
Token and
Token ID290
Feature activation+1.54e-02

Pos logit contributions
 sky+0.044
 voice+0.040
+0.039
't+0.037
 hawk+0.036
Neg logit contributions
ash-0.075
 theirs-0.071
uries-0.070
 yours-0.069
asty-0.067
Token said
Token ID531
Feature activation+3.13e-02

Pos logit contributions
 sky+0.022
 voice+0.020
+0.020
't+0.019
 hawk+0.018
Neg logit contributions
ash-0.028
 theirs-0.026
uries-0.026
 yours-0.026
asty-0.025
Token,
Token ID11
Feature activation-1.33e-02

Pos logit contributions
 sky+0.024
 voice+0.022
+0.020
't+0.019
 poster+0.018
Neg logit contributions
ash-0.079
uries-0.075
 theirs-0.074
wn-0.073
 yours-0.072
Token "
Token ID366
Feature activation-1.15e-02

Pos logit contributions
ash+0.021
 theirs+0.020
uries+0.020
asty+0.019
iding+0.019
Neg logit contributions
 sky-0.020
 voice-0.019
 hawk-0.019
-0.019
 cage-0.018
TokenA
Token ID32
Feature activation-1.72e-02

Pos logit contributions
ash+0.020
 theirs+0.019
uries+0.019
 yours+0.018
asty+0.018
Neg logit contributions
 sky-0.017
 voice-0.016
-0.016
't-0.015
 poster-0.015
Tokenbr
Token ID1671
Feature activation-1.56e-01

Pos logit contributions
ash+0.031
 theirs+0.029
uries+0.028
 yours+0.028
asty+0.027
Neg logit contributions
 sky-0.025
 voice-0.023
-0.023
't-0.022
 poster-0.021
Tokenac
Token ID330
Feature activation-5.08e-02

Pos logit contributions
ash+0.072
 theirs+0.052
uries+0.049
 yours+0.045
asty+0.039
Neg logit contributions
 sky-0.439
 voice-0.421
-0.418
't-0.407
 poster-0.405
Tokenad
Token ID324
Feature activation-6.96e-02

Pos logit contributions
ash+0.077
 yours+0.071
ams+0.068
ac+0.067
 theirs+0.065
Neg logit contributions
-0.097
 sky-0.091
 hawk-0.080
't-0.080
 sudden-0.079
Tokenab
Token ID397
Feature activation-5.80e-02

Pos logit contributions
ash+0.099
 theirs+0.093
uries+0.093
uggets+0.088
asty+0.087
Neg logit contributions
 sky-0.126
 voice-0.118
-0.113
 poster-0.113
't-0.111
Tokenra
Token ID430
Feature activation-1.26e-02

Pos logit contributions
ash+0.102
 theirs+0.095
uries+0.093
 yours+0.091
wn+0.090
Neg logit contributions
 sky-0.087
 voice-0.082
-0.080
't-0.076
 poster-0.076
Token,
Token ID11
Feature activation-5.96e-02

Pos logit contributions
ash+0.027
 theirs+0.026
uries+0.026
 enjoyable+0.025
ust+0.025
Neg logit contributions
 sky-0.014
 voice-0.013
't-0.013
-0.012
 poster-0.012
Token Pete
Token ID17542
Feature activation-3.67e-02

Pos logit contributions
ash+0.026
iding+0.025
uries+0.025
wn+0.025
uggets+0.024
Neg logit contributions
 sky-0.014
 voice-0.012
 bird-0.011
't-0.011
 tree-0.010
Token had
Token ID550
Feature activation+7.75e-03

Pos logit contributions
ash+0.074
 theirs+0.070
uries+0.068
 yours+0.068
iding+0.067
Neg logit contributions
 sky-0.047
 voice-0.044
-0.041
't-0.040
 bird-0.039
Token ever
Token ID1683
Feature activation-2.50e-02

Pos logit contributions
 sky+0.011
 voice+0.010
't+0.010
 bird+0.009
 cage+0.009
Neg logit contributions
ash-0.015
iding-0.014
uries-0.013
aghetti-0.013
asty-0.013
Token seen
Token ID1775
Feature activation+1.29e-02

Pos logit contributions
ash+0.043
iding+0.041
uries+0.040
 theirs+0.039
 yours+0.038
Neg logit contributions
 sky-0.040
 voice-0.036
 crying-0.034
 bird-0.033
 cage-0.032
Token sh
Token ID427
Feature activation-5.20e-02

Pos logit contributions
 sky+0.019
 voice+0.016
 bird+0.015
't+0.015
+0.015
Neg logit contributions
ash-0.024
iding-0.023
wn-0.023
uries-0.023
ust-0.023
Tokenrim
Token ID3036
Feature activation-1.56e-01

Pos logit contributions
ash+0.090
 theirs+0.082
uries+0.082
 yours+0.080
asty+0.079
Neg logit contributions
 sky-0.082
 voice-0.075
-0.073
 hawk-0.070
 poster-0.070
Tokenps
Token ID862
Feature activation+1.03e-02

Pos logit contributions
 enjoyable+0.297
ash+0.296
 theirs+0.278
uries+0.275
 kil+0.270
Neg logit contributions
 voice-0.178
't-0.176
 sky-0.175
-0.150
 crying-0.149
Token and
Token ID290
Feature activation+9.93e-03

Pos logit contributions
 sky+0.013
 voice+0.012
't+0.011
 crying+0.010
 bird+0.010
Neg logit contributions
ash-0.021
uries-0.020
uggets-0.020
wn-0.020
aghetti-0.019
Token his
Token ID465
Feature activation-2.12e-03

Pos logit contributions
 sky+0.012
 voice+0.012
't+0.010
 crying+0.010
 bird+0.010
Neg logit contributions
ash-0.021
iding-0.019
wn-0.019
aghetti-0.019
uries-0.019
Token dad
Token ID9955
Feature activation+3.08e-02

Pos logit contributions
ash+0.004
 theirs+0.003
uries+0.003
 yours+0.003
asty+0.003
Neg logit contributions
 sky-0.003
 voice-0.003
-0.003
't-0.003
 hawk-0.003
Token was
Token ID373
Feature activation+2.40e-02

Pos logit contributions
 sky+0.040
 voice+0.038
+0.036
't+0.034
 bird+0.033
Neg logit contributions
ash-0.062
 theirs-0.057
uries-0.056
 yours-0.056
wn-0.056
Token and
Token ID290
Feature activation+2.00e-02

Pos logit contributions
 sky+0.019
+0.018
 voice+0.017
 hawk+0.017
't+0.017
Neg logit contributions
ash-0.027
 theirs-0.025
uries-0.025
iding-0.024
 organize-0.024
Token said
Token ID531
Feature activation+3.68e-02

Pos logit contributions
 sky+0.028
 voice+0.026
+0.026
't+0.024
 poster+0.024
Neg logit contributions
ash-0.037
 theirs-0.034
uries-0.034
 yours-0.033
asty-0.033
Token,
Token ID11
Feature activation-1.20e-02

Pos logit contributions
 sky+0.034
 voice+0.029
+0.029
't+0.026
 poster+0.025
Neg logit contributions
ash-0.087
 theirs-0.082
uries-0.081
 yours-0.080
wn-0.079
Token "
Token ID366
Feature activation-6.90e-03

Pos logit contributions
ash+0.018
 theirs+0.018
asty+0.017
uries+0.017
iding+0.017
Neg logit contributions
 sky-0.019
 voice-0.018
 hawk-0.017
-0.017
 cage-0.017
TokenA
Token ID32
Feature activation-1.23e-02

Pos logit contributions
ash+0.013
 theirs+0.013
uries+0.012
 yours+0.012
iding+0.012
Neg logit contributions
 sky-0.009
 voice-0.008
-0.008
't-0.008
 hawk-0.008
Tokenbr
Token ID1671
Feature activation-1.55e-01

Pos logit contributions
ash+0.022
 theirs+0.021
uries+0.020
 yours+0.020
asty+0.019
Neg logit contributions
 sky-0.018
 voice-0.017
-0.016
't-0.016
 hawk-0.016
Tokenac
Token ID330
Feature activation-5.16e-02

Pos logit contributions
ash+0.075
 theirs+0.064
uries+0.064
 yours+0.057
 organize+0.052
Neg logit contributions
 sky-0.417
 voice-0.402
-0.396
 poster-0.385
 cage-0.384
Tokenad
Token ID324
Feature activation-7.10e-02

Pos logit contributions
ash+0.076
 yours+0.070
asty+0.067
asting+0.067
ac+0.067
Neg logit contributions
-0.097
 sky-0.094
 poster-0.086
 crying-0.082
 voice-0.081
Tokenab
Token ID397
Feature activation-5.91e-02

Pos logit contributions
ash+0.101
 theirs+0.094
uries+0.094
uggets+0.088
 organize+0.088
Neg logit contributions
 sky-0.128
 voice-0.120
-0.116
't-0.115
 poster-0.114
Tokenra
Token ID430
Feature activation-1.51e-02

Pos logit contributions
ash+0.111
 theirs+0.104
uries+0.103
wn+0.099
 enjoyable+0.099
Neg logit contributions
 sky-0.081
 voice-0.080
-0.076
't-0.073
 poster-0.071
Token!"
Token ID2474
Feature activation+2.21e-02

Pos logit contributions
ash+0.027
 theirs+0.026
uries+0.025
 enjoyable+0.025
uggets+0.025
Neg logit contributions
 sky-0.021
't-0.021
 voice-0.020
-0.020
 bird-0.019
Token stove
Token ID27635
Feature activation+7.29e-03

Pos logit contributions
 sky+0.027
 voice+0.024
+0.022
 cage+0.021
 poster+0.021
Neg logit contributions
ash-0.039
 theirs-0.037
uries-0.036
 yours-0.036
iding-0.036
Token -
Token ID532
Feature activation-1.95e-02

Pos logit contributions
 sky+0.010
 voice+0.009
+0.008
't+0.008
 bird+0.008
Neg logit contributions
ash-0.015
uries-0.014
 theirs-0.014
 yours-0.014
wn-0.013
Token two
Token ID734
Feature activation+3.64e-03

Pos logit contributions
ash+0.044
uries+0.041
iding+0.040
wn+0.040
ust+0.039
Neg logit contributions
 sky-0.024
 voice-0.020
-0.019
't-0.018
 bird-0.018
Token more
Token ID517
Feature activation-2.49e-02

Pos logit contributions
 sky+0.005
 voice+0.005
+0.004
 bird+0.004
 cage+0.004
Neg logit contributions
ash-0.007
 yours-0.007
uries-0.007
 theirs-0.007
asty-0.006
Token sh
Token ID427
Feature activation-6.18e-02

Pos logit contributions
ash+0.043
uries+0.043
iding+0.040
 yours+0.040
ust+0.040
Neg logit contributions
 sky-0.040
 voice-0.037
 bird-0.033
-0.032
 crying-0.032
Tokenrim
Token ID3036
Feature activation-1.55e-01

Pos logit contributions
ash+0.077
 theirs+0.070
uries+0.068
 yours+0.067
asty+0.064
Neg logit contributions
 sky-0.125
 voice-0.118
-0.117
't-0.112
 poster-0.111
Tokenps
Token ID862
Feature activation+4.09e-03

Pos logit contributions
ash+0.284
 enjoyable+0.273
 organize+0.268
uries+0.266
 theirs+0.265
Neg logit contributions
 sky-0.185
 voice-0.176
't-0.166
 crying-0.155
-0.151
Token!
Token ID0
Feature activation-3.50e-03

Pos logit contributions
 sky+0.006
 voice+0.005
 bird+0.005
 crying+0.005
+0.005
Neg logit contributions
ash-0.008
uries-0.008
 yours-0.007
uggets-0.007
ust-0.007
Token His
Token ID2399
Feature activation-1.33e-03

Pos logit contributions
ash+0.006
 theirs+0.005
uries+0.005
 yours+0.005
wn+0.005
Neg logit contributions
 sky-0.006
 voice-0.005
-0.005
't-0.005
 hawk-0.005
Token dad
Token ID9955
Feature activation+2.75e-02

Pos logit contributions
ash+0.002
 theirs+0.002
uries+0.002
 yours+0.002
asty+0.002
Neg logit contributions
 sky-0.002
-0.002
 voice-0.002
't-0.002
 hawk-0.002
Token had
Token ID550
Feature activation+2.26e-02

Pos logit contributions
 sky+0.036
 voice+0.033
+0.033
't+0.030
 poster+0.030
Neg logit contributions
ash-0.053
 theirs-0.050
uries-0.049
 yours-0.049
asty-0.047
Token before
Token ID878
Feature activation+3.90e-02

Pos logit contributions
 sky+0.001
 voice+0.001
't+0.001
 bird+0.001
 crying+0.001
Neg logit contributions
ash-0.002
uries-0.002
uggets-0.002
 yours-0.002
 theirs-0.002
Token.
Token ID13
Feature activation-1.07e-02

Pos logit contributions
+0.062
 sky+0.062
 poster+0.061
 hawk+0.059
 voice+0.059
Neg logit contributions
 theirs-0.053
ash-0.051
asty-0.050
 yours-0.049
 organize-0.048
Token
Token ID198
Feature activation-6.67e-03

Pos logit contributions
ash+0.017
uries+0.017
 theirs+0.017
 yours+0.016
asty+0.016
Neg logit contributions
 sky-0.016
 voice-0.015
-0.015
 poster-0.015
 hawk-0.015
Token
Token ID198
Feature activation-6.56e-03

Pos logit contributions
ash+0.012
iding+0.011
uries+0.011
asting+0.011
 organize+0.011
Neg logit contributions
 sky-0.009
 hawk-0.008
-0.008
 poster-0.008
 voice-0.007
Token"
Token ID1
Feature activation-7.28e-04

Pos logit contributions
ash+0.011
uries+0.010
iding+0.010
wn+0.010
 theirs+0.010
Neg logit contributions
 sky-0.010
-0.010
 voice-0.009
 poster-0.009
 hawk-0.008
TokenSil
Token ID15086
Feature activation-1.55e-01

Pos logit contributions
ash+0.001
 theirs+0.001
uries+0.001
 yours+0.001
asty+0.001
Neg logit contributions
 sky-0.001
 voice-0.001
-0.001
't-0.001
 poster-0.001
Tokenv
Token ID85
Feature activation-2.26e-02

Pos logit contributions
ash+0.156
 theirs+0.151
 yours+0.144
 organize+0.141
asty+0.140
Neg logit contributions
 sky-0.318
 voice-0.302
-0.294
 poster-0.292
't-0.291
Tokenie
Token ID494
Feature activation-2.04e-02

Pos logit contributions
ash+0.033
ac+0.027
 yours+0.027
 theirs+0.027
asting+0.027
Neg logit contributions
 sky-0.042
-0.040
 poster-0.037
 hawk-0.036
't-0.036
Token,"
Token ID553
Feature activation+5.75e-02

Pos logit contributions
ash+0.042
 theirs+0.039
 yours+0.039
uries+0.039
asty+0.038
Neg logit contributions
 sky-0.024
-0.022
 voice-0.020
 poster-0.019
't-0.019
Token he
Token ID339
Feature activation-1.42e-02

Pos logit contributions
+0.089
 sky+0.084
 poster+0.071
't+0.071
 hawk+0.071
Neg logit contributions
 theirs-0.088
 organize-0.085
 remember-0.084
ash-0.083
 yours-0.083
Token called
Token ID1444
Feature activation-2.27e-02

Pos logit contributions
ash+0.029
 theirs+0.027
uries+0.026
ust+0.026
 yours+0.026
Neg logit contributions
 sky-0.017
-0.016
 poster-0.014
 voice-0.014
't-0.014
Token day
Token ID1110
Feature activation+5.42e-02

Pos logit contributions
ash+0.082
uries+0.078
 theirs+0.076
 yours+0.075
iding+0.074
Neg logit contributions
 sky-0.058
 voice-0.052
-0.049
 bird-0.048
't-0.047
Token,
Token ID11
Feature activation-2.96e-02

Pos logit contributions
 sky+0.050
 voice+0.043
+0.042
't+0.038
 poster+0.038
Neg logit contributions
ash-0.127
 theirs-0.120
uries-0.119
 yours-0.118
asty-0.116
Token he
Token ID339
Feature activation-1.87e-02

Pos logit contributions
ash+0.044
uries+0.040
 theirs+0.039
 yours+0.038
iding+0.037
Neg logit contributions
 sky-0.054
 voice-0.050
-0.050
't-0.048
 hawk-0.047
Token went
Token ID1816
Feature activation+1.45e-03

Pos logit contributions
ash+0.036
 theirs+0.034
uries+0.034
 yours+0.033
iding+0.033
Neg logit contributions
 sky-0.026
 voice-0.024
-0.022
't-0.022
 bird-0.021
Token to
Token ID284
Feature activation+3.50e-02

Pos logit contributions
 sky+0.002
+0.002
 voice+0.002
 hawk+0.002
 poster+0.002
Neg logit contributions
ash-0.002
 theirs-0.002
 yours-0.002
uries-0.002
wn-0.002
Token the
Token ID262
Feature activation+4.34e-02

Pos logit contributions
 sky+0.054
 voice+0.050
+0.050
't+0.047
 hawk+0.047
Neg logit contributions
ash-0.060
 theirs-0.056
uries-0.055
 yours-0.054
asty-0.053
Token park
Token ID3952
Feature activation+3.10e-02

Pos logit contributions
 sky+0.039
+0.039
 voice+0.038
 hawk+0.034
't+0.033
Neg logit contributions
ash-0.095
 yours-0.090
 organize-0.090
 theirs-0.090
uries-0.090
Token to
Token ID284
Feature activation+1.59e-02

Pos logit contributions
 sky+0.050
+0.046
 voice+0.046
 hawk+0.045
 poster+0.043
Neg logit contributions
ash-0.051
 theirs-0.047
uries-0.046
 yours-0.045
 organize-0.044
Token play
Token ID711
Feature activation+3.49e-03

Pos logit contributions
 sky+0.028
 voice+0.026
+0.025
't+0.025
 poster+0.024
Neg logit contributions
ash-0.026
iding-0.023
uries-0.023
 theirs-0.023
ust-0.023
Token with
Token ID351
Feature activation-5.24e-02

Pos logit contributions
 sky+0.006
 voice+0.005
+0.005
't+0.005
 bird+0.005
Neg logit contributions
ash-0.006
uries-0.006
 theirs-0.005
 yours-0.005
ust-0.005
Token his
Token ID465
Feature activation-1.10e-03

Pos logit contributions
ash+0.078
uries+0.075
iding+0.071
ust+0.068
wn+0.068
Neg logit contributions
 sky-0.097
 voice-0.091
 bird-0.087
't-0.087
-0.086
Token was
Token ID373
Feature activation+1.25e-02

Pos logit contributions
 sky+0.033
+0.031
 voice+0.030
 hawk+0.028
't+0.028
Neg logit contributions
ash-0.046
uries-0.042
 theirs-0.042
 yours-0.041
 organize-0.041
Token so
Token ID523
Feature activation+1.54e-02

Pos logit contributions
 sky+0.017
 voice+0.016
't+0.014
+0.014
 bird+0.014
Neg logit contributions
ash-0.024
uries-0.022
 theirs-0.022
 yours-0.022
aghetti-0.022
Token excited
Token ID6568
Feature activation+4.76e-02

Pos logit contributions
 sky+0.021
 voice+0.019
+0.018
't+0.018
 poster+0.017
Neg logit contributions
ash-0.031
uries-0.028
 theirs-0.028
 yours-0.027
wn-0.027
Token that
Token ID326
Feature activation-6.39e-03

Pos logit contributions
 sky+0.052
 voice+0.047
+0.042
't+0.042
 bird+0.040
Neg logit contributions
ash-0.105
uries-0.100
 theirs-0.098
wn-0.097
 yours-0.096
Token he
Token ID339
Feature activation-2.79e-02

Pos logit contributions
ash+0.016
wn+0.015
uries+0.015
aghetti+0.015
iding+0.015
Neg logit contributions
 sky-0.006
 voice-0.006
 bird-0.005
't-0.005
 hawk-0.004
Token decided
Token ID3066
Feature activation+4.07e-02

Pos logit contributions
ash+0.059
 theirs+0.055
uggets+0.055
wn+0.054
uries+0.054
Neg logit contributions
 sky-0.035
 voice-0.033
't-0.031
 bird-0.031
-0.028
Token to
Token ID284
Feature activation+3.28e-02

Pos logit contributions
 sky+0.045
 voice+0.042
't+0.040
 bird+0.036
 poster+0.035
Neg logit contributions
ash-0.093
uries-0.083
wn-0.082
aghetti-0.082
uggets-0.081
Token join
Token ID4654
Feature activation-6.94e-02

Pos logit contributions
 voice+0.061
 sky+0.061
't+0.059
+0.055
 bird+0.055
Neg logit contributions
ash-0.050
 theirs-0.044
aghetti-0.042
uggets-0.042
wn-0.042
Token them
Token ID606
Feature activation-9.92e-03

Pos logit contributions
ash+0.127
uries+0.122
wn+0.117
ust+0.114
 theirs+0.113
Neg logit contributions
 sky-0.100
 voice-0.098
't-0.086
 bird-0.085
-0.084
Token and
Token ID290
Feature activation+1.65e-02

Pos logit contributions
ash+0.020
wn+0.018
uries+0.018
 theirs+0.018
aghetti+0.018
Neg logit contributions
 sky-0.013
 voice-0.012
't-0.011
 bird-0.011
 poster-0.011
Token start
Token ID923
Feature activation+3.00e-03

Pos logit contributions
 sky+0.029
 voice+0.028
't+0.026
 bird+0.026
 tree+0.025
Neg logit contributions
ash-0.028
aghetti-0.024
iding-0.024
wn-0.024
uries-0.023
Token.
Token ID13
Feature activation-2.22e-02

Pos logit contributions
ash+0.126
 theirs+0.125
uries+0.123
uggets+0.120
 yours+0.120
Neg logit contributions
 sky-0.071
 voice-0.066
't-0.061
 bird-0.059
 cage-0.058
Token Ben
Token ID3932
Feature activation-3.91e-04

Pos logit contributions
ash+0.042
 theirs+0.040
 yours+0.039
uries+0.039
asty+0.038
Neg logit contributions
 sky-0.029
 voice-0.027
-0.027
 poster-0.025
 hawk-0.025
Token and
Token ID290
Feature activation+1.34e-02

Pos logit contributions
ash+0.001
 theirs+0.001
uries+0.001
 yours+0.001
 organize+0.001
Neg logit contributions
 sky-0.000
-0.000
 voice-0.000
 hawk-0.000
't-0.000
Token Tom
Token ID4186
Feature activation+1.26e-02

Pos logit contributions
 sky+0.023
 voice+0.023
 bird+0.021
 crying+0.020
 poster+0.020
Neg logit contributions
ash-0.023
uries-0.021
iding-0.020
asting-0.020
aghetti-0.020
Token are
Token ID389
Feature activation-3.76e-03

Pos logit contributions
 sky+0.022
 voice+0.021
+0.020
't+0.019
 poster+0.019
Neg logit contributions
ash-0.019
 theirs-0.018
uries-0.017
 yours-0.017
asty-0.017
Token scared
Token ID12008
Feature activation+4.33e-02

Pos logit contributions
ash+0.010
uries+0.010
aghetti+0.010
 yours+0.009
iding+0.009
Neg logit contributions
 sky-0.003
 voice-0.002
 crying-0.002
 cage-0.002
't-0.002
Token.
Token ID13
Feature activation-8.97e-03

Pos logit contributions
 sky+0.063
 voice+0.058
+0.054
't+0.053
 bird+0.052
Neg logit contributions
ash-0.080
uries-0.075
 theirs-0.074
 yours-0.072
wn-0.072
Token They
Token ID1119
Feature activation-4.57e-03

Pos logit contributions
ash+0.014
 theirs+0.013
uries+0.013
 yours+0.012
asty+0.012
Neg logit contributions
 sky-0.015
-0.014
 voice-0.014
 poster-0.013
 hawk-0.013
Token want
Token ID765
Feature activation+1.73e-02

Pos logit contributions
ash+0.007
 theirs+0.007
uries+0.006
 yours+0.006
asty+0.006
Neg logit contributions
 sky-0.008
 voice-0.007
-0.007
't-0.007
 poster-0.007
Token to
Token ID284
Feature activation+3.06e-02

Pos logit contributions
 sky+0.023
 voice+0.022
't+0.020
 bird+0.020
 cage+0.019
Neg logit contributions
ash-0.035
iding-0.032
uries-0.032
ust-0.031
wn-0.031
Token stop
Token ID2245
Feature activation+3.84e-03

Pos logit contributions
 voice+0.058
 sky+0.058
't+0.056
 bird+0.053
+0.053
Neg logit contributions
ash-0.045
 theirs-0.038
uries-0.038
iding-0.038
uggets-0.037
Token time
Token ID640
Feature activation-7.09e-04

Pos logit contributions
ash+0.026
uries+0.024
 theirs+0.024
iding+0.024
 yours+0.023
Neg logit contributions
 sky-0.018
 voice-0.016
-0.015
 bird-0.015
 cage-0.015
Token.
Token ID13
Feature activation-2.53e-02

Pos logit contributions
ash+0.002
wn+0.001
uries+0.001
ust+0.001
iding+0.001
Neg logit contributions
 sky-0.001
 voice-0.001
-0.001
 bird-0.001
't-0.001
Token They
Token ID1119
Feature activation-2.09e-02

Pos logit contributions
ash+0.050
 theirs+0.048
uries+0.047
 yours+0.046
asty+0.045
Neg logit contributions
 sky-0.032
 voice-0.029
-0.028
 hawk-0.027
 poster-0.027
Token learned
Token ID4499
Feature activation+2.46e-02

Pos logit contributions
ash+0.040
 theirs+0.037
uries+0.037
 yours+0.036
iding+0.036
Neg logit contributions
 sky-0.029
 voice-0.027
-0.026
't-0.024
 hawk-0.024
Token their
Token ID511
Feature activation-1.75e-02

Pos logit contributions
 sky+0.041
+0.039
 voice+0.037
 hawk+0.035
't+0.035
Neg logit contributions
ash-0.039
 theirs-0.039
 yours-0.036
asty-0.035
uries-0.035
Token lesson
Token ID11483
Feature activation+6.44e-02

Pos logit contributions
ash+0.025
 theirs+0.025
 organize+0.024
 yours+0.024
 enjoyable+0.023
Neg logit contributions
 sky-0.030
-0.030
 voice-0.027
 hawk-0.027
't-0.027
Token.
Token ID13
Feature activation-1.69e-02

Pos logit contributions
 sky+0.098
+0.093
 voice+0.090
 hawk+0.085
 poster+0.085
Neg logit contributions
ash-0.112
 theirs-0.106
uries-0.102
 yours-0.101
asty-0.098
Token They
Token ID1119
Feature activation-1.02e-02

Pos logit contributions
ash+0.030
 theirs+0.029
uries+0.028
 yours+0.028
uggets+0.028
Neg logit contributions
 sky-0.023
 voice-0.022
-0.022
 hawk-0.021
 poster-0.021
Token were
Token ID547
Feature activation-5.72e-04

Pos logit contributions
ash+0.018
 theirs+0.017
uries+0.017
 yours+0.016
asty+0.016
Neg logit contributions
 sky-0.015
 voice-0.014
-0.014
't-0.013
 poster-0.013
Token happy
Token ID3772
Feature activation+5.75e-02

Pos logit contributions
ash+0.001
uries+0.001
iding+0.001
aghetti+0.001
rated+0.001
Neg logit contributions
 sky-0.001
 voice-0.001
 crying-0.001
 bird-0.001
 cage-0.001
Token and
Token ID290
Feature activation+3.21e-02

Pos logit contributions
 sky+0.079
+0.073
 voice+0.072
't+0.067
 hawk+0.067
Neg logit contributions
ash-0.108
 theirs-0.102
uries-0.099
 yours-0.099
asty-0.096
Token into
Token ID656
Feature activation+7.53e-03

Pos logit contributions
ash+0.023
uries+0.021
 theirs+0.021
iding+0.020
 yours+0.020
Neg logit contributions
 sky-0.023
 voice-0.021
-0.019
't-0.019
 bird-0.019
Token a
Token ID257
Feature activation+2.13e-02

Pos logit contributions
 sky+0.010
 voice+0.010
+0.009
 cage+0.008
 bird+0.008
Neg logit contributions
ash-0.015
uries-0.014
iding-0.014
wn-0.013
 theirs-0.013
Token wonderful
Token ID7932
Feature activation-1.85e-02

Pos logit contributions
 sky+0.031
+0.030
't+0.029
 voice+0.028
 poster+0.027
Neg logit contributions
ash-0.035
 yours-0.033
 theirs-0.033
uries-0.033
 organize-0.032
Token adventure
Token ID8855
Feature activation+1.60e-02

Pos logit contributions
ash+0.034
 theirs+0.031
uries+0.031
 yours+0.031
wn+0.030
Neg logit contributions
 sky-0.026
-0.024
 voice-0.024
't-0.023
 poster-0.022
Token!
Token ID0
Feature activation-1.91e-03

Pos logit contributions
 sky+0.023
 voice+0.020
+0.019
 bird+0.019
't+0.019
Neg logit contributions
ash-0.030
uries-0.029
 theirs-0.028
uggets-0.028
asty-0.028
Token<|endoftext|>
Token ID50256
Feature activation+6.25e-02

Pos logit contributions
ash+0.005
 theirs+0.005
uries+0.004
 yours+0.004
asty+0.004
Neg logit contributions
 sky-0.001
 voice-0.001
-0.001
 poster-0.001
 hawk-0.001
TokenOne
Token ID3198
Feature activation-4.42e-02

Pos logit contributions
 voice+0.050
 hawk+0.046
 poster+0.046
 sky+0.046
+0.042
Neg logit contributions
ash-0.146
 theirs-0.131
 yours-0.129
asting-0.128
 organize-0.127
Token day
Token ID1110
Feature activation+7.32e-02

Pos logit contributions
ash+0.084
uries+0.082
 theirs+0.080
 yours+0.078
uggets+0.077
Neg logit contributions
 sky-0.061
 voice-0.055
-0.051
 bird-0.050
't-0.049
Token,
Token ID11
Feature activation-1.50e-02

Pos logit contributions
 sky+0.055
 voice+0.048
+0.046
't+0.044
 bird+0.036
Neg logit contributions
ash-0.187
uries-0.179
 theirs-0.177
wn-0.173
 yours-0.173
Token Joe
Token ID5689
Feature activation-1.27e-02

Pos logit contributions
ash+0.029
 theirs+0.027
uries+0.026
 yours+0.026
asty+0.025
Neg logit contributions
 sky-0.021
 voice-0.019
-0.019
't-0.017
 hawk-0.017
Token went
Token ID1816
Feature activation+1.72e-02

Pos logit contributions
ash+0.027
uries+0.025
 theirs+0.025
iding+0.024
 yours+0.024
Neg logit contributions
 sky-0.015
 voice-0.014
-0.012
't-0.012
 bird-0.012
Token the
Token ID262
Feature activation+2.06e-02

Pos logit contributions
 sky+0.011
 voice+0.011
+0.011
 poster+0.010
't+0.010
Neg logit contributions
ash-0.013
 theirs-0.013
 yours-0.012
uries-0.012
asty-0.012
Token little
Token ID1310
Feature activation+2.50e-02

Pos logit contributions
+0.020
't+0.018
 poster+0.018
iren+0.017
 crying+0.016
Neg logit contributions
asting-0.039
 enjoyable-0.038
 remember-0.037
ash-0.037
 activity-0.037
Token bird
Token ID6512
Feature activation+3.94e-03

Pos logit contributions
+0.025
't+0.023
 poster+0.020
 sky+0.020
 devastated+0.018
Neg logit contributions
 theirs-0.051
ash-0.050
 yours-0.050
 enjoyable-0.049
 remember-0.048
Token filled
Token ID5901
Feature activation-7.97e-03

Pos logit contributions
 sky+0.006
+0.006
 poster+0.006
't+0.006
 voice+0.006
Neg logit contributions
ash-0.006
asting-0.005
 remember-0.005
wn-0.005
 organize-0.005
Token his
Token ID465
Feature activation+1.32e-02

Pos logit contributions
 theirs+0.011
ash+0.011
 yours+0.011
asty+0.010
uggets+0.010
Neg logit contributions
 sky-0.014
-0.014
 voice-0.013
 poster-0.013
't-0.012
Token wings
Token ID12098
Feature activation-2.19e-04

Pos logit contributions
't+0.015
 sky+0.015
+0.015
 poster+0.014
 hawk+0.013
Neg logit contributions
ash-0.025
 yours-0.024
uries-0.023
 theirs-0.023
wn-0.023
Token with
Token ID351
Feature activation-3.84e-02

Pos logit contributions
ash+0.000
 theirs+0.000
uries+0.000
 yours+0.000
iding+0.000
Neg logit contributions
 sky-0.000
-0.000
 voice-0.000
 poster-0.000
't-0.000
Token tw
Token ID665
Feature activation-5.68e-02

Pos logit contributions
ash+0.063
 theirs+0.060
 yours+0.057
uries+0.057
asty+0.056
Neg logit contributions
 sky-0.061
-0.057
 voice-0.056
't-0.054
 poster-0.054
Tokenigs
Token ID9235
Feature activation-6.19e-02

Pos logit contributions
ash+0.093
 theirs+0.085
uries+0.084
 yours+0.083
asty+0.081
Neg logit contributions
 sky-0.093
 voice-0.087
-0.085
't-0.081
 poster-0.081
Token,
Token ID11
Feature activation-2.12e-02

Pos logit contributions
ash+0.126
 theirs+0.122
 yours+0.118
uries+0.116
iding+0.116
Neg logit contributions
 sky-0.071
 voice-0.065
-0.065
 poster-0.061
 hawk-0.060
Token the
Token ID262
Feature activation+2.48e-02

Pos logit contributions
ash+0.042
uries+0.039
 theirs+0.038
 yours+0.038
iding+0.037
Neg logit contributions
 sky-0.029
 voice-0.026
-0.025
 hawk-0.024
't-0.024
Token their
Token ID511
Feature activation-1.03e-03

Pos logit contributions
 sky+0.022
 voice+0.020
+0.018
 hawk+0.017
 bird+0.017
Neg logit contributions
ash-0.042
uries-0.039
 theirs-0.038
 yours-0.038
iding-0.038
Token broken
Token ID5445
Feature activation+3.78e-02

Pos logit contributions
ash+0.002
 theirs+0.002
 yours+0.002
uries+0.002
wn+0.001
Neg logit contributions
 sky-0.002
-0.002
 voice-0.001
 hawk-0.001
't-0.001
Token blocks
Token ID7021
Feature activation-7.29e-03

Pos logit contributions
 sky+0.057
+0.055
 voice+0.053
't+0.051
 hawk+0.050
Neg logit contributions
ash-0.064
 theirs-0.061
 yours-0.059
uries-0.058
iding-0.056
Token.
Token ID13
Feature activation-1.72e-02

Pos logit contributions
ash+0.013
 theirs+0.012
uries+0.011
 yours+0.011
asty+0.011
Neg logit contributions
 sky-0.011
 voice-0.010
-0.010
't-0.010
 poster-0.010
Token They
Token ID1119
Feature activation-1.01e-02

Pos logit contributions
ash+0.030
 theirs+0.030
uggets+0.029
uries+0.028
asty+0.028
Neg logit contributions
 sky-0.022
 voice-0.022
 poster-0.022
 hawk-0.021
 cage-0.020
Token felt
Token ID2936
Feature activation-9.86e-03

Pos logit contributions
ash+0.017
 theirs+0.016
uries+0.016
 organize+0.015
asty+0.015
Neg logit contributions
 sky-0.014
-0.014
 voice-0.013
 poster-0.013
 hawk-0.013
Token sorry
Token ID7926
Feature activation+2.31e-02

Pos logit contributions
ash+0.022
 theirs+0.021
uries+0.021
 yours+0.020
iding+0.020
Neg logit contributions
 sky-0.010
 voice-0.009
-0.009
't-0.008
 hawk-0.008
Token and
Token ID290
Feature activation+2.75e-02

Pos logit contributions
 sky+0.045
 voice+0.042
+0.042
't+0.040
 poster+0.040
Neg logit contributions
ash-0.031
 theirs-0.028
uries-0.027
 yours-0.027
wn-0.026
Token scared
Token ID12008
Feature activation+3.01e-02

Pos logit contributions
+0.034
 sky+0.033
't+0.029
 poster+0.028
 hawk+0.027
Neg logit contributions
 theirs-0.053
ash-0.052
 yours-0.051
 organize-0.050
asty-0.050
Token.
Token ID13
Feature activation-9.62e-03

Pos logit contributions
 sky+0.041
 voice+0.039
't+0.035
 bird+0.035
+0.034
Neg logit contributions
ash-0.059
uries-0.057
wn-0.055
 theirs-0.054
 yours-0.054
Token
Token ID198
Feature activation-1.28e-03

Pos logit contributions
ash+0.020
 theirs+0.020
uggets+0.019
uries+0.019
 yours+0.018
Neg logit contributions
 sky-0.010
 poster-0.009
 voice-0.009
 hawk-0.009
-0.009
Token opened
Token ID4721
Feature activation-8.67e-03

Pos logit contributions
 sky+0.024
 voice+0.022
+0.022
 bird+0.021
 cage+0.020
Neg logit contributions
ash-0.028
 yours-0.026
 theirs-0.026
uries-0.026
asty-0.024
Token it
Token ID340
Feature activation+6.27e-03

Pos logit contributions
 theirs+0.012
ash+0.012
 yours+0.012
asty+0.011
 organize+0.010
Neg logit contributions
-0.015
 sky-0.015
 voice-0.014
 hawk-0.014
 poster-0.014
Token and
Token ID290
Feature activation+2.52e-03

Pos logit contributions
 sky+0.009
 hawk+0.009
+0.009
 voice+0.008
 poster+0.008
Neg logit contributions
ash-0.011
 theirs-0.010
uries-0.010
iding-0.010
 organize-0.010
Token saw
Token ID2497
Feature activation+2.07e-03

Pos logit contributions
 sky+0.003
 voice+0.003
+0.003
't+0.003
 bird+0.003
Neg logit contributions
ash-0.005
uries-0.005
 theirs-0.005
 yours-0.005
iding-0.005
Token inside
Token ID2641
Feature activation+1.17e-02

Pos logit contributions
+0.003
 sky+0.003
 voice+0.003
 poster+0.003
't+0.003
Neg logit contributions
 theirs-0.003
ash-0.003
 yours-0.003
asty-0.003
uries-0.003
Token it
Token ID340
Feature activation+2.24e-03

Pos logit contributions
 sky+0.015
 voice+0.014
't+0.013
+0.013
 bird+0.012
Neg logit contributions
ash-0.024
uries-0.023
wn-0.022
 theirs-0.022
aghetti-0.021
Token were
Token ID547
Feature activation-6.03e-03

Pos logit contributions
 sky+0.003
 voice+0.003
+0.003
't+0.003
 bird+0.002
Neg logit contributions
ash-0.004
 theirs-0.004
uries-0.004
 yours-0.004
wn-0.004
Token lots
Token ID6041
Feature activation-1.09e-02

Pos logit contributions
ash+0.013
iding+0.011
uries+0.011
aghetti+0.011
ales+0.011
Neg logit contributions
 sky-0.009
 voice-0.008
 cage-0.007
 tree-0.007
 bird-0.007
Token of
Token ID286
Feature activation-4.41e-02

Pos logit contributions
ash+0.020
uries+0.019
 theirs+0.019
 yours+0.018
iding+0.018
Neg logit contributions
 sky-0.016
 voice-0.015
-0.014
 bird-0.013
 cage-0.013
Token photos
Token ID5205
Feature activation-1.91e-02

Pos logit contributions
ash+0.078
uries+0.072
 theirs+0.072
iding+0.071
 yours+0.070
Neg logit contributions
 sky-0.069
 voice-0.063
-0.058
 cage-0.057
 poster-0.057
Token.
Token ID13
Feature activation-7.02e-03

Pos logit contributions
ash+0.037
uries+0.036
asty+0.035
 theirs+0.035
wn+0.034
Neg logit contributions
 sky-0.027
-0.022
 voice-0.022
't-0.022
 bird-0.022
Token replied
Token ID8712
Feature activation+4.97e-02

Pos logit contributions
 sky+0.024
+0.021
 voice+0.020
 hawk+0.019
 poster+0.019
Neg logit contributions
ash-0.050
 theirs-0.046
uries-0.046
 yours-0.045
asty-0.045
Token.
Token ID13
Feature activation-4.81e-03

Pos logit contributions
 sky+0.071
 voice+0.068
+0.065
't+0.062
 crying+0.060
Neg logit contributions
ash-0.091
uries-0.084
 theirs-0.084
 yours-0.083
wn-0.081
Token
Token ID198
Feature activation+2.65e-03

Pos logit contributions
ash+0.008
 theirs+0.008
uries+0.008
uggets+0.008
asty+0.008
Neg logit contributions
 hawk-0.006
 sky-0.006
 poster-0.006
 voice-0.006
 cage-0.006
Token
Token ID198
Feature activation-4.53e-04

Pos logit contributions
 sky+0.003
 hawk+0.003
 poster+0.003
 voice+0.003
+0.003
Neg logit contributions
ash-0.006
 theirs-0.005
iding-0.005
 yours-0.005
 organize-0.005
TokenL
Token ID43
Feature activation-9.50e-02

Pos logit contributions
ash+0.001
 theirs+0.001
uries+0.001
 yours+0.001
asty+0.001
Neg logit contributions
 sky-0.001
 voice-0.001
-0.001
't-0.001
 poster-0.001
Tokenily
Token ID813
Feature activation-8.37e-03

Pos logit contributions
ash+0.123
uries+0.113
 theirs+0.113
 yours+0.107
wn+0.104
Neg logit contributions
 sky-0.183
 voice-0.172
-0.170
't-0.165
 poster-0.161
Token smelled
Token ID37609
Feature activation-4.79e-02

Pos logit contributions
ash+0.014
uries+0.013
 theirs+0.013
 organize+0.013
asty+0.013
Neg logit contributions
 sky-0.012
-0.011
 voice-0.011
 hawk-0.011
 poster-0.011
Token the
Token ID262
Feature activation+3.84e-02

Pos logit contributions
ash+0.086
 theirs+0.081
 yours+0.078
uries+0.078
asty+0.077
Neg logit contributions
 sky-0.069
-0.064
 voice-0.063
 poster-0.060
't-0.060
Token pepper
Token ID13385
Feature activation-1.75e-02

Pos logit contributions
+0.064
 sky+0.063
 poster+0.062
 voice+0.061
 hawk+0.061
Neg logit contributions
ash-0.054
asting-0.053
 theirs-0.050
 yours-0.049
asty-0.048
Token and
Token ID290
Feature activation+1.80e-02

Pos logit contributions
ash+0.037
uries+0.035
 theirs+0.035
 yours+0.034
wn+0.033
Neg logit contributions
 sky-0.021
 voice-0.018
-0.018
't-0.017
 bird-0.016
Token made
Token ID925
Feature activation-4.96e-02

Pos logit contributions
 sky+0.021
 voice+0.019
 bird+0.017
+0.017
't+0.016
Neg logit contributions
ash-0.040
uries-0.037
 theirs-0.036
iding-0.036
wn-0.036
Token showed
Token ID3751
Feature activation-2.85e-02

Pos logit contributions
ash+0.014
 theirs+0.014
uries+0.013
 yours+0.013
iding+0.013
Neg logit contributions
 sky-0.007
 voice-0.006
 bird-0.006
-0.006
't-0.006
Token that
Token ID326
Feature activation+7.43e-03

Pos logit contributions
ash+0.049
uries+0.045
 theirs+0.044
iding+0.043
aghetti+0.043
Neg logit contributions
 sky-0.045
 voice-0.043
 bird-0.039
't-0.039
-0.038
Token the
Token ID262
Feature activation+2.57e-02

Pos logit contributions
 sky+0.010
 voice+0.009
+0.008
't+0.008
 poster+0.008
Neg logit contributions
ash-0.015
uries-0.014
 theirs-0.014
iding-0.014
wn-0.014
Token rock
Token ID3881
Feature activation+1.89e-02

Pos logit contributions
 sky+0.034
+0.033
 voice+0.032
't+0.031
 hawk+0.030
Neg logit contributions
ash-0.046
uries-0.043
 theirs-0.043
 yours-0.043
 organize-0.042
Token was
Token ID373
Feature activation+1.58e-03

Pos logit contributions
 sky+0.020
 voice+0.018
+0.018
't+0.016
 poster+0.016
Neg logit contributions
ash-0.042
 theirs-0.039
uries-0.039
 yours-0.038
asty-0.037
Token very
Token ID845
Feature activation+2.65e-03

Pos logit contributions
 sky+0.002
 voice+0.002
 crying+0.002
 cage+0.002
 tree+0.002
Neg logit contributions
ash-0.003
uries-0.003
aghetti-0.003
iding-0.003
ust-0.003
Token heavy
Token ID4334
Feature activation+1.98e-02

Pos logit contributions
 sky+0.003
 voice+0.003
 tree+0.002
 cage+0.002
 bird+0.002
Neg logit contributions
ash-0.006
uries-0.006
iding-0.005
aghetti-0.005
 theirs-0.005
Token.
Token ID13
Feature activation-8.31e-03

Pos logit contributions
 sky+0.025
 voice+0.022
+0.020
 bird+0.020
 crying+0.020
Neg logit contributions
ash-0.041
uries-0.038
 theirs-0.037
uggets-0.037
iding-0.037
Token Daisy
Token ID40355
Feature activation-2.18e-02

Pos logit contributions
ash+0.010
 theirs+0.009
 organize+0.009
uries+0.009
 yours+0.008
Neg logit contributions
 poster-0.015
 sky-0.015
 hawk-0.015
 voice-0.014
 cage-0.014
Token was
Token ID373
Feature activation+1.42e-02

Pos logit contributions
ash+0.035
 organize+0.033
uries+0.033
 remember+0.032
asting+0.032
Neg logit contributions
 sky-0.032
-0.030
 hawk-0.029
 poster-0.029
 voice-0.028
Token amazed
Token ID24562
Feature activation+3.01e-02

Pos logit contributions
 sky+0.021
+0.020
 voice+0.019
 poster+0.019
 hawk+0.018
Neg logit contributions
ash-0.025
 theirs-0.024
uries-0.023
 yours-0.023
asty-0.023
Token.
Token ID13
Feature activation-2.17e-02

Pos logit contributions
 sky+0.016
 voice+0.014
't+0.013
+0.013
 bird+0.013
Neg logit contributions
ash-0.023
 theirs-0.022
uries-0.022
wn-0.021
asty-0.021
Token I
Token ID314
Feature activation-2.49e-02

Pos logit contributions
ash+0.039
 theirs+0.037
wn+0.035
uries+0.035
iding+0.034
Neg logit contributions
 sky-0.033
-0.030
't-0.030
 voice-0.030
 bird-0.027
Token wish
Token ID4601
Feature activation+4.87e-02

Pos logit contributions
ash+0.040
 theirs+0.037
uries+0.036
 yours+0.036
 organize+0.035
Neg logit contributions
 sky-0.041
 voice-0.038
-0.037
 hawk-0.036
 poster-0.036
Token I
Token ID314
Feature activation-1.56e-02

Pos logit contributions
 sky+0.071
't+0.066
 voice+0.065
 bird+0.059
+0.058
Neg logit contributions
ash-0.093
uries-0.086
wn-0.086
 theirs-0.084
aghetti-0.082
Token could
Token ID714
Feature activation+7.51e-02

Pos logit contributions
ash+0.029
 theirs+0.027
iding+0.026
uries+0.026
uggets+0.026
Neg logit contributions
 sky-0.022
't-0.021
 voice-0.020
-0.020
 bird-0.019
Token be
Token ID307
Feature activation-3.88e-02

Pos logit contributions
 sky+0.133
 voice+0.125
+0.123
't+0.119
 poster+0.116
Neg logit contributions
ash-0.113
 theirs-0.104
uries-0.101
 yours-0.099
wn-0.097
Token as
Token ID355
Feature activation+1.06e-02

Pos logit contributions
ash+0.081
aghetti+0.073
uries+0.073
iding+0.072
ruits+0.071
Neg logit contributions
 voice-0.051
 sky-0.050
 bird-0.047
't-0.045
 crying-0.043
Token strong
Token ID1913
Feature activation-6.36e-03

Pos logit contributions
 sky+0.016
 voice+0.015
't+0.014
+0.014
 bird+0.014
Neg logit contributions
ash-0.019
uries-0.018
 theirs-0.017
iding-0.017
wn-0.017
Token as
Token ID355
Feature activation+7.08e-03

Pos logit contributions
ash+0.009
 theirs+0.008
uries+0.008
ust+0.008
iding+0.008
Neg logit contributions
 sky-0.012
 voice-0.011
-0.011
't-0.011
 hawk-0.011
Token you
Token ID345
Feature activation-5.48e-02

Pos logit contributions
 sky+0.010
't+0.009
 voice+0.009
 bird+0.009
 tree+0.008
Neg logit contributions
ash-0.014
uries-0.013
wn-0.013
iding-0.012
 theirs-0.012
Token."
Token ID526
Feature activation+2.88e-02

Pos logit contributions
ash+0.082
 theirs+0.079
uggets+0.075
uries+0.074
iding+0.073
Neg logit contributions
 sky-0.098
't-0.090
 voice-0.090
-0.089
 bird-0.084
Token.
Token ID13
Feature activation-1.31e-02

Pos logit contributions
 sky+0.036
 voice+0.032
 bird+0.031
 cage+0.030
't+0.030
Neg logit contributions
ash-0.067
uries-0.064
wn-0.064
 yours-0.063
wy-0.062
Token Lily
Token ID20037
Feature activation-1.16e-02

Pos logit contributions
ash+0.018
 theirs+0.017
uries+0.017
 organize+0.016
 yours+0.016
Neg logit contributions
 sky-0.023
 hawk-0.023
 voice-0.022
 poster-0.022
 cage-0.021
Token was
Token ID373
Feature activation+1.04e-02

Pos logit contributions
ash+0.020
 organize+0.019
uries+0.019
iding+0.018
ust+0.018
Neg logit contributions
 sky-0.017
-0.015
 hawk-0.015
 poster-0.014
 voice-0.014
Token so
Token ID523
Feature activation+1.43e-02

Pos logit contributions
 sky+0.015
+0.014
 voice+0.013
 poster+0.013
 hawk+0.013
Neg logit contributions
ash-0.018
 theirs-0.018
uries-0.017
 yours-0.017
asty-0.017
Token excited
Token ID6568
Feature activation+4.63e-02

Pos logit contributions
 sky+0.020
 voice+0.019
+0.018
't+0.017
 poster+0.017
Neg logit contributions
ash-0.027
 theirs-0.025
uries-0.025
 yours-0.024
wn-0.024
Token because
Token ID780
Feature activation-3.93e-02

Pos logit contributions
 sky+0.060
 voice+0.055
+0.052
't+0.051
 poster+0.049
Neg logit contributions
ash-0.091
uries-0.086
 theirs-0.086
 yours-0.084
wn-0.083
Token she
Token ID673
Feature activation-3.65e-02

Pos logit contributions
ash+0.089
uries+0.084
wn+0.081
 theirs+0.081
iding+0.080
Neg logit contributions
 sky-0.043
 voice-0.036
-0.035
't-0.035
 bird-0.033
Token loved
Token ID6151
Feature activation+3.35e-02

Pos logit contributions
ash+0.066
 theirs+0.063
uries+0.060
 yours+0.060
iding+0.058
Neg logit contributions
 sky-0.054
 voice-0.051
-0.049
't-0.048
 poster-0.045
Token going
Token ID1016
Feature activation+6.48e-03

Pos logit contributions
 sky+0.050
 voice+0.044
 bird+0.042
't+0.042
 poster+0.041
Neg logit contributions
ash-0.064
uries-0.060
iding-0.059
ust-0.058
ackers-0.056
Token down
Token ID866
Feature activation+4.13e-02

Pos logit contributions
 sky+0.009
't+0.007
 voice+0.007
+0.007
 poster+0.007
Neg logit contributions
ash-0.013
uries-0.012
 theirs-0.012
uggets-0.012
ust-0.012
Token the
Token ID262
Feature activation+2.55e-02

Pos logit contributions
 sky+0.058
 voice+0.053
+0.052
't+0.049
 poster+0.048
Neg logit contributions
ash-0.078
uries-0.073
 theirs-0.072
 yours-0.071
iding-0.070
Token was
Token ID373
Feature activation-6.77e-05

Pos logit contributions
 sky+0.020
 voice+0.017
+0.016
't+0.015
 poster+0.015
Neg logit contributions
ash-0.044
 theirs-0.041
uries-0.041
 yours-0.040
iding-0.040
Token bright
Token ID6016
Feature activation-3.02e-02

Pos logit contributions
ash+0.000
uries+0.000
iding+0.000
ust+0.000
 theirs+0.000
Neg logit contributions
 sky-0.000
 voice-0.000
't-0.000
 cage-0.000
 bird-0.000
Token red
Token ID2266
Feature activation+4.21e-04

Pos logit contributions
ash+0.069
uries+0.066
 theirs+0.065
 yours+0.063
wn+0.063
Neg logit contributions
 sky-0.033
 voice-0.028
-0.026
 bird-0.024
 cage-0.023
Token and
Token ID290
Feature activation+1.98e-02

Pos logit contributions
 sky+0.000
 voice+0.000
+0.000
't+0.000
 poster+0.000
Neg logit contributions
ash-0.001
 theirs-0.001
uries-0.001
 yours-0.001
wn-0.001
Token it
Token ID340
Feature activation-1.87e-03

Pos logit contributions
 sky+0.026
 voice+0.019
 tree+0.019
 bird+0.019
't+0.019
Neg logit contributions
ash-0.046
uries-0.044
iding-0.043
uggets-0.042
asty-0.041
Token made
Token ID925
Feature activation-5.75e-02

Pos logit contributions
ash+0.004
 theirs+0.004
uggets+0.004
uries+0.004
iding+0.004
Neg logit contributions
 sky-0.002
 voice-0.002
't-0.001
 bird-0.001
-0.001
Token a
Token ID257
Feature activation+1.93e-02

Pos logit contributions
uries+0.115
ash+0.111
iding+0.105
ust+0.104
aghetti+0.103
Neg logit contributions
 sky-0.080
 voice-0.071
't-0.067
 bird-0.061
 skies-0.059
Token loud
Token ID7812
Feature activation+1.62e-03

Pos logit contributions
 sky+0.029
+0.028
 voice+0.027
't+0.026
 hawk+0.025
Neg logit contributions
ash-0.032
 theirs-0.030
uries-0.030
 yours-0.030
asty-0.029
Token noise
Token ID7838
Feature activation+3.07e-03

Pos logit contributions
 sky+0.002
+0.002
 voice+0.002
't+0.002
 hawk+0.002
Neg logit contributions
ash-0.003
 theirs-0.003
uries-0.003
 yours-0.003
asty-0.003
Token.
Token ID13
Feature activation-6.63e-03

Pos logit contributions
 sky+0.003
 voice+0.003
 bird+0.003
't+0.003
 crying+0.002
Neg logit contributions
ash-0.007
ust-0.007
uggets-0.007
uries-0.007
wn-0.007
Token He
Token ID679
Feature activation+3.84e-03

Pos logit contributions
ash+0.013
uries+0.012
 theirs+0.012
 yours+0.012
wn+0.012
Neg logit contributions
 sky-0.009
-0.008
 voice-0.008
't-0.007
 bird-0.007
Token,
Token ID11
Feature activation-1.72e-04

Pos logit contributions
 sky+0.033
 voice+0.032
't+0.029
+0.028
 crying+0.024
Neg logit contributions
ash-0.134
uries-0.126
wn-0.123
 theirs-0.122
aghetti-0.121
Token "
Token ID366
Feature activation+4.02e-03

Pos logit contributions
ash+0.000
 theirs+0.000
uries+0.000
 yours+0.000
asty+0.000
Neg logit contributions
 sky-0.000
 voice-0.000
-0.000
 hawk-0.000
 poster-0.000
TokenI
Token ID40
Feature activation-7.08e-03

Pos logit contributions
 sky+0.005
 voice+0.005
+0.005
't+0.004
 hawk+0.004
Neg logit contributions
ash-0.008
 theirs-0.007
uries-0.007
 yours-0.007
iding-0.007
Token'm
Token ID1101
Feature activation-1.46e-02

Pos logit contributions
ash+0.013
 theirs+0.012
uries+0.012
 yours+0.012
iding+0.011
Neg logit contributions
 sky-0.010
 voice-0.010
-0.009
't-0.009
 poster-0.009
Token glad
Token ID9675
Feature activation+5.35e-02

Pos logit contributions
ash+0.027
 theirs+0.025
uries+0.025
 yours+0.024
iding+0.024
Neg logit contributions
 sky-0.021
 voice-0.019
-0.019
't-0.018
 poster-0.018
Token you
Token ID345
Feature activation-4.86e-02

Pos logit contributions
 sky+0.072
 voice+0.066
't+0.064
+0.062
 bird+0.061
Neg logit contributions
ash-0.106
uries-0.099
 theirs-0.097
wn-0.097
iding-0.095
Token had
Token ID550
Feature activation+2.79e-02

Pos logit contributions
ash+0.088
uggets+0.087
 theirs+0.086
iding+0.086
aghetti+0.081
Neg logit contributions
 sky-0.072
't-0.064
 voice-0.062
-0.061
 bird-0.060
Token fun
Token ID1257
Feature activation+3.23e-03

Pos logit contributions
 sky+0.031
 voice+0.029
't+0.026
 bird+0.026
 tree+0.025
Neg logit contributions
ash-0.061
uries-0.059
uggets-0.057
aghetti-0.057
 theirs-0.057
Token,
Token ID11
Feature activation-3.27e-02

Pos logit contributions
 sky+0.005
 voice+0.004
+0.004
't+0.004
 bird+0.004
Neg logit contributions
ash-0.006
 theirs-0.006
uries-0.006
uggets-0.005
wn-0.005
Token but
Token ID475
Feature activation-7.32e-03

Pos logit contributions
ash+0.059
uries+0.052
wn+0.052
iding+0.050
aghetti+0.050
Neg logit contributions
 sky-0.052
 voice-0.050
 bird-0.047
't-0.045
-0.044
Token be
Token ID307
Feature activation-2.72e-02

Pos logit contributions
ash+0.012
 theirs+0.011
uries+0.011
wn+0.011
iding+0.011
Neg logit contributions
 sky-0.012
 voice-0.011
-0.011
't-0.010
 poster-0.010
TokenFinally
Token ID11158
Feature activation+5.89e-03

Pos logit contributions
ash+0.017
 theirs+0.016
uries+0.016
 yours+0.016
wn+0.016
Neg logit contributions
 sky-0.009
 voice-0.008
-0.008
't-0.008
 hawk-0.007
Token,
Token ID11
Feature activation-2.84e-02

Pos logit contributions
 sky+0.004
 voice+0.003
+0.003
't+0.003
 bird+0.002
Neg logit contributions
ash-0.017
uries-0.016
aghetti-0.016
wn-0.015
ust-0.015
Token the
Token ID262
Feature activation+2.01e-02

Pos logit contributions
ash+0.060
uries+0.056
wn+0.055
 theirs+0.054
iding+0.054
Neg logit contributions
 sky-0.037
 voice-0.032
-0.032
't-0.031
 bird-0.030
Token ear
Token ID1027
Feature activation+1.36e-02

Pos logit contributions
 sky+0.027
+0.027
 voice+0.025
't+0.024
 poster+0.024
Neg logit contributions
ash-0.036
uries-0.034
 yours-0.034
 theirs-0.033
asty-0.032
Token had
Token ID550
Feature activation+1.83e-02

Pos logit contributions
 sky+0.018
 voice+0.017
+0.016
't+0.015
 bird+0.015
Neg logit contributions
ash-0.027
 theirs-0.025
uries-0.025
 yours-0.025
wn-0.024
Token counted
Token ID14789
Feature activation-3.97e-02

Pos logit contributions
 sky+0.028
 voice+0.024
't+0.023
 bird+0.023
+0.022
Neg logit contributions
ash-0.035
uries-0.032
iding-0.031
aghetti-0.031
uggets-0.031
Token all
Token ID477
Feature activation-3.47e-02

Pos logit contributions
ash+0.080
uries+0.076
aghetti+0.074
wn+0.074
uggets+0.071
Neg logit contributions
 sky-0.055
 voice-0.047
't-0.044
 bird-0.043
 cage-0.041
Token the
Token ID262
Feature activation+2.50e-02

Pos logit contributions
uries+0.064
ash+0.064
uggets+0.061
aghetti+0.061
iding+0.059
Neg logit contributions
 sky-0.052
 voice-0.046
 bird-0.042
 tree-0.041
't-0.041
Token way
Token ID835
Feature activation+8.16e-03

Pos logit contributions
 sky+0.039
 voice+0.036
 bird+0.032
 cage+0.032
 poster+0.032
Neg logit contributions
ash-0.047
 theirs-0.043
asty-0.042
uries-0.042
iding-0.041
Token to
Token ID284
Feature activation+1.12e-02

Pos logit contributions
 sky+0.012
 voice+0.010
't+0.010
 bird+0.009
 crying+0.009
Neg logit contributions
ash-0.016
uries-0.015
aghetti-0.015
uggets-0.014
wn-0.014
Token 10
Token ID838
Feature activation-2.09e-02

Pos logit contributions
 sky+0.018
 voice+0.017
't+0.016
 tree+0.015
 bird+0.015
Neg logit contributions
ash-0.021
aghetti-0.019
uggets-0.018
wn-0.018
uries-0.018
Token more
Token ID517
Feature activation-2.17e-02

Pos logit contributions
ash+0.071
uries+0.068
ust+0.067
wn+0.066
uggets+0.065
Neg logit contributions
 sky-0.053
 voice-0.049
't-0.044
 bird-0.043
 poster-0.043
Token cartoons
Token ID30070
Feature activation-1.56e-02

Pos logit contributions
ash+0.038
uries+0.037
ust+0.036
uggets+0.036
 yours+0.036
Neg logit contributions
 sky-0.034
 voice-0.032
 poster-0.029
 bird-0.028
 cage-0.027
Token.
Token ID13
Feature activation-1.73e-02

Pos logit contributions
ash+0.031
uries+0.029
uggets+0.028
ust+0.028
wn+0.028
Neg logit contributions
 sky-0.021
't-0.019
 voice-0.018
-0.018
 poster-0.017
Token
Token ID198
Feature activation-4.59e-04

Pos logit contributions
ash+0.030
 theirs+0.028
 organize+0.027
 yours+0.027
uries+0.027
Neg logit contributions
 hawk-0.025
 voice-0.023
 sky-0.023
 poster-0.023
 cage-0.022
Token
Token ID198
Feature activation-3.37e-03

Pos logit contributions
ash+0.001
 theirs+0.001
 organize+0.001
asting+0.001
 yours+0.001
Neg logit contributions
 hawk-0.001
 sky-0.001
-0.000
 voice-0.000
 poster-0.000
TokenL
Token ID43
Feature activation-1.02e-01

Pos logit contributions
ash+0.006
 theirs+0.005
uries+0.005
 yours+0.005
asty+0.005
Neg logit contributions
 sky-0.005
 voice-0.005
-0.005
't-0.005
 poster-0.005
Tokenily
Token ID813
Feature activation-1.07e-02

Pos logit contributions
ash+0.123
 theirs+0.110
uries+0.108
 yours+0.106
asty+0.102
Neg logit contributions
 sky-0.210
 voice-0.198
-0.196
't-0.188
 poster-0.187
Token was
Token ID373
Feature activation+6.70e-03

Pos logit contributions
ash+0.018
 organize+0.017
uries+0.016
ust+0.016
ots+0.015
Neg logit contributions
 sky-0.016
-0.016
 hawk-0.015
 voice-0.015
 poster-0.015
Token amazed
Token ID24562
Feature activation+2.56e-02

Pos logit contributions
 sky+0.010
+0.010
 voice+0.009
 poster+0.009
 hawk+0.009
Neg logit contributions
ash-0.011
 theirs-0.011
uries-0.011
 yours-0.011
asty-0.010
Token and
Token ID290
Feature activation+1.48e-02

Pos logit contributions
 sky+0.042
 voice+0.039
+0.038
't+0.036
 poster+0.036
Neg logit contributions
ash-0.042
 theirs-0.039
uries-0.039
 yours-0.038
wn-0.037
Token said
Token ID531
Feature activation+3.74e-02

Pos logit contributions
 sky+0.019
 voice+0.018
't+0.016
 crying+0.016
 bird+0.015
Neg logit contributions
ash-0.031
uries-0.028
 theirs-0.028
 yours-0.027
iding-0.027
Token exciting
Token ID7895
Feature activation-2.79e-03

Pos logit contributions
 sky+0.012
 voice+0.011
't+0.010
+0.010
 cage+0.009
Neg logit contributions
ash-0.014
uries-0.013
uggets-0.012
iding-0.012
 yours-0.012
Token!
Token ID0
Feature activation-1.55e-02

Pos logit contributions
ash+0.006
uries+0.005
ackers+0.005
wn+0.005
uggets+0.005
Neg logit contributions
 sky-0.003
 voice-0.003
't-0.003
-0.003
 poster-0.003
Token
Token ID220
Feature activation+1.59e-03

Pos logit contributions
ash+0.033
 theirs+0.031
uries+0.031
 yours+0.030
uggets+0.029
Neg logit contributions
 sky-0.016
 voice-0.015
 poster-0.015
 hawk-0.015
-0.014
Token
Token ID198
Feature activation+4.21e-04

Pos logit contributions
 sky+0.001
 voice+0.001
+0.001
 hawk+0.001
 poster+0.001
Neg logit contributions
ash-0.004
 theirs-0.004
uries-0.004
 yours-0.004
iding-0.004
Token
Token ID198
Feature activation-1.85e-03

Pos logit contributions
 sky+0.000
 voice+0.000
 hawk+0.000
+0.000
 poster+0.000
Neg logit contributions
ash-0.001
uries-0.001
 theirs-0.001
asting-0.001
iding-0.001
TokenP
Token ID47
Feature activation-1.04e-01

Pos logit contributions
ash+0.004
 theirs+0.003
 yours+0.003
uries+0.003
asty+0.003
Neg logit contributions
 sky-0.002
 voice-0.002
-0.002
't-0.002
 hawk-0.002
Tokenolly
Token ID5098
Feature activation-3.04e-02

Pos logit contributions
ash+0.150
 theirs+0.139
uries+0.136
 yours+0.134
asty+0.129
Neg logit contributions
 sky-0.187
 voice-0.176
-0.175
't-0.166
 poster-0.164
Token's
Token ID338
Feature activation-1.44e-02

Pos logit contributions
ash+0.058
uries+0.054
 theirs+0.054
 yours+0.052
iding+0.052
Neg logit contributions
 sky-0.040
-0.037
 voice-0.036
't-0.034
 hawk-0.034
Token mom
Token ID1995
Feature activation+2.55e-02

Pos logit contributions
ash+0.024
 theirs+0.023
uries+0.022
asty+0.022
 yours+0.022
Neg logit contributions
 sky-0.021
-0.020
't-0.019
 hawk-0.019
 voice-0.019
Tokenmy
Token ID1820
Feature activation+1.72e-02

Pos logit contributions
 sky+0.034
 voice+0.032
+0.031
't+0.029
 poster+0.029
Neg logit contributions
ash-0.049
 theirs-0.046
uries-0.045
 yours-0.045
asty-0.044
Token let
Token ID1309
Feature activation+1.91e-02

Pos logit contributions
 sky+0.023
 voice+0.021
+0.021
 hawk+0.020
 poster+0.020
Neg logit contributions
ash-0.032
 theirs-0.030
uries-0.030
 yours-0.029
asty-0.029
Token groceries
Token ID38464
Feature activation-3.88e-03

Pos logit contributions
ash+0.077
uries+0.071
iding+0.069
 theirs+0.068
ust+0.067
Neg logit contributions
 sky-0.073
 voice-0.068
-0.065
't-0.062
 bird-0.061
Token.
Token ID13
Feature activation-2.91e-02

Pos logit contributions
ash+0.008
iding+0.008
wn+0.008
uries+0.008
ust+0.008
Neg logit contributions
 sky-0.004
-0.004
 voice-0.004
't-0.004
 cage-0.004
Token
Token ID220
Feature activation-3.20e-03

Pos logit contributions
ash+0.067
 theirs+0.063
uries+0.062
 yours+0.062
wn+0.061
Neg logit contributions
 sky-0.029
 voice-0.025
-0.025
't-0.023
 poster-0.022
Token
Token ID198
Feature activation-6.95e-03

Pos logit contributions
ash+0.009
 theirs+0.008
uries+0.008
 yours+0.008
wn+0.008
Neg logit contributions
 sky-0.002
-0.001
 voice-0.001
't-0.001
 poster-0.001
Token
Token ID198
Feature activation-8.87e-03

Pos logit contributions
ash+0.016
 theirs+0.015
uries+0.015
asting+0.015
 yours+0.015
Neg logit contributions
 sky-0.006
 voice-0.006
 hawk-0.006
-0.005
 poster-0.005
TokenP
Token ID47
Feature activation-1.05e-01

Pos logit contributions
ash+0.018
 theirs+0.017
 yours+0.016
uries+0.016
asty+0.016
Neg logit contributions
 sky-0.011
 voice-0.010
-0.010
't-0.010
 poster-0.009
Tokenete
Token ID14471
Feature activation-1.75e-02

Pos logit contributions
ash+0.158
 theirs+0.146
uries+0.143
 yours+0.141
asty+0.136
Neg logit contributions
 sky-0.185
 voice-0.173
-0.172
't-0.163
 poster-0.162
Token took
Token ID1718
Feature activation-4.24e-02

Pos logit contributions
ash+0.033
uries+0.031
 theirs+0.031
 yours+0.030
 organize+0.029
Neg logit contributions
 sky-0.024
-0.021
 voice-0.021
 hawk-0.020
 poster-0.020
Token his
Token ID465
Feature activation+7.93e-04

Pos logit contributions
iding+0.096
ash+0.095
ust+0.094
uries+0.093
aghetti+0.092
Neg logit contributions
 sky-0.044
 voice-0.041
't-0.035
 bird-0.035
-0.034
Token groceries
Token ID38464
Feature activation+2.46e-02

Pos logit contributions
 sky+0.001
 voice+0.001
+0.001
't+0.001
 poster+0.001
Neg logit contributions
ash-0.001
 theirs-0.001
uries-0.001
 yours-0.001
asty-0.001
Token home
Token ID1363
Feature activation+3.91e-02

Pos logit contributions
 sky+0.033
 voice+0.030
+0.030
't+0.028
 poster+0.028
Neg logit contributions
ash-0.047
 theirs-0.044
uries-0.044
 yours-0.043
asty-0.042
Token place
Token ID1295
Feature activation+3.81e-03

Pos logit contributions
ash+0.002
 yours+0.002
 theirs+0.002
uries+0.002
 organize+0.002
Neg logit contributions
 sky-0.002
-0.002
 voice-0.001
't-0.001
 hawk-0.001
Token where
Token ID810
Feature activation-1.99e-02

Pos logit contributions
 sky+0.006
 voice+0.005
 cage+0.005
't+0.005
 poster+0.005
Neg logit contributions
ash-0.007
uries-0.006
wn-0.006
asty-0.006
iding-0.006
Token she
Token ID673
Feature activation-5.00e-02

Pos logit contributions
ash+0.042
 theirs+0.040
uries+0.039
 yours+0.039
asty+0.038
Neg logit contributions
 sky-0.022
 voice-0.020
-0.020
 poster-0.018
't-0.018
Token could
Token ID714
Feature activation+5.01e-02

Pos logit contributions
ash+0.094
 theirs+0.090
uries+0.087
uggets+0.085
iding+0.085
Neg logit contributions
 sky-0.072
 voice-0.065
-0.062
 bird-0.061
't-0.060
Token find
Token ID1064
Feature activation-3.27e-02

Pos logit contributions
 sky+0.077
 voice+0.072
+0.070
't+0.068
 cage+0.065
Neg logit contributions
ash-0.089
 theirs-0.081
uries-0.080
 yours-0.078
wn-0.077
Token tast
Token ID14854
Feature activation-1.09e-01

Pos logit contributions
ash+0.067
uries+0.065
iding+0.063
aghetti+0.063
uggets+0.060
Neg logit contributions
 sky-0.043
 voice-0.040
 bird-0.038
 cage-0.036
 tree-0.035
Tokenier
Token ID959
Feature activation-1.63e-02

Pos logit contributions
uries+0.168
ash+0.156
 theirs+0.145
 organize+0.145
rated+0.139
Neg logit contributions
 sky-0.183
 voice-0.168
-0.164
't-0.161
 cage-0.156
Token leaves
Token ID5667
Feature activation-4.17e-02

Pos logit contributions
ash+0.023
aghetti+0.019
iding+0.019
ust+0.019
asty+0.019
Neg logit contributions
 sky-0.033
 voice-0.032
 cage-0.031
 bird-0.030
 tree-0.029
Token to
Token ID284
Feature activation-5.95e-03

Pos logit contributions
ash+0.081
uries+0.076
wn+0.073
iding+0.072
 theirs+0.072
Neg logit contributions
 sky-0.057
 voice-0.049
't-0.048
 cage-0.048
-0.047
Token eat
Token ID4483
Feature activation-3.25e-02

Pos logit contributions
ash+0.011
iding+0.009
uries+0.009
aghetti+0.009
 theirs+0.009
Neg logit contributions
 sky-0.010
 voice-0.009
 cage-0.009
 bird-0.009
 tree-0.009
Token.
Token ID13
Feature activation-1.84e-02

Pos logit contributions
ash+0.075
uries+0.074
wn+0.072
iding+0.070
rated+0.069
Neg logit contributions
 sky-0.033
 tree-0.030
 bush-0.027
 bird-0.027
 cage-0.027
Token Her
Token ID2332
Feature activation-2.29e-02

Pos logit contributions
ash+0.015
uries+0.014
 theirs+0.014
 yours+0.013
 organize+0.013
Neg logit contributions
 sky-0.007
-0.007
 hawk-0.007
 voice-0.007
 poster-0.007
Token mom
Token ID1995
Feature activation+2.59e-02

Pos logit contributions
 organize+0.028
ash+0.028
 theirs+0.027
uggets+0.027
 proper+0.027
Neg logit contributions
 sky-0.039
 hawk-0.038
 poster-0.037
ner-0.036
iren-0.036
Token had
Token ID550
Feature activation+1.77e-02

Pos logit contributions
 sky+0.039
+0.036
 voice+0.035
 hawk+0.034
 poster+0.033
Neg logit contributions
ash-0.046
 theirs-0.042
uries-0.042
 yours-0.041
wn-0.040
Token a
Token ID257
Feature activation-4.41e-04

Pos logit contributions
 sky+0.028
 voice+0.026
+0.026
 poster+0.024
 hawk+0.024
Neg logit contributions
ash-0.030
 theirs-0.028
uries-0.027
 yours-0.027
wn-0.026
Token black
Token ID2042
Feature activation-2.25e-02

Pos logit contributions
ash+0.001
 theirs+0.001
 yours+0.001
 organize+0.001
uries+0.001
Neg logit contributions
 sky-0.001
-0.001
 voice-0.001
't-0.001
 hawk-0.001
Token pr
Token ID778
Feature activation-1.16e-01

Pos logit contributions
ash+0.041
 theirs+0.037
 yours+0.037
uries+0.037
asty+0.036
Neg logit contributions
 sky-0.031
-0.029
 voice-0.028
't-0.027
 hawk-0.027
Tokenune
Token ID1726
Feature activation-1.71e-02

Pos logit contributions
ash+0.197
 theirs+0.189
uries+0.183
 yours+0.181
iding+0.176
Neg logit contributions
 sky-0.179
-0.167
 voice-0.164
't-0.155
 cage-0.152
Token in
Token ID287
Feature activation-2.43e-02

Pos logit contributions
ash+0.035
 theirs+0.034
uries+0.033
 yours+0.033
iding+0.032
Neg logit contributions
 sky-0.020
 voice-0.018
-0.018
't-0.017
 cage-0.017
Token a
Token ID257
Feature activation-6.46e-03

Pos logit contributions
ash+0.037
 theirs+0.035
 yours+0.034
uries+0.033
asty+0.033
Neg logit contributions
 sky-0.042
 voice-0.039
-0.038
 poster-0.037
 hawk-0.036
Token bowl
Token ID9396
Feature activation+8.70e-03

Pos logit contributions
ash+0.012
 yours+0.011
 organize+0.011
uries+0.011
wn+0.011
Neg logit contributions
 sky-0.008
-0.008
't-0.007
 voice-0.007
 hawk-0.007
Token on
Token ID319
Feature activation-1.60e-02

Pos logit contributions
 sky+0.012
 voice+0.011
+0.011
't+0.010
 cage+0.010
Neg logit contributions
ash-0.016
uries-0.015
 theirs-0.015
 yours-0.015
wn-0.015