TOP ACTIVATIONS
MAX = 8.682

it was called a " gem ". She explained that gems
" I want to eat peanuts , but I can 't
okay , Lily . Acc idents happen . Just be careful
, sweet ie . Acc idents happen . Let 's clean
okay , Anna . Acc idents happen . I 'm not
okay , Lily . Acc idents happen . It 's not
where it was hiding its peanuts . <|endoftext|> Once upon a
It 's okay . Acc idents happen . Just be more
the story is : Acc idents happen , but we should
okay , Lily . Acc idents happen . Just remember to
okay , Anna . Acc idents happen . You don 't
Its okay . Acc idents happen . â
okay , Lily . Acc idents happen . I 'm glad
okay , Lily . Acc idents happen . Let 's clean
, so reluctantly , the peanuts agreed . In return ,
, sweet ie . Acc idents happen . Let 's clean
cry , boys . Acc idents happen . I have something
okay , Lily . Acc idents happen . Let 's clean
was an accident . Acc idents happen . I 'm not
gives Sara a bowl of peanuts and Ben a bowl of

MIN ACTIVATIONS
MIN = -10.721

happy boy . <|endoftext|> Jo Jo was sad . He wanted
and harder . Jo jo and his mom were
lucky happy boy . <|endoftext|> Jo Jo was sad . He
to the village . Jo Jo smiled with anticipation and asked
unloaded , John and Jo Jo started to make their way
felt so proud ! <|endoftext|> Jo was a lively three -
friend Jo Jo . Jo Jo was thrilled to see Big
've got an idea Jo Jo . Maybe next time we
Don 't worry , Jo Jo . I can help you
into his best friend Jo Jo . Jo Jo was thrilled
His mom looked at Jo Jo and said " Don 't
the same time . <|endoftext|> Jo Jo was a clever little
same time . <|endoftext|> Jo Jo was a clever little boy
â Jo hopped on the bike and
Jo shouted . Jo opened the book and saw
thing to do . <|endoftext|> Jo el saw a banana in
't bud ge ! Jo Jo was getting frustrated . She
very reliable ." <|endoftext|> Jo Jo was playing in the park
been very reliable ." <|endoftext|> Jo Jo was playing in the
said together . Jo smiled and took them to

INTERVAL 3.831 - 8.682
CONTAINS 1.078%

her teacher gave her a folder to keep her papers in
Lily and Tom and w ags his tail . He forg
help . The moral of the story is always
and drink something good . A nice lady came and gave
, she joined a special club . They were celebrating by

INTERVAL -1.019 - 3.831
CONTAINS 81.627%

a good dream and reminded her to always be careful about
thank you " and smiled . Mama p atted her head
to go for a walk . He looked around and saw
anytime . And don 't forget to share your blue berries
big lion . He was huge and very strong . He

INTERVAL -5.870 - -1.019
CONTAINS 17.223%

started to float away , taking the people with it .
iness of the toilet . â The little
. We can help you ." L ily stops
make history . They both knew that their kiss would always
a butterfly and chased after it . The butterfly flew away

INTERVAL -10.721 - -5.870
CONTAINS 0.072%

completely filled . Anne and Jack were so happy
special game of hide - and - seek , so she
. She runs to the living room . She sees the
One day , Mon a was playing dolls with T
at the special find . Ann abel le taught them the
Token it
Token ID340
Feature activation-1.27e+00

Pos logit contributions
+0.002
idents+0.002
 sack+0.002
 Dino+0.002
 cooler+0.002
Neg logit contributions
Jo-0.003
rum-0.003
ud-0.003
Jamie-0.002
 Pen-0.002
Token was
Token ID373
Feature activation-5.63e-01

Pos logit contributions
Jo+0.122
rum+0.122
ud+0.111
and+0.106
 Pen+0.105
Neg logit contributions
-0.108
idents-0.097
 sack-0.091
 surely-0.089
 cooler-0.088
Token called
Token ID1444
Feature activation+8.70e-01

Pos logit contributions
Jo+0.046
rum+0.046
 Pen+0.039
 Ali+0.038
 Jacob+0.038
Neg logit contributions
-0.059
idents-0.051
ory-0.047
 hotter-0.047
Sorry-0.046
Token a
Token ID257
Feature activation-3.14e-01

Pos logit contributions
+0.071
 sack+0.061
idents+0.059
 Dino+0.059
 cooler+0.058
Neg logit contributions
Jo-0.090
rum-0.086
ud-0.079
and-0.076
jo-0.075
Token "
Token ID366
Feature activation-7.63e-01

Pos logit contributions
Jo+0.032
rum+0.032
ud+0.028
and+0.028
 Pen+0.027
Neg logit contributions
-0.026
 sack-0.021
idents-0.021
 hotter-0.020
 cooler-0.020
Tokengem
Token ID24090
Feature activation+8.68e+00

Pos logit contributions
Jo+0.077
rum+0.070
and+0.067
ud+0.064
jo+0.062
Neg logit contributions
-0.063
idents-0.058
 hotter-0.054
 sack-0.053
 cooler-0.052
Token".
Token ID1911
Feature activation-2.50e+00

Pos logit contributions
+0.852
idents+0.730
 sack+0.723
 surely+0.703
ory+0.701
Neg logit contributions
Jo-0.741
rum-0.708
ud-0.630
 Pen-0.620
 Ali-0.617
Token She
Token ID1375
Feature activation-4.06e-01

Pos logit contributions
Jo+0.231
rum+0.219
 Pen+0.194
 Ali+0.194
and+0.192
Neg logit contributions
-0.232
idents-0.197
 hotter-0.192
 sack-0.189
ory-0.189
Token explained
Token ID4893
Feature activation+2.51e+00

Pos logit contributions
Jo+0.042
rum+0.041
ud+0.037
and+0.036
 Pen+0.036
Neg logit contributions
-0.033
idents-0.027
 sack-0.026
 surely-0.026
ory-0.025
Token that
Token ID326
Feature activation-7.87e-01

Pos logit contributions
+0.174
idents+0.157
 sack+0.155
 Dino+0.152
 cooler+0.142
Neg logit contributions
Jo-0.271
rum-0.265
ud-0.244
 Pen-0.234
jo-0.231
Token gems
Token ID23685
Feature activation+6.22e+00

Pos logit contributions
rum+0.085
Jo+0.084
ud+0.078
and+0.073
 Pen+0.073
Neg logit contributions
-0.056
 sack-0.051
 Dino-0.049
idents-0.048
 Ros-0.046
Token "
Token ID366
Feature activation-1.54e-01

Pos logit contributions
+0.063
idents+0.048
 Dino+0.048
 sack+0.046
 hotter+0.046
Neg logit contributions
Jo-0.070
rum-0.069
ud-0.061
and-0.060
jo-0.059
TokenI
Token ID40
Feature activation+2.29e+00

Pos logit contributions
Jo+0.017
rum+0.016
ud+0.015
 Pen+0.015
 Ali+0.014
Neg logit contributions
-0.012
idents-0.009
 hotter-0.009
 surely-0.009
 sack-0.009
Token want
Token ID765
Feature activation-8.55e-01

Pos logit contributions
+0.208
idents+0.175
 surely+0.169
 sack+0.168
ory+0.168
Neg logit contributions
Jo-0.215
rum-0.209
 Pen-0.186
and-0.185
 Ali-0.182
Token to
Token ID284
Feature activation-1.67e-01

Pos logit contributions
Jo+0.097
rum+0.095
jo+0.087
ud+0.085
Jamie+0.080
Neg logit contributions
-0.059
 peanuts-0.054
 cooler-0.053
 sack-0.052
 Dino-0.052
Token eat
Token ID4483
Feature activation+8.14e-01

Pos logit contributions
Jo+0.019
rum+0.018
ud+0.017
and+0.016
 Pen+0.016
Neg logit contributions
-0.012
idents-0.010
 sack-0.010
 surely-0.009
ory-0.009
Token peanuts
Token ID45612
Feature activation+8.33e+00

Pos logit contributions
+0.070
idents+0.060
 hotter+0.057
 cooler+0.057
 sack+0.057
Neg logit contributions
Jo-0.083
rum-0.078
jo-0.071
ud-0.070
 Ali-0.067
Token,
Token ID11
Feature activation+3.80e-01

Pos logit contributions
+0.829
idents+0.712
 sack+0.684
ory+0.684
 surely+0.673
Neg logit contributions
Jo-0.730
rum-0.684
 Pen-0.590
ud-0.589
 Ali-0.589
Token but
Token ID475
Feature activation-4.89e-01

Pos logit contributions
+0.035
idents+0.030
 sack+0.028
 hotter+0.028
ory+0.028
Neg logit contributions
Jo-0.036
rum-0.035
ud-0.031
 Pen-0.030
and-0.030
Token I
Token ID314
Feature activation-1.38e+00

Pos logit contributions
Jo+0.044
rum+0.043
 Pen+0.038
ud+0.037
 Ali+0.037
Neg logit contributions
-0.046
idents-0.039
 hotter-0.037
 sack-0.037
 surely-0.037
Token can
Token ID460
Feature activation+2.22e+00

Pos logit contributions
Jo+0.127
rum+0.122
 Pen+0.107
ud+0.106
and+0.106
Neg logit contributions
-0.130
idents-0.110
 sack-0.105
 surely-0.105
 hotter-0.105
Token't
Token ID470
Feature activation+2.32e+00

Pos logit contributions
+0.189
idents+0.162
 hotter+0.158
 sack+0.152
ory+0.150
Neg logit contributions
Jo-0.214
rum-0.209
 Pen-0.185
 Jacob-0.183
ud-0.183
Token okay
Token ID8788
Feature activation+1.26e+00

Pos logit contributions
Jo+0.266
rum+0.262
 Pen+0.233
 Ali+0.231
ud+0.230
Neg logit contributions
-0.207
idents-0.166
ory-0.159
 sack-0.158
 hotter-0.154
Token,
Token ID11
Feature activation+3.44e-02

Pos logit contributions
idents+0.079
+0.075
 Ros+0.064
ory+0.064
 sack+0.061
Neg logit contributions
Jo-0.148
rum-0.140
ud-0.132
Jamie-0.129
and-0.125
Token Lily
Token ID20037
Feature activation+1.29e+00

Pos logit contributions
+0.002
idents+0.002
 sack+0.002
 hotter+0.002
 cooler+0.002
Neg logit contributions
Jo-0.004
rum-0.004
ud-0.004
jo-0.003
and-0.003
Token.
Token ID13
Feature activation-5.35e-02

Pos logit contributions
+0.092
idents+0.083
 sack+0.075
 Dino+0.073
 surely+0.070
Neg logit contributions
Jo-0.141
rum-0.130
and-0.126
ud-0.125
 Pen-0.123
Token Acc
Token ID6366
Feature activation-1.93e+00

Pos logit contributions
Jo+0.005
rum+0.005
ud+0.004
and+0.004
 Pen+0.004
Neg logit contributions
-0.005
idents-0.004
 surely-0.004
 Dino-0.004
 hotter-0.004
Tokenidents
Token ID3231
Feature activation+8.33e+00

Pos logit contributions
Jo+0.293
rum+0.289
and+0.270
jo+0.268
 Jacob+0.266
Neg logit contributions
-0.057
 surely-0.025
 sack-0.025
 hotter-0.023
 Dino-0.018
Token happen
Token ID1645
Feature activation+1.51e+00

Pos logit contributions
+0.694
idents+0.577
 hotter+0.547
 sack+0.546
 surely+0.540
Neg logit contributions
Jo-0.851
rum-0.822
 Pen-0.731
ud-0.730
and-0.722
Token.
Token ID13
Feature activation-4.49e-02

Pos logit contributions
+0.127
idents+0.118
 hotter+0.106
 surely+0.103
 sack+0.103
Neg logit contributions
Jo-0.149
rum-0.142
ud-0.127
 Pen-0.123
jo-0.122
Token Just
Token ID2329
Feature activation+1.00e+00

Pos logit contributions
Jo+0.004
rum+0.004
ud+0.003
and+0.003
 Pen+0.003
Neg logit contributions
-0.004
idents-0.004
 Dino-0.004
 surely-0.004
 hotter-0.004
Token be
Token ID307
Feature activation-2.64e-01

Pos logit contributions
+0.084
idents+0.071
 surely+0.067
 sack+0.067
 hotter+0.067
Neg logit contributions
Jo-0.102
rum-0.098
ud-0.088
 Pen-0.087
and-0.087
Token careful
Token ID8161
Feature activation-4.84e+00

Pos logit contributions
Jo+0.024
rum+0.021
jo+0.021
ud+0.020
 Pen+0.020
Neg logit contributions
-0.023
 hotter-0.022
 cooler-0.022
 ang-0.021
 prett-0.021
Token,
Token ID11
Feature activation+9.42e-02

Pos logit contributions
idents+0.068
+0.064
ory+0.053
 cooler+0.051
 sack+0.049
Neg logit contributions
Jo-0.158
rum-0.149
ud-0.141
and-0.139
Jamie-0.134
Token sweet
Token ID6029
Feature activation-1.15e+00

Pos logit contributions
idents+0.008
+0.008
 cooler+0.008
 sack+0.007
 surely+0.007
Neg logit contributions
Jo-0.009
rum-0.009
jo-0.008
and-0.008
ud-0.008
Tokenie
Token ID494
Feature activation+2.27e-01

Pos logit contributions
rum+0.129
Jo+0.128
and+0.119
 Pen+0.110
 Jacob+0.109
Neg logit contributions
ory-0.068
-0.067
idents-0.065
 cooler-0.060
 sack-0.058
Token.
Token ID13
Feature activation+7.68e-02

Pos logit contributions
+0.014
 sack+0.012
idents+0.012
 cooler+0.011
ory+0.010
Neg logit contributions
Jo-0.026
rum-0.025
and-0.025
Jamie-0.024
ud-0.024
Token Acc
Token ID6366
Feature activation-1.84e+00

Pos logit contributions
+0.007
idents+0.006
 surely+0.005
 Dino+0.005
 sack+0.005
Neg logit contributions
Jo-0.008
rum-0.007
ud-0.007
and-0.007
jo-0.006
Tokenidents
Token ID3231
Feature activation+8.27e+00

Pos logit contributions
Jo+0.270
rum+0.270
and+0.252
 Pen+0.250
 Ali+0.249
Neg logit contributions
-0.057
 surely-0.028
 sack-0.027
 hotter-0.024
 Dino-0.024
Token happen
Token ID1645
Feature activation+1.50e+00

Pos logit contributions
+0.580
idents+0.509
 sack+0.453
 hotter+0.453
 surely+0.441
Neg logit contributions
Jo-0.938
rum-0.888
ud-0.832
 Ali-0.817
 Pen-0.810
Token.
Token ID13
Feature activation+7.23e-02

Pos logit contributions
+0.110
idents+0.108
 hotter+0.093
 cooler+0.093
 sack+0.090
Neg logit contributions
Jo-0.159
rum-0.151
ud-0.141
Jamie-0.132
 Ali-0.131
Token Let
Token ID3914
Feature activation-2.89e+00

Pos logit contributions
+0.006
idents+0.006
 Dino+0.005
 surely+0.005
 hotter+0.005
Neg logit contributions
Jo-0.007
rum-0.007
ud-0.006
and-0.006
jo-0.006
Token's
Token ID338
Feature activation-2.46e+00

Pos logit contributions
Jo+0.185
rum+0.175
 Pen+0.144
ud+0.142
and+0.140
Neg logit contributions
-0.352
idents-0.310
 hotter-0.300
 sack-0.299
 surely-0.298
Token clean
Token ID3424
Feature activation+4.71e-01

Pos logit contributions
Jo+0.260
rum+0.252
 Pen+0.225
ud+0.224
 Ali+0.222
Neg logit contributions
-0.194
idents-0.159
 hotter-0.151
 sack-0.150
ory-0.149
Token okay
Token ID8788
Feature activation+1.20e+00

Pos logit contributions
rum+0.240
Jo+0.229
 Pen+0.206
 Ali+0.203
ud+0.200
Neg logit contributions
-0.242
ory-0.192
idents-0.188
 trigger-0.182
 sack-0.182
Token,
Token ID11
Feature activation+1.51e-01

Pos logit contributions
idents+0.064
+0.064
ory+0.049
 cooler+0.048
 sack+0.048
Neg logit contributions
Jo-0.153
rum-0.142
ud-0.132
jo-0.129
Jamie-0.128
Token Anna
Token ID11735
Feature activation-4.50e+00

Pos logit contributions
idents+0.013
+0.013
 cooler+0.012
 hotter+0.012
 surely+0.011
Neg logit contributions
Jo-0.014
rum-0.014
jo-0.013
ud-0.012
and-0.012
Token.
Token ID13
Feature activation+1.44e-01

Pos logit contributions
Jo+0.555
rum+0.503
Jamie+0.482
and+0.479
ud+0.470
Neg logit contributions
-0.278
idents-0.236
 sack-0.231
 cooler-0.210
 still-0.204
Token Acc
Token ID6366
Feature activation-1.91e+00

Pos logit contributions
+0.013
idents+0.011
 sack+0.011
 surely+0.010
 hotter+0.010
Neg logit contributions
Jo-0.014
rum-0.013
ud-0.012
and-0.012
jo-0.011
Tokenidents
Token ID3231
Feature activation+8.27e+00

Pos logit contributions
rum+0.290
Jo+0.290
and+0.270
 Ali+0.268
 Jacob+0.268
Neg logit contributions
-0.057
 surely-0.025
 sack-0.023
 hotter-0.018
 Dino-0.018
Token happen
Token ID1645
Feature activation+1.42e+00

Pos logit contributions
+0.640
idents+0.547
 hotter+0.505
 sack+0.501
 surely+0.495
Neg logit contributions
Jo-0.883
rum-0.843
ud-0.771
 Pen-0.763
 Ali-0.757
Token.
Token ID13
Feature activation+1.49e-01

Pos logit contributions
+0.097
idents+0.091
 hotter+0.079
 cooler+0.077
 sack+0.075
Neg logit contributions
Jo-0.162
rum-0.151
ud-0.138
jo-0.136
 Pen-0.136
Token I
Token ID314
Feature activation-1.56e+00

Pos logit contributions
+0.013
idents+0.011
 Dino+0.010
 hotter+0.010
 sack+0.010
Neg logit contributions
Jo-0.015
rum-0.014
ud-0.013
and-0.012
jo-0.012
Token'm
Token ID1101
Feature activation-2.12e-01

Pos logit contributions
Jo+0.125
rum+0.119
ud+0.103
and+0.101
 Pen+0.101
Neg logit contributions
-0.164
idents-0.139
 hotter-0.137
 sack-0.135
ory-0.134
Token not
Token ID407
Feature activation+4.41e-01

Pos logit contributions
Jo+0.022
rum+0.021
ud+0.019
jo+0.019
and+0.018
Neg logit contributions
-0.018
idents-0.015
 hotter-0.014
 surely-0.014
 sack-0.014
Token okay
Token ID8788
Feature activation+1.16e+00

Pos logit contributions
rum+0.236
Jo+0.226
 Pen+0.204
 Ali+0.201
 Jacob+0.196
Neg logit contributions
-0.248
ory-0.201
idents-0.193
 trigger-0.190
 sack-0.187
Token,
Token ID11
Feature activation+8.56e-02

Pos logit contributions
+0.078
idents+0.076
ory+0.063
 sack+0.062
 Ros+0.061
Neg logit contributions
Jo-0.134
rum-0.125
ud-0.116
Jamie-0.113
and-0.112
Token Lily
Token ID20037
Feature activation+1.35e+00

Pos logit contributions
+0.006
idents+0.005
 sack+0.005
 hotter+0.005
 surely+0.005
Neg logit contributions
Jo-0.010
rum-0.009
ud-0.008
jo-0.008
and-0.008
Token.
Token ID13
Feature activation+5.84e-02

Pos logit contributions
+0.096
idents+0.086
 sack+0.078
 surely+0.071
ory+0.071
Neg logit contributions
Jo-0.153
rum-0.141
Jamie-0.133
ud-0.133
and-0.132
Token Acc
Token ID6366
Feature activation-2.00e+00

Pos logit contributions
+0.006
idents+0.005
 surely+0.005
 sack+0.005
 Dino+0.005
Neg logit contributions
Jo-0.005
rum-0.005
ud-0.004
and-0.004
 Pen-0.004
Tokenidents
Token ID3231
Feature activation+8.24e+00

Pos logit contributions
rum+0.298
Jo+0.297
and+0.275
 Jacob+0.274
 Ali+0.274
Neg logit contributions
-0.060
 surely-0.030
 sack-0.029
 hotter-0.024
 cooler-0.021
Token happen
Token ID1645
Feature activation+1.39e+00

Pos logit contributions
+0.724
idents+0.594
ory+0.575
 sack+0.572
 hotter+0.572
Neg logit contributions
Jo-0.809
rum-0.785
 Pen-0.689
and-0.686
ud-0.682
Token.
Token ID13
Feature activation+2.71e-02

Pos logit contributions
+0.120
idents+0.109
 hotter+0.100
 sack+0.098
 surely+0.097
Neg logit contributions
Jo-0.136
rum-0.129
ud-0.114
 Pen-0.114
 Ali-0.111
Token It
Token ID632
Feature activation+3.65e-01

Pos logit contributions
+0.003
idents+0.002
 Dino+0.002
 surely+0.002
 hotter+0.002
Neg logit contributions
Jo-0.002
rum-0.002
ud-0.002
and-0.002
 Pen-0.002
Token's
Token ID338
Feature activation-2.60e+00

Pos logit contributions
+0.045
idents+0.039
ory+0.039
 sack+0.038
 hotter+0.038
Neg logit contributions
Jo-0.023
rum-0.021
 Pen-0.018
 Ali-0.017
ud-0.017
Token not
Token ID407
Feature activation+3.28e-01

Pos logit contributions
rum+0.244
Jo+0.242
 Pen+0.213
 Ali+0.208
ud+0.206
Neg logit contributions
-0.242
idents-0.193
ory-0.191
 sack-0.181
 trigger-0.175
Token where
Token ID810
Feature activation-2.60e+00

Pos logit contributions
+0.062
 sack+0.061
 cooler+0.058
 Dino+0.057
 hotter+0.056
Neg logit contributions
Jo-0.108
rum-0.105
ud-0.098
jo-0.094
Jamie-0.091
Token it
Token ID340
Feature activation-1.24e+00

Pos logit contributions
rum+0.305
Jo+0.297
ud+0.280
and+0.262
jo+0.260
Neg logit contributions
-0.165
 sack-0.150
 cooler-0.142
idents-0.140
 hotter-0.139
Token was
Token ID373
Feature activation-5.86e-01

Pos logit contributions
Jo+0.111
rum+0.105
 Pen+0.095
 Ali+0.093
and+0.092
Neg logit contributions
-0.119
idents-0.099
 hotter-0.095
ory-0.095
 sack-0.093
Token hiding
Token ID11816
Feature activation-3.21e+00

Pos logit contributions
Jo+0.060
rum+0.057
ud+0.052
 Ali+0.051
 Pen+0.051
Neg logit contributions
-0.047
 sack-0.041
 hotter-0.041
 cooler-0.040
 surely-0.040
Token its
Token ID663
Feature activation-2.65e+00

Pos logit contributions
Jo+0.304
rum+0.290
ud+0.257
 Pen+0.254
 Ali+0.251
Neg logit contributions
-0.290
idents-0.245
 sack-0.240
 hotter-0.235
 surely-0.234
Token peanuts
Token ID45612
Feature activation+8.24e+00

Pos logit contributions
Jo+0.249
rum+0.239
ud+0.210
 Pen+0.210
and+0.207
Neg logit contributions
-0.243
idents-0.205
 sack-0.198
 hotter-0.196
 surely-0.194
Token.
Token ID13
Feature activation+6.60e-02

Pos logit contributions
+0.779
idents+0.659
 sack+0.639
 hotter+0.628
 surely+0.624
Neg logit contributions
Jo-0.750
rum-0.720
ud-0.627
 Pen-0.627
 Ali-0.620
Token<|endoftext|>
Token ID50256
Feature activation-1.00e-01

Pos logit contributions
+0.005
idents+0.004
 Dino+0.004
ory+0.004
 sack+0.004
Neg logit contributions
rum-0.007
Jo-0.007
ud-0.006
and-0.006
jo-0.006
TokenOnce
Token ID7454
Feature activation+9.99e-01

Pos logit contributions
rum+0.011
Jo+0.011
ud+0.009
and+0.009
 Pen+0.009
Neg logit contributions
-0.008
 sack-0.006
idents-0.006
 Dino-0.006
 cooler-0.006
Token upon
Token ID2402
Feature activation+2.08e+00

Pos logit contributions
+0.058
idents+0.044
ory+0.042
 sack+0.041
 surely+0.041
Neg logit contributions
Jo-0.125
rum-0.123
ud-0.110
 Pen-0.110
and-0.109
Token a
Token ID257
Feature activation-2.05e-01

Pos logit contributions
+0.128
 cooler+0.107
 sack+0.099
 Dino+0.093
idents+0.093
Neg logit contributions
rum-0.254
Jo-0.241
ud-0.227
jo-0.220
 Ali-0.211
Token It
Token ID632
Feature activation+4.34e-01

Pos logit contributions
+0.016
 Dino+0.013
idents+0.013
 surely+0.012
 sack+0.012
Neg logit contributions
Jo-0.019
rum-0.018
ud-0.016
and-0.016
jo-0.016
Token's
Token ID338
Feature activation-2.54e+00

Pos logit contributions
+0.043
idents+0.038
 sack+0.036
 hotter+0.036
 surely+0.036
Neg logit contributions
Jo-0.037
rum-0.036
ud-0.031
and-0.031
 Ali-0.030
Token okay
Token ID8788
Feature activation+1.22e+00

Pos logit contributions
Jo+0.274
rum+0.262
ud+0.234
and+0.234
 Pen+0.233
Neg logit contributions
-0.199
idents-0.166
 hotter-0.160
 sack-0.158
 surely-0.157
Token.
Token ID13
Feature activation+1.85e-01

Pos logit contributions
idents+0.067
+0.062
 cooler+0.059
 still+0.055
ory+0.055
Neg logit contributions
Jo-0.151
rum-0.140
ud-0.132
Jamie-0.128
 Jacob-0.122
Token Acc
Token ID6366
Feature activation-1.92e+00

Pos logit contributions
+0.017
idents+0.014
 Dino+0.014
 surely+0.013
 sack+0.013
Neg logit contributions
Jo-0.019
rum-0.017
ud-0.016
and-0.015
jo-0.015
Tokenidents
Token ID3231
Feature activation+8.23e+00

Pos logit contributions
rum+0.279
Jo+0.279
and+0.262
 Jacob+0.259
 Ali+0.258
Neg logit contributions
-0.063
 sack-0.031
 surely-0.031
 hotter-0.027
 Dino-0.022
Token happen
Token ID1645
Feature activation+1.42e+00

Pos logit contributions
+0.690
idents+0.574
 hotter+0.544
 sack+0.543
 surely+0.537
Neg logit contributions
Jo-0.838
rum-0.810
 Pen-0.719
ud-0.717
and-0.710
Token.
Token ID13
Feature activation+1.93e-01

Pos logit contributions
+0.095
idents+0.092
 cooler+0.083
 hotter+0.082
ory+0.080
Neg logit contributions
Jo-0.158
rum-0.150
ud-0.138
 Ali-0.132
 Pen-0.132
Token Just
Token ID2329
Feature activation+1.01e+00

Pos logit contributions
+0.017
idents+0.014
 Dino+0.014
 surely+0.013
 hotter+0.013
Neg logit contributions
Jo-0.020
rum-0.018
ud-0.017
and-0.016
jo-0.016
Token be
Token ID307
Feature activation-1.86e-01

Pos logit contributions
+0.084
idents+0.070
 hotter+0.067
 surely+0.067
 sack+0.067
Neg logit contributions
Jo-0.103
rum-0.099
ud-0.088
 Pen-0.087
and-0.087
Token more
Token ID517
Feature activation+4.15e-01

Pos logit contributions
Jo+0.018
rum+0.016
jo+0.015
ud+0.015
 Pen+0.014
Neg logit contributions
-0.015
 hotter-0.015
 cooler-0.015
 ang-0.015
 prett-0.015
Token the
Token ID262
Feature activation+4.76e-01

Pos logit contributions
Jo+0.333
rum+0.331
ud+0.297
jo+0.294
and+0.292
Neg logit contributions
-0.186
 Dino-0.155
 surely-0.153
 sack-0.147
 hotter-0.142
Token story
Token ID1621
Feature activation+7.01e-01

Pos logit contributions
+0.054
idents+0.047
 hotter+0.045
 surely+0.045
ory+0.044
Neg logit contributions
Jo-0.035
rum-0.033
 Pen-0.028
ud-0.028
 Ali-0.028
Token is
Token ID318
Feature activation-1.20e+00

Pos logit contributions
+0.058
idents+0.055
 surely+0.051
 sack+0.049
ols+0.048
Neg logit contributions
Jo-0.071
rum-0.063
 Pen-0.056
Jamie-0.056
ud-0.055
Token:
Token ID25
Feature activation+1.79e+00

Pos logit contributions
Jo+0.096
rum+0.092
 Pen+0.079
ud+0.079
 Ali+0.078
Neg logit contributions
-0.127
idents-0.109
 hotter-0.106
 sack-0.105
ory-0.104
Token Acc
Token ID6366
Feature activation-2.01e+00

Pos logit contributions
+0.155
idents+0.135
 surely+0.132
 Dino+0.131
 sack+0.125
Neg logit contributions
Jo-0.177
rum-0.166
ud-0.150
jo-0.148
 Pen-0.144
Tokenidents
Token ID3231
Feature activation+8.22e+00

Pos logit contributions
Jo+0.295
rum+0.289
and+0.275
 Ali+0.272
 Jamie+0.272
Neg logit contributions
-0.067
 surely-0.033
 sack-0.033
 hotter-0.031
 cooler-0.023
Token happen
Token ID1645
Feature activation+1.43e+00

Pos logit contributions
+0.636
idents+0.540
 surely+0.502
 sack+0.498
 hotter+0.497
Neg logit contributions
Jo-0.871
rum-0.841
ud-0.761
 Pen-0.757
 Ali-0.746
Token,
Token ID11
Feature activation-2.36e-02

Pos logit contributions
+0.104
idents+0.097
 sack+0.087
 surely+0.086
ory+0.085
Neg logit contributions
Jo-0.155
rum-0.145
 Pen-0.132
ud-0.130
jo-0.126
Token but
Token ID475
Feature activation-8.64e-01

Pos logit contributions
Jo+0.002
rum+0.002
ud+0.002
 Pen+0.002
jo+0.002
Neg logit contributions
-0.002
idents-0.002
 Dino-0.002
 sack-0.002
 surely-0.002
Token we
Token ID356
Feature activation+1.53e+00

Pos logit contributions
Jo+0.082
rum+0.079
ud+0.069
 Pen+0.069
and+0.068
Neg logit contributions
-0.078
idents-0.066
 sack-0.063
 hotter-0.063
 surely-0.063
Token should
Token ID815
Feature activation+1.07e+00

Pos logit contributions
+0.143
 hotter+0.119
idents+0.119
ory+0.113
Sorry+0.112
Neg logit contributions
Jo-0.138
rum-0.134
 Pen-0.119
ud-0.117
 Ali-0.116
Token okay
Token ID8788
Feature activation+1.24e+00

Pos logit contributions
rum+0.201
Jo+0.182
 supposed+0.164
 about+0.162
 Pen+0.162
Neg logit contributions
-0.274
ory-0.230
 trigger-0.221
glers-0.219
clips-0.217
Token,
Token ID11
Feature activation+1.59e-01

Pos logit contributions
+0.087
idents+0.083
ory+0.071
 sack+0.071
 Dino+0.068
Neg logit contributions
Jo-0.141
rum-0.132
Jamie-0.120
ud-0.120
 Jacob-0.119
Token Lily
Token ID20037
Feature activation+1.40e+00

Pos logit contributions
+0.012
idents+0.010
 hotter+0.009
 sack+0.009
ory+0.009
Neg logit contributions
Jo-0.017
rum-0.017
 Pen-0.015
ud-0.015
and-0.015
Token.
Token ID13
Feature activation+1.10e-01

Pos logit contributions
+0.100
idents+0.090
 sack+0.081
 Dino+0.074
 hotter+0.074
Neg logit contributions
Jo-0.158
rum-0.147
Jamie-0.139
and-0.137
ud-0.136
Token Acc
Token ID6366
Feature activation-1.98e+00

Pos logit contributions
+0.011
idents+0.010
 hotter+0.009
 sack+0.009
 surely+0.009
Neg logit contributions
Jo-0.009
rum-0.009
 Pen-0.008
ud-0.008
and-0.008
Tokenidents
Token ID3231
Feature activation+8.21e+00

Pos logit contributions
rum+0.288
Jo+0.287
and+0.269
jo+0.265
 Jacob+0.261
Neg logit contributions
-0.066
 surely-0.035
 sack-0.034
 hotter-0.031
 Dino-0.026
Token happen
Token ID1645
Feature activation+1.43e+00

Pos logit contributions
+0.716
idents+0.588
ory+0.567
 sack+0.566
 hotter+0.566
Neg logit contributions
Jo-0.810
rum-0.787
 Pen-0.692
and-0.688
ud-0.687
Token.
Token ID13
Feature activation+9.96e-02

Pos logit contributions
+0.126
idents+0.113
 hotter+0.104
 sack+0.102
 surely+0.101
Neg logit contributions
Jo-0.139
rum-0.132
 Pen-0.116
ud-0.116
 Ali-0.114
Token Just
Token ID2329
Feature activation+1.01e+00

Pos logit contributions
+0.010
idents+0.009
 surely+0.008
 hotter+0.008
 Dino+0.008
Neg logit contributions
Jo-0.009
rum-0.008
ud-0.007
 Pen-0.007
and-0.007
Token remember
Token ID3505
Feature activation+4.95e-01

Pos logit contributions
+0.091
idents+0.076
 hotter+0.072
 sack+0.072
ory+0.072
Neg logit contributions
Jo-0.094
rum-0.092
 Pen-0.081
ud-0.080
and-0.080
Token to
Token ID284
Feature activation-5.82e-01

Pos logit contributions
+0.039
idents+0.036
 sack+0.034
 hotter+0.032
 cooler+0.032
Neg logit contributions
Jo-0.052
rum-0.049
jo-0.044
ud-0.043
Jamie-0.043
Token okay
Token ID8788
Feature activation+1.11e+00

Pos logit contributions
Jo+0.281
rum+0.274
 Pen+0.247
 Ali+0.244
ud+0.243
Neg logit contributions
-0.207
idents-0.166
ory-0.158
 sack-0.157
 hotter-0.155
Token,
Token ID11
Feature activation+4.85e-02

Pos logit contributions
idents+0.059
+0.054
ory+0.044
 cooler+0.043
 sack+0.041
Neg logit contributions
Jo-0.140
rum-0.136
ud-0.127
and-0.123
old-0.120
Token Anna
Token ID11735
Feature activation-4.54e+00

Pos logit contributions
idents+0.004
+0.004
 cooler+0.004
 surely+0.004
 hotter+0.004
Neg logit contributions
Jo-0.005
rum-0.005
ud-0.004
jo-0.004
and-0.004
Token.
Token ID13
Feature activation+7.92e-02

Pos logit contributions
Jo+0.546
rum+0.507
and+0.502
Jamie+0.477
ud+0.470
Neg logit contributions
-0.279
 sack-0.235
idents-0.235
 cooler-0.215
 Dino-0.207
Token Acc
Token ID6366
Feature activation-2.01e+00

Pos logit contributions
+0.007
idents+0.006
 Dino+0.005
 sack+0.005
 surely+0.005
Neg logit contributions
Jo-0.008
rum-0.008
and-0.007
ud-0.007
jo-0.006
Tokenidents
Token ID3231
Feature activation+8.21e+00

Pos logit contributions
Jo+0.312
rum+0.309
 Jacob+0.287
 Pen+0.287
 Ali+0.287
Neg logit contributions
-0.054
 surely-0.021
 sack-0.020
 hotter-0.017
 Dino-0.012
Token happen
Token ID1645
Feature activation+1.36e+00

Pos logit contributions
+0.617
idents+0.528
 hotter+0.486
 sack+0.484
 surely+0.477
Neg logit contributions
Jo-0.892
rum-0.858
ud-0.787
 Pen-0.771
 Ali-0.768
Token.
Token ID13
Feature activation+5.99e-02

Pos logit contributions
+0.108
idents+0.100
 hotter+0.090
 cooler+0.088
 sack+0.088
Neg logit contributions
Jo-0.141
rum-0.134
ud-0.121
 Pen-0.117
jo-0.116
Token You
Token ID921
Feature activation-2.68e-01

Pos logit contributions
+0.005
idents+0.005
 Dino+0.004
 surely+0.004
 hotter+0.004
Neg logit contributions
Jo-0.006
rum-0.006
ud-0.005
and-0.005
Jamie-0.005
Token don
Token ID836
Feature activation+1.46e+00

Pos logit contributions
Jo+0.024
rum+0.023
 Pen+0.021
 Ali+0.020
ud+0.020
Neg logit contributions
-0.025
idents-0.021
 hotter-0.020
ory-0.020
 Dino-0.019
Token't
Token ID470
Feature activation+1.90e+00

Pos logit contributions
+0.135
ory+0.134
idents+0.128
 hotter+0.123
 cooler+0.123
Neg logit contributions
Jo-0.125
rum-0.118
 Pen-0.101
ud-0.101
 Ali-0.099
Token
Token ID241
Feature activation+9.59e-01

Pos logit contributions
Jo+0.054
rum+0.052
 Pen+0.046
ud+0.046
and+0.046
Neg logit contributions
-0.051
idents-0.043
 sack-0.041
 hotter-0.041
 surely-0.040
TokenIts
Token ID20459
Feature activation-1.28e+00

Pos logit contributions
+0.070
Sorry+0.054
idents+0.048
 hotter+0.046
ory+0.044
Neg logit contributions
rum-0.106
Jo-0.099
 Pen-0.095
 Ali-0.094
abel-0.093
Token okay
Token ID8788
Feature activation+1.18e+00

Pos logit contributions
Jo+0.135
rum+0.129
ud+0.117
 Pen+0.117
and+0.116
Neg logit contributions
-0.106
idents-0.090
 hotter-0.083
 sack-0.083
 surely-0.083
Token.
Token ID13
Feature activation-1.23e-01

Pos logit contributions
+0.086
idents+0.074
 hotter+0.067
 sack+0.067
ory+0.067
Neg logit contributions
Jo-0.128
rum-0.118
 Pen-0.114
ud-0.113
and-0.110
Token Acc
Token ID6366
Feature activation-2.03e+00

Pos logit contributions
Jo+0.011
rum+0.011
ud+0.010
 Pen+0.009
and+0.009
Neg logit contributions
-0.012
idents-0.010
 sack-0.009
 hotter-0.009
 Dino-0.009
Tokenidents
Token ID3231
Feature activation+8.19e+00

Pos logit contributions
Jo+0.310
rum+0.309
and+0.285
jo+0.284
 Jacob+0.283
Neg logit contributions
-0.057
 surely-0.026
 sack-0.025
 hotter-0.023
 cooler-0.017
Token happen
Token ID1645
Feature activation+1.39e+00

Pos logit contributions
+0.709
idents+0.587
 hotter+0.562
 sack+0.561
ory+0.559
Neg logit contributions
Jo-0.814
rum-0.789
 Pen-0.693
ud-0.689
and-0.688
Token.
Token ID13
Feature activation-1.12e-01

Pos logit contributions
+0.110
idents+0.098
 hotter+0.087
 sack+0.087
 surely+0.087
Neg logit contributions
Jo-0.145
rum-0.137
ud-0.126
 Pen-0.124
and-0.121
Tokenâ
Token ID22940
Feature activation-2.22e+00

Pos logit contributions
Jo+0.011
rum+0.010
ud+0.009
 Pen+0.009
jo+0.009
Neg logit contributions
-0.010
idents-0.008
 Dino-0.008
 hotter-0.008
 sack-0.008
Token
Token ID26391
Feature activation+1.54e+00

Pos logit contributions
rum+0.200
Jo+0.199
jo+0.169
rd+0.167
old+0.161
Neg logit contributions
-0.205
 hotter-0.175
ory-0.174
idents-0.171
 cooler-0.171
Token
Token ID198
Feature activation+2.65e-01

Pos logit contributions
+0.139
idents+0.117
 sack+0.107
 Dino+0.103
 surely+0.100
Neg logit contributions
Jo-0.151
rum-0.146
 Pen-0.131
ud-0.130
and-0.127
Token okay
Token ID8788
Feature activation+1.21e+00

Pos logit contributions
Jo+0.272
rum+0.270
 Pen+0.239
 Ali+0.237
ud+0.237
Neg logit contributions
-0.214
idents-0.173
ory-0.164
 sack-0.163
 hotter-0.159
Token,
Token ID11
Feature activation-3.00e-04

Pos logit contributions
+0.080
idents+0.077
ory+0.066
 cooler+0.063
 sack+0.062
Neg logit contributions
Jo-0.143
rum-0.132
ud-0.123
Jamie-0.118
 Pen-0.117
Token Lily
Token ID20037
Feature activation+1.27e+00

Pos logit contributions
Jo+0.000
rum+0.000
ud+0.000
jo+0.000
and+0.000
Neg logit contributions
-0.000
idents-0.000
 cooler-0.000
 Dino-0.000
 sack-0.000
Token.
Token ID13
Feature activation+1.55e-02

Pos logit contributions
+0.081
idents+0.070
 sack+0.067
 Dino+0.065
 cooler+0.064
Neg logit contributions
Jo-0.153
rum-0.137
Jamie-0.132
and-0.131
ud-0.130
Token Acc
Token ID6366
Feature activation-1.96e+00

Pos logit contributions
+0.001
idents+0.001
 Dino+0.001
 surely+0.001
 sack+0.001
Neg logit contributions
Jo-0.002
rum-0.001
ud-0.001
and-0.001
jo-0.001
Tokenidents
Token ID3231
Feature activation+8.18e+00

Pos logit contributions
rum+0.287
Jo+0.286
and+0.268
 Ali+0.266
 Jacob+0.266
Neg logit contributions
-0.061
 surely-0.031
 sack-0.030
 hotter-0.027
 cooler-0.020
Token happen
Token ID1645
Feature activation+1.33e+00

Pos logit contributions
+0.636
idents+0.543
 hotter+0.505
 sack+0.497
 surely+0.495
Neg logit contributions
Jo-0.872
rum-0.835
ud-0.759
 Pen-0.754
 Ali-0.747
Token.
Token ID13
Feature activation+2.67e-03

Pos logit contributions
+0.108
idents+0.097
 hotter+0.089
 cooler+0.086
 sack+0.086
Neg logit contributions
Jo-0.137
rum-0.129
ud-0.116
 Pen-0.115
jo-0.113
Token I
Token ID314
Feature activation-1.64e+00

Pos logit contributions
+0.000
idents+0.000
 Dino+0.000
 surely+0.000
 hotter+0.000
Neg logit contributions
Jo-0.000
rum-0.000
ud-0.000
and-0.000
Jamie-0.000
Token'm
Token ID1101
Feature activation-2.72e-01

Pos logit contributions
Jo+0.141
rum+0.134
ud+0.117
and+0.116
 Pen+0.114
Neg logit contributions
-0.163
idents-0.135
 hotter-0.134
ory-0.132
 sack-0.132
Token glad
Token ID9675
Feature activation-1.48e+00

Pos logit contributions
Jo+0.030
rum+0.029
ud+0.027
jo+0.026
and+0.026
Neg logit contributions
-0.020
idents-0.017
 hotter-0.016
 cooler-0.016
 surely-0.016
Token okay
Token ID8788
Feature activation+1.22e+00

Pos logit contributions
rum+0.191
Jo+0.166
 supposed+0.160
 about+0.157
 Pen+0.149
Neg logit contributions
-0.277
ory-0.233
glers-0.226
 trigger-0.224
clips-0.221
Token,
Token ID11
Feature activation+2.18e-01

Pos logit contributions
+0.088
idents+0.083
 sack+0.072
ory+0.071
 hotter+0.068
Neg logit contributions
Jo-0.137
rum-0.126
Jamie-0.115
ud-0.115
 Pen-0.115
Token Lily
Token ID20037
Feature activation+1.35e+00

Pos logit contributions
+0.016
idents+0.013
 hotter+0.013
 sack+0.013
 surely+0.012
Neg logit contributions
Jo-0.024
rum-0.023
 Pen-0.021
ud-0.021
and-0.021
Token.
Token ID13
Feature activation+8.46e-02

Pos logit contributions
+0.102
idents+0.092
 sack+0.084
 hotter+0.079
 Dino+0.078
Neg logit contributions
Jo-0.148
rum-0.135
Jamie-0.127
 Jacob-0.127
 Pen-0.126
Token Acc
Token ID6366
Feature activation-1.98e+00

Pos logit contributions
+0.009
idents+0.007
 hotter+0.007
 sack+0.007
 surely+0.007
Neg logit contributions
Jo-0.007
rum-0.007
ud-0.006
 Pen-0.006
and-0.006
Tokenidents
Token ID3231
Feature activation+8.18e+00

Pos logit contributions
rum+0.283
Jo+0.281
and+0.264
jo+0.259
 Jamie+0.258
Neg logit contributions
-0.069
 surely-0.040
 sack-0.038
 hotter-0.033
 cooler-0.031
Token happen
Token ID1645
Feature activation+1.40e+00

Pos logit contributions
+0.744
idents+0.603
ory+0.602
 sack+0.590
 hotter+0.589
Neg logit contributions
Jo-0.777
rum-0.761
and-0.663
 Pen-0.659
ud-0.651
Token.
Token ID13
Feature activation+7.77e-02

Pos logit contributions
+0.127
idents+0.114
 hotter+0.105
 sack+0.104
 surely+0.103
Neg logit contributions
Jo-0.133
rum-0.125
 Pen-0.110
ud-0.110
 Ali-0.108
Token Let
Token ID3914
Feature activation-2.98e+00

Pos logit contributions
+0.008
idents+0.007
 surely+0.007
 hotter+0.007
 Dino+0.007
Neg logit contributions
Jo-0.006
rum-0.006
ud-0.005
 Pen-0.005
and-0.005
Token's
Token ID338
Feature activation-2.50e+00

Pos logit contributions
Jo+0.137
rum+0.116
 Pen+0.096
ud+0.092
and+0.090
Neg logit contributions
-0.417
ory-0.358
idents-0.355
 surely-0.355
 hotter-0.351
Token clean
Token ID3424
Feature activation+4.02e-01

Pos logit contributions
Jo+0.250
rum+0.241
 Pen+0.215
 Ali+0.214
ud+0.212
Neg logit contributions
-0.207
idents-0.170
 hotter-0.165
ory-0.163
 Dino-0.159
Token,
Token ID11
Feature activation+7.57e-02

Pos logit contributions
+0.000
idents+0.000
 sack+0.000
 surely+0.000
ory+0.000
Neg logit contributions
Jo-0.000
rum-0.000
ud-0.000
and-0.000
 Pen-0.000
Token so
Token ID523
Feature activation-3.79e-01

Pos logit contributions
+0.006
 sack+0.005
 cooler+0.005
idents+0.005
 hotter+0.005
Neg logit contributions
Jo-0.008
rum-0.008
ud-0.007
and-0.007
jo-0.007
Token reluctantly
Token ID35462
Feature activation-1.13e+00

Pos logit contributions
Jo+0.045
rum+0.045
ud+0.042
and+0.041
jo+0.039
Neg logit contributions
-0.024
 surely-0.019
 cooler-0.019
 sack-0.019
 hotter-0.019
Token,
Token ID11
Feature activation-5.47e-01

Pos logit contributions
Jo+0.122
rum+0.122
ud+0.113
and+0.110
jo+0.106
Neg logit contributions
-0.082
ory-0.067
 surely-0.067
 sack-0.066
idents-0.063
Token the
Token ID262
Feature activation-2.41e-02

Pos logit contributions
rum+0.061
Jo+0.059
ud+0.055
and+0.053
jo+0.052
Neg logit contributions
-0.040
 sack-0.033
 surely-0.032
 cooler-0.032
 hotter-0.032
Token peanuts
Token ID45612
Feature activation+8.18e+00

Pos logit contributions
Jo+0.002
rum+0.002
 Pen+0.002
ud+0.002
and+0.002
Neg logit contributions
-0.002
idents-0.002
 sack-0.002
 hotter-0.002
 surely-0.002
Token agreed
Token ID4987
Feature activation-6.88e-01

Pos logit contributions
+0.698
idents+0.574
 sack+0.560
 hotter+0.548
 surely+0.547
Neg logit contributions
Jo-0.818
rum-0.794
ud-0.700
 Pen-0.697
and-0.693
Token.
Token ID13
Feature activation-7.16e-01

Pos logit contributions
rum+0.074
Jo+0.074
ud+0.071
jo+0.067
 Pen+0.064
Neg logit contributions
-0.049
idents-0.041
 surely-0.040
 sack-0.040
 cooler-0.040
Token In
Token ID554
Feature activation+2.05e+00

Pos logit contributions
Jo+0.075
rum+0.074
ud+0.066
jo+0.064
and+0.063
Neg logit contributions
-0.061
idents-0.045
 Dino-0.044
ory-0.044
 surely-0.043
Token return
Token ID1441
Feature activation+1.04e+00

Pos logit contributions
+0.161
 surely+0.130
 sack+0.125
 cooler+0.120
 Dino+0.118
Neg logit contributions
Jo-0.224
rum-0.219
and-0.208
ud-0.197
jo-0.195
Token,
Token ID11
Feature activation-6.56e-01

Pos logit contributions
+0.098
idents+0.084
 hotter+0.080
 sack+0.079
 surely+0.079
Neg logit contributions
Jo-0.094
rum-0.090
 Pen-0.079
ud-0.079
and-0.078
Token,
Token ID11
Feature activation-2.05e-01

Pos logit contributions
idents+0.066
+0.061
 sack+0.052
 cooler+0.051
 Ros+0.050
Neg logit contributions
Jo-0.136
rum-0.129
ud-0.126
and-0.117
Jamie-0.112
Token sweet
Token ID6029
Feature activation-1.34e+00

Pos logit contributions
Jo+0.021
rum+0.021
ud+0.021
jo+0.019
and+0.018
Neg logit contributions
idents-0.015
-0.015
 surely-0.013
 cooler-0.013
 hotter-0.013
Tokenie
Token ID494
Feature activation-3.91e-02

Pos logit contributions
Jo+0.143
rum+0.138
and+0.126
ud+0.125
 Pen+0.123
Neg logit contributions
-0.089
idents-0.085
ory-0.084
 sack-0.077
 cooler-0.077
Token.
Token ID13
Feature activation-2.71e-01

Pos logit contributions
Jo+0.004
rum+0.004
ud+0.004
and+0.004
Jamie+0.004
Neg logit contributions
-0.003
idents-0.003
 sack-0.002
 cooler-0.002
 hotter-0.002
Token Acc
Token ID6366
Feature activation-2.12e+00

Pos logit contributions
Jo+0.026
rum+0.025
ud+0.023
and+0.022
jo+0.022
Neg logit contributions
-0.025
idents-0.021
 surely-0.020
 Dino-0.019
 hotter-0.019
Tokenidents
Token ID3231
Feature activation+8.17e+00

Pos logit contributions
Jo+0.338
rum+0.333
 Ali+0.310
 Pen+0.309
 Jacob+0.308
Neg logit contributions
-0.050
 sack-0.014
 surely-0.014
 hotter-0.013
ory-0.008
Token happen
Token ID1645
Feature activation+1.35e+00

Pos logit contributions
+0.636
idents+0.540
 hotter+0.499
 sack+0.496
 surely+0.496
Neg logit contributions
Jo-0.874
rum-0.841
ud-0.767
 Pen-0.755
 Ali-0.751
Token.
Token ID13
Feature activation-2.81e-01

Pos logit contributions
+0.119
idents+0.110
 hotter+0.101
 sack+0.098
 surely+0.098
Neg logit contributions
Jo-0.128
rum-0.123
ud-0.111
 Pen-0.106
 Ali-0.105
Token Let
Token ID3914
Feature activation-3.18e+00

Pos logit contributions
Jo+0.026
rum+0.025
ud+0.023
and+0.022
jo+0.022
Neg logit contributions
-0.027
idents-0.023
 surely-0.021
 Dino-0.021
 hotter-0.020
Token's
Token ID338
Feature activation-2.77e+00

Pos logit contributions
Jo+0.225
rum+0.221
ud+0.183
and+0.178
 Pen+0.178
Neg logit contributions
-0.362
idents-0.323
 sack-0.314
 hotter-0.310
 surely-0.307
Token clean
Token ID3424
Feature activation+2.90e-01

Pos logit contributions
Jo+0.303
rum+0.295
ud+0.265
 Pen+0.263
and+0.263
Neg logit contributions
-0.211
idents-0.172
 sack-0.166
 surely-0.163
 hotter-0.161
Token cry
Token ID3960
Feature activation-3.18e+00

Pos logit contributions
+0.190
idents+0.160
 hotter+0.153
 sack+0.153
 surely+0.151
Neg logit contributions
Jo-0.204
rum-0.197
 Pen-0.173
ud-0.173
and-0.171
Token,
Token ID11
Feature activation+1.91e-02

Pos logit contributions
Jo+0.353
rum+0.325
Jamie+0.299
ud+0.295
 Pen+0.293
Neg logit contributions
-0.240
idents-0.220
ory-0.206
 Dino-0.196
 hotter-0.195
Token boys
Token ID6510
Feature activation+1.25e+00

Pos logit contributions
+0.001
 Dino+0.001
idents+0.001
 sack+0.001
 cooler+0.001
Neg logit contributions
Jo-0.002
rum-0.002
ud-0.002
jo-0.002
and-0.002
Token.
Token ID13
Feature activation-2.31e-01

Pos logit contributions
+0.081
idents+0.071
 sack+0.071
ory+0.068
 cooler+0.065
Neg logit contributions
Jo-0.149
rum-0.136
Jamie-0.130
and-0.128
 Ali-0.126
Token Acc
Token ID6366
Feature activation-2.06e+00

Pos logit contributions
Jo+0.022
rum+0.021
ud+0.019
and+0.018
 Pen+0.018
Neg logit contributions
-0.021
idents-0.018
 sack-0.017
 Dino-0.017
 surely-0.017
Tokenidents
Token ID3231
Feature activation+8.17e+00

Pos logit contributions
rum+0.282
Jo+0.275
and+0.258
 Jamie+0.258
 Jacob+0.257
Neg logit contributions
-0.086
 surely-0.058
 sack-0.046
 cooler-0.039
gem-0.039
Token happen
Token ID1645
Feature activation+1.21e+00

Pos logit contributions
+0.608
idents+0.529
 hotter+0.490
 sack+0.484
 surely+0.475
Neg logit contributions
Jo-0.884
rum-0.839
ud-0.777
 Pen-0.775
 Ali-0.768
Token.
Token ID13
Feature activation-3.06e-01

Pos logit contributions
+0.111
idents+0.096
 hotter+0.091
 sack+0.090
ory+0.090
Neg logit contributions
Jo-0.114
rum-0.108
 Pen-0.096
ud-0.096
 Ali-0.094
Token I
Token ID314
Feature activation-1.65e+00

Pos logit contributions
Jo+0.029
rum+0.027
ud+0.025
and+0.024
 Pen+0.024
Neg logit contributions
-0.028
idents-0.024
 Dino-0.022
 hotter-0.022
 sack-0.022
Token have
Token ID423
Feature activation+5.26e-01

Pos logit contributions
Jo+0.142
rum+0.137
ud+0.119
and+0.117
 Pen+0.115
Neg logit contributions
-0.160
idents-0.132
 hotter-0.130
 Dino-0.130
ory-0.129
Token something
Token ID1223
Feature activation+1.81e+00

Pos logit contributions
+0.044
idents+0.037
 sack+0.037
 hotter+0.035
 Dino+0.035
Neg logit contributions
Jo-0.054
rum-0.052
jo-0.047
 Pen-0.046
 Ali-0.046
Token okay
Token ID8788
Feature activation+1.18e+00

Pos logit contributions
rum+0.236
Jo+0.225
 Pen+0.199
 Ali+0.194
ud+0.193
Neg logit contributions
-0.248
ory-0.203
idents-0.195
 trigger-0.189
 sack-0.189
Token,
Token ID11
Feature activation+5.05e-02

Pos logit contributions
+0.076
idents+0.076
 sack+0.061
 hotter+0.060
ory+0.059
Neg logit contributions
Jo-0.138
rum-0.129
ud-0.120
and-0.118
Jamie-0.118
Token Lily
Token ID20037
Feature activation+1.27e+00

Pos logit contributions
+0.003
idents+0.003
 cooler+0.003
 sack+0.003
 hotter+0.003
Neg logit contributions
Jo-0.006
rum-0.006
ud-0.005
jo-0.005
and-0.005
Token.
Token ID13
Feature activation-6.26e-02

Pos logit contributions
+0.091
idents+0.081
 sack+0.073
 hotter+0.068
 surely+0.067
Neg logit contributions
Jo-0.143
rum-0.132
Jamie-0.125
 Jacob-0.123
and-0.123
Token Acc
Token ID6366
Feature activation-2.05e+00

Pos logit contributions
Jo+0.006
rum+0.005
ud+0.005
and+0.005
 Pen+0.005
Neg logit contributions
-0.006
idents-0.005
 surely-0.005
 Dino-0.005
 sack-0.005
Tokenidents
Token ID3231
Feature activation+8.16e+00

Pos logit contributions
Jo+0.303
rum+0.303
 Ali+0.279
and+0.278
jo+0.278
Neg logit contributions
-0.064
 surely-0.033
 sack-0.032
 hotter-0.025
 cooler-0.023
Token happen
Token ID1645
Feature activation+1.32e+00

Pos logit contributions
+0.718
idents+0.593
ory+0.570
 sack+0.569
 hotter+0.568
Neg logit contributions
Jo-0.798
rum-0.774
 Pen-0.680
and-0.676
ud-0.676
Token.
Token ID13
Feature activation-9.64e-02

Pos logit contributions
+0.119
idents+0.105
 hotter+0.098
 sack+0.097
 surely+0.096
Neg logit contributions
Jo-0.126
rum-0.119
 Pen-0.105
ud-0.105
 Ali-0.103
Token Let
Token ID3914
Feature activation-3.06e+00

Pos logit contributions
Jo+0.009
rum+0.008
ud+0.007
and+0.007
 Pen+0.007
Neg logit contributions
-0.009
idents-0.008
 Dino-0.008
 surely-0.008
 hotter-0.008
Token's
Token ID338
Feature activation-2.59e+00

Pos logit contributions
Jo+0.160
rum+0.142
 Pen+0.117
ud+0.112
and+0.111
Neg logit contributions
-0.410
idents-0.354
ory-0.350
 surely-0.348
 hotter-0.347
Token clean
Token ID3424
Feature activation+3.88e-01

Pos logit contributions
Jo+0.269
rum+0.260
 Pen+0.231
 Ali+0.230
ud+0.230
Neg logit contributions
-0.208
idents-0.169
 hotter-0.162
ory-0.161
 Dino-0.156
Token was
Token ID373
Feature activation-4.93e-01

Pos logit contributions
+0.037
idents+0.033
 hotter+0.032
 sack+0.032
 surely+0.031
Neg logit contributions
Jo-0.025
rum-0.024
ud-0.021
and-0.020
 Pen-0.020
Token an
Token ID281
Feature activation+4.82e-01

Pos logit contributions
Jo+0.040
rum+0.040
 Pen+0.036
 Ali+0.035
 Jacob+0.034
Neg logit contributions
-0.051
idents-0.043
ory-0.042
 sack-0.040
 surely-0.040
Token accident
Token ID5778
Feature activation-3.38e+00

Pos logit contributions
+0.040
idents+0.035
 sack+0.034
 hotter+0.033
ory+0.033
Neg logit contributions
Jo-0.049
rum-0.045
 Pen-0.042
 Ali-0.041
and-0.041
Token.
Token ID13
Feature activation+8.40e-02

Pos logit contributions
Jo+0.357
rum+0.343
Jamie+0.306
ud+0.306
 Pen+0.303
Neg logit contributions
-0.268
idents-0.230
 hotter-0.224
 sack-0.217
 cooler-0.215
Token Acc
Token ID6366
Feature activation-2.00e+00

Pos logit contributions
+0.008
idents+0.007
 Dino+0.006
 surely+0.006
 hotter+0.006
Neg logit contributions
Jo-0.008
rum-0.008
ud-0.007
and-0.007
jo-0.007
Tokenidents
Token ID3231
Feature activation+8.15e+00

Pos logit contributions
Jo+0.290
rum+0.290
and+0.272
 Ali+0.270
 Jacob+0.269
Neg logit contributions
-0.066
 surely-0.035
 sack-0.033
 hotter-0.029
 Dino-0.025
Token happen
Token ID1645
Feature activation+1.33e+00

Pos logit contributions
+0.670
idents+0.559
 hotter+0.528
 sack+0.526
 surely+0.521
Neg logit contributions
Jo-0.838
rum-0.809
ud-0.722
 Pen-0.721
 Ali-0.712
Token.
Token ID13
Feature activation+7.12e-02

Pos logit contributions
+0.101
idents+0.092
 hotter+0.083
 cooler+0.082
 sack+0.081
Neg logit contributions
Jo-0.143
rum-0.134
ud-0.121
 Pen-0.120
jo-0.118
Token I
Token ID314
Feature activation-1.63e+00

Pos logit contributions
+0.006
idents+0.006
 Dino+0.005
 hotter+0.005
 surely+0.005
Neg logit contributions
Jo-0.007
rum-0.007
ud-0.006
and-0.006
jo-0.006
Token'm
Token ID1101
Feature activation-2.57e-01

Pos logit contributions
Jo+0.129
rum+0.120
ud+0.105
and+0.103
 Pen+0.101
Neg logit contributions
-0.174
idents-0.148
 hotter-0.147
ory-0.145
 sack-0.143
Token not
Token ID407
Feature activation+4.15e-01

Pos logit contributions
Jo+0.028
rum+0.027
ud+0.024
 Pen+0.024
and+0.024
Neg logit contributions
-0.020
idents-0.016
 hotter-0.015
 sack-0.015
 surely-0.015
Token gives
Token ID3607
Feature activation+8.20e-01

Pos logit contributions
+0.008
 cooler+0.007
 sack+0.007
idents+0.006
 surely+0.006
Neg logit contributions
rum-0.011
Jo-0.010
and-0.010
ud-0.009
jo-0.009
Token Sara
Token ID24799
Feature activation-2.29e+00

Pos logit contributions
+0.072
idents+0.060
 hotter+0.057
 sack+0.057
 surely+0.057
Neg logit contributions
Jo-0.080
rum-0.077
 Pen-0.069
ud-0.068
 Ali-0.068
Token a
Token ID257
Feature activation+2.29e-02

Pos logit contributions
Jo+0.237
rum+0.232
ud+0.202
and+0.196
jo+0.195
Neg logit contributions
-0.178
ory-0.155
 cooler-0.154
 sack-0.154
idents-0.154
Token bowl
Token ID9396
Feature activation+1.92e-01

Pos logit contributions
+0.002
idents+0.002
 hotter+0.001
 sack+0.001
 surely+0.001
Neg logit contributions
Jo-0.002
rum-0.002
 Pen-0.002
ud-0.002
and-0.002
Token of
Token ID286
Feature activation-2.47e+00

Pos logit contributions
+0.020
idents+0.017
 sack+0.017
ory+0.017
 surely+0.016
Neg logit contributions
Jo-0.016
rum-0.015
 Pen-0.013
ud-0.013
 Ali-0.013
Token peanuts
Token ID45612
Feature activation+8.15e+00

Pos logit contributions
Jo+0.260
rum+0.253
 Pen+0.228
ud+0.225
 Ali+0.224
Neg logit contributions
-0.193
idents-0.159
 surely-0.149
 hotter-0.148
 sack-0.147
Token and
Token ID290
Feature activation+7.46e-01

Pos logit contributions
+0.816
idents+0.713
 hotter+0.690
 surely+0.677
 sack+0.661
Neg logit contributions
Jo-0.658
rum-0.653
and-0.569
 Pen-0.565
ud-0.558
Token Ben
Token ID3932
Feature activation-5.43e-01

Pos logit contributions
+0.057
 sack+0.047
idents+0.047
 cooler+0.045
 Dino+0.045
Neg logit contributions
Jo-0.082
rum-0.080
and-0.073
ud-0.072
jo-0.070
Token a
Token ID257
Feature activation-6.61e-02

Pos logit contributions
Jo+0.055
rum+0.051
ud+0.046
and+0.046
jo+0.045
Neg logit contributions
-0.047
 sack-0.039
idents-0.039
ory-0.038
 cooler-0.038
Token bowl
Token ID9396
Feature activation+9.83e-02

Pos logit contributions
Jo+0.007
rum+0.006
 Pen+0.006
ud+0.006
 Ali+0.006
Neg logit contributions
-0.005
idents-0.005
 hotter-0.004
 surely-0.004
ory-0.004
Token of
Token ID286
Feature activation-2.54e+00

Pos logit contributions
+0.009
 cooler+0.007
idents+0.007
ory+0.007
 sack+0.007
Neg logit contributions
Jo-0.010
rum-0.009
 Ali-0.008
 Pen-0.008
ud-0.008
Token happy
Token ID3772
Feature activation-1.19e+00

Pos logit contributions
+0.169
 sack+0.147
 cooler+0.141
 surely+0.140
ory+0.137
Neg logit contributions
rum-0.207
Jo-0.202
and-0.177
ud-0.177
jo-0.170
Token boy
Token ID2933
Feature activation-6.06e-02

Pos logit contributions
rum+0.126
Jo+0.124
ud+0.111
and+0.111
 Pen+0.110
Neg logit contributions
-0.093
 sack-0.083
 cooler-0.077
 surely-0.074
idents-0.073
Token.
Token ID13
Feature activation-1.35e-01

Pos logit contributions
Jo+0.006
rum+0.006
ud+0.006
Jamie+0.005
 Pen+0.005
Neg logit contributions
-0.005
 surely-0.004
 Dino-0.004
 sack-0.004
ory-0.004
Token<|endoftext|>
Token ID50256
Feature activation-3.16e-01

Pos logit contributions
Jo+0.015
rum+0.014
ud+0.013
 Pen+0.013
and+0.012
Neg logit contributions
-0.011
 Dino-0.008
ory-0.008
idents-0.008
 surely-0.007
TokenJo
Token ID9908
Feature activation-1.06e+01

Pos logit contributions
Jo+0.039
rum+0.039
ud+0.034
 Pen+0.034
and+0.034
Neg logit contributions
-0.020
idents-0.014
 sack-0.014
 hotter-0.013
ory-0.013
TokenJo
Token ID9908
Feature activation-1.07e+01

Pos logit contributions
rum+1.049
and+0.967
Jo+0.925
ud+0.893
 Pen+0.885
Neg logit contributions
-0.813
ory-0.734
 surely-0.693
 sack-0.656
idents-0.646
Token was
Token ID373
Feature activation-7.78e-01

Pos logit contributions
rum+1.066
and+0.981
Jo+0.938
ud+0.900
 Pen+0.897
Neg logit contributions
-0.808
ory-0.712
 surely-0.677
 sack-0.645
 continued-0.638
Token sad
Token ID6507
Feature activation+1.13e+00

Pos logit contributions
rum+0.086
Jo+0.084
jo+0.074
ud+0.074
and+0.073
Neg logit contributions
-0.060
 surely-0.051
 hotter-0.049
 cooler-0.049
 prett-0.047
Token.
Token ID13
Feature activation-1.37e-01

Pos logit contributions
+0.092
idents+0.078
 sack+0.075
 cooler+0.073
 hotter+0.071
Neg logit contributions
Jo-0.118
rum-0.115
 Pen-0.103
ud-0.102
 Ali-0.100
Token He
Token ID679
Feature activation+1.30e-01

Pos logit contributions
rum+0.017
ud+0.016
e+0.016
ggie+0.016
Jo+0.016
Neg logit contributions
-0.006
idents-0.004
 cooler-0.004
 surely-0.003
 still-0.003
Token wanted
Token ID2227
Feature activation-2.68e+00

Pos logit contributions
+0.011
idents+0.009
 sack+0.009
 surely+0.009
 cooler+0.008
Neg logit contributions
rum-0.013
Jo-0.013
and-0.012
 Pen-0.011
ud-0.011
Token and
Token ID290
Feature activation+1.68e-01

Pos logit contributions
Jo+0.066
rum+0.065
Jamie+0.060
 Pen+0.060
old+0.059
Neg logit contributions
-0.027
 cooler-0.025
idents-0.024
 hotter-0.023
 sack-0.022
Token harder
Token ID7069
Feature activation-5.39e-01

Pos logit contributions
+0.015
ory+0.012
idents+0.012
 sack+0.012
 Dino+0.011
Neg logit contributions
Jo-0.016
rum-0.015
 Pen-0.014
 Ali-0.014
 Jacob-0.014
Token.
Token ID13
Feature activation-2.07e-01

Pos logit contributions
Jo+0.063
rum+0.060
Jamie+0.057
ud+0.057
and+0.055
Neg logit contributions
-0.031
idents-0.029
 cooler-0.028
 sack-0.026
 hotter-0.026
Token
Token ID198
Feature activation+2.86e-02

Pos logit contributions
rum+0.022
Jo+0.021
ud+0.019
and+0.018
jo+0.018
Neg logit contributions
-0.017
idents-0.014
 sack-0.013
 Dino-0.013
 hotter-0.013
Token
Token ID198
Feature activation+6.18e-03

Pos logit contributions
+0.001
 Dino+0.001
Ros+0.001
Sorry+0.001
 surely+0.001
Neg logit contributions
rum-0.004
Jo-0.003
 clim-0.003
abel-0.003
ud-0.003
TokenJo
Token ID9908
Feature activation-1.07e+01

Pos logit contributions
+0.000
Sorry+0.000
 sack+0.000
 Dino+0.000
 surely+0.000
Neg logit contributions
rum-0.001
Jo-0.001
ud-0.001
 Pen-0.001
abel-0.001
Tokenjo
Token ID7639
Feature activation-7.45e+00

Pos logit contributions
rum+1.102
and+0.947
Jo+0.944
 Jacob+0.940
 Pen+0.911
Neg logit contributions
-0.762
ory-0.675
ized-0.653
 surely-0.648
 sack-0.637
Token and
Token ID290
Feature activation+1.41e-01

Pos logit contributions
rum+0.889
Jo+0.798
and+0.777
ud+0.723
 Jacob+0.722
Neg logit contributions
-0.469
 sack-0.406
 continued-0.384
ory-0.373
 surely-0.368
Token his
Token ID465
Feature activation-1.40e+00

Pos logit contributions
 sack+0.009
+0.009
 Dino+0.009
idents+0.009
 cooler+0.008
Neg logit contributions
rum-0.015
Jo-0.015
ud-0.014
and-0.014
rd-0.013
Token mom
Token ID1995
Feature activation+1.25e+00

Pos logit contributions
Jo+0.132
rum+0.125
 Pen+0.112
ud+0.111
 Ali+0.110
Neg logit contributions
-0.128
idents-0.109
 hotter-0.105
 surely-0.103
ory-0.102
Token were
Token ID547
Feature activation-4.63e-01

Pos logit contributions
+0.087
 sack+0.069
idents+0.068
 hotter+0.067
ory+0.066
Neg logit contributions
rum-0.142
Jo-0.141
 Pen-0.125
and-0.124
ud-0.123
Token lucky
Token ID9670
Feature activation+2.02e+00

Pos logit contributions
Jo+0.041
rum+0.039
 Pen+0.035
ud+0.034
 Ali+0.034
Neg logit contributions
-0.039
idents-0.033
 hotter-0.031
 sack-0.031
ory-0.031
Token happy
Token ID3772
Feature activation-1.19e+00

Pos logit contributions
+0.169
 sack+0.147
 cooler+0.141
 surely+0.140
ory+0.137
Neg logit contributions
rum-0.207
Jo-0.202
and-0.177
ud-0.177
jo-0.170
Token boy
Token ID2933
Feature activation-6.06e-02

Pos logit contributions
rum+0.126
Jo+0.124
ud+0.111
and+0.111
 Pen+0.110
Neg logit contributions
-0.093
 sack-0.083
 cooler-0.077
 surely-0.074
idents-0.073
Token.
Token ID13
Feature activation-1.35e-01

Pos logit contributions
Jo+0.006
rum+0.006
ud+0.006
Jamie+0.005
 Pen+0.005
Neg logit contributions
-0.005
 surely-0.004
 Dino-0.004
 sack-0.004
ory-0.004
Token<|endoftext|>
Token ID50256
Feature activation-3.16e-01

Pos logit contributions
Jo+0.015
rum+0.014
ud+0.013
 Pen+0.013
and+0.012
Neg logit contributions
-0.011
 Dino-0.008
ory-0.008
idents-0.008
 surely-0.007
TokenJo
Token ID9908
Feature activation-1.06e+01

Pos logit contributions
Jo+0.039
rum+0.039
ud+0.034
 Pen+0.034
and+0.034
Neg logit contributions
-0.020
idents-0.014
 sack-0.014
 hotter-0.013
ory-0.013
TokenJo
Token ID9908
Feature activation-1.07e+01

Pos logit contributions
rum+1.049
and+0.967
Jo+0.925
ud+0.893
 Pen+0.885
Neg logit contributions
-0.813
ory-0.734
 surely-0.693
 sack-0.656
idents-0.646
Token was
Token ID373
Feature activation-7.78e-01

Pos logit contributions
rum+1.066
and+0.981
Jo+0.938
ud+0.900
 Pen+0.897
Neg logit contributions
-0.808
ory-0.712
 surely-0.677
 sack-0.645
 continued-0.638
Token sad
Token ID6507
Feature activation+1.13e+00

Pos logit contributions
rum+0.086
Jo+0.084
jo+0.074
ud+0.074
and+0.073
Neg logit contributions
-0.060
 surely-0.051
 hotter-0.049
 cooler-0.049
 prett-0.047
Token.
Token ID13
Feature activation-1.37e-01

Pos logit contributions
+0.092
idents+0.078
 sack+0.075
 cooler+0.073
 hotter+0.071
Neg logit contributions
Jo-0.118
rum-0.115
 Pen-0.103
ud-0.102
 Ali-0.100
Token He
Token ID679
Feature activation+1.30e-01

Pos logit contributions
rum+0.017
ud+0.016
e+0.016
ggie+0.016
Jo+0.016
Neg logit contributions
-0.006
idents-0.004
 cooler-0.004
 surely-0.003
 still-0.003
Token to
Token ID284
Feature activation-8.96e-01

Pos logit contributions
+0.085
idents+0.073
 hotter+0.069
ory+0.067
Sorry+0.066
Neg logit contributions
Jo-0.087
rum-0.083
 Pen-0.073
and-0.073
 Ali-0.072
Token the
Token ID262
Feature activation+1.86e-01

Pos logit contributions
rum+0.103
Jo+0.100
ud+0.097
and+0.092
jo+0.092
Neg logit contributions
-0.060
 sack-0.053
 surely-0.048
 cooler-0.047
 Dino-0.047
Token village
Token ID7404
Feature activation-5.32e-01

Pos logit contributions
+0.015
idents+0.012
ory+0.011
 hotter+0.011
 surely+0.011
Neg logit contributions
Jo-0.019
rum-0.018
 Pen-0.017
ud-0.017
 Jacob-0.016
Token.
Token ID13
Feature activation-4.15e-01

Pos logit contributions
rum+0.059
Jo+0.057
ud+0.054
 Pen+0.051
 Ali+0.050
Neg logit contributions
-0.036
 sack-0.033
 cooler-0.032
 surely-0.031
ized-0.030
Token Jo
Token ID5302
Feature activation-7.10e+00

Pos logit contributions
rum+0.047
ud+0.043
Jo+0.040
and+0.040
rd+0.039
Neg logit contributions
-0.029
idents-0.020
 Dino-0.020
 surely-0.019
 hotter-0.018
TokenJo
Token ID9908
Feature activation-1.06e+01

Pos logit contributions
rum+0.329
and+0.221
ud+0.214
uzzle+0.206
 liar+0.194
Neg logit contributions
-0.881
 surely-0.835
 continued-0.818
 finally-0.813
 still-0.811
Token smiled
Token ID13541
Feature activation-1.73e-01

Pos logit contributions
rum+1.046
and+0.937
ud+0.877
uzzle+0.830
Jo+0.826
Neg logit contributions
-0.835
 surely-0.732
ized-0.713
ory-0.706
 continued-0.699
Token with
Token ID351
Feature activation+1.21e-02

Pos logit contributions
Jo+0.015
rum+0.014
 Pen+0.012
 Ali+0.012
 Jacob+0.012
Neg logit contributions
-0.018
idents-0.015
 sack-0.014
 hotter-0.014
 surely-0.014
Token anticipation
Token ID24054
Feature activation-2.52e+00

Pos logit contributions
+0.001
idents+0.001
 sack+0.001
 surely+0.001
 hotter+0.001
Neg logit contributions
Jo-0.001
rum-0.001
ud-0.001
 Pen-0.001
and-0.001
Token and
Token ID290
Feature activation+6.94e-03

Pos logit contributions
Jo+0.264
rum+0.259
ud+0.238
 Pen+0.237
 Ali+0.231
Neg logit contributions
-0.194
idents-0.156
 surely-0.155
ory-0.152
 sack-0.151
Token asked
Token ID1965
Feature activation-8.59e-01

Pos logit contributions
+0.000
 surely+0.000
idents+0.000
 sack+0.000
 Dino+0.000
Neg logit contributions
rum-0.001
Jo-0.001
ud-0.001
and-0.001
jo-0.001
Token unloaded
Token ID49975
Feature activation+1.05e+00

Pos logit contributions
Jo+0.064
rum+0.062
ud+0.056
and+0.055
 Pen+0.055
Neg logit contributions
-0.053
 hotter-0.043
 surely-0.043
idents-0.043
 sack-0.042
Token,
Token ID11
Feature activation-1.74e-01

Pos logit contributions
+0.103
idents+0.088
 hotter+0.083
ory+0.083
 sack+0.083
Neg logit contributions
Jo-0.091
rum-0.088
 Pen-0.076
 Ali-0.076
ud-0.076
Token John
Token ID1757
Feature activation-5.01e+00

Pos logit contributions
rum+0.017
ud+0.014
Jo+0.014
and+0.014
rd+0.014
Neg logit contributions
-0.015
 hotter-0.013
 surely-0.013
 cooler-0.013
 Dino-0.012
Token and
Token ID290
Feature activation+2.07e-01

Pos logit contributions
rum+0.534
Jo+0.510
and+0.469
ud+0.465
 Pen+0.458
Neg logit contributions
-0.379
 surely-0.310
 sack-0.304
ory-0.299
idents-0.292
Token Jo
Token ID5302
Feature activation-7.09e+00

Pos logit contributions
 surely+0.020
+0.019
 Dino+0.019
 Ros+0.018
 continued+0.018
Neg logit contributions
rum-0.014
ud-0.013
and-0.012
rd-0.011
old-0.011
TokenJo
Token ID9908
Feature activation-1.06e+01

Pos logit contributions
rum+0.622
and+0.532
ud+0.505
 Pen+0.474
Jo+0.464
Neg logit contributions
-0.621
 surely-0.576
 continued-0.551
ory-0.550
 finally-0.525
Token started
Token ID2067
Feature activation+2.69e+00

Pos logit contributions
rum+1.155
and+1.068
Jo+1.006
ud+0.987
 Pen+0.985
Neg logit contributions
-0.744
 surely-0.622
ory-0.603
 continued-0.592
ized-0.591
Token to
Token ID284
Feature activation-9.34e-01

Pos logit contributions
+0.239
 sack+0.196
 hotter+0.195
 cooler+0.191
idents+0.188
Neg logit contributions
rum-0.249
Jo-0.243
jo-0.222
ud-0.222
 Pen-0.220
Token make
Token ID787
Feature activation+9.41e-02

Pos logit contributions
Jo+0.101
rum+0.100
ud+0.093
and+0.092
jo+0.089
Neg logit contributions
-0.071
 sack-0.058
idents-0.056
 surely-0.055
 hotter-0.054
Token their
Token ID511
Feature activation-1.18e+00

Pos logit contributions
+0.008
idents+0.007
 hotter+0.007
 sack+0.007
 cooler+0.006
Neg logit contributions
rum-0.009
Jo-0.009
ud-0.008
and-0.008
 Pen-0.008
Token way
Token ID835
Feature activation-3.76e+00

Pos logit contributions
Jo+0.122
rum+0.118
 Pen+0.105
ud+0.104
and+0.103
Neg logit contributions
-0.098
idents-0.081
 hotter-0.077
 sack-0.077
 surely-0.076
Token felt
Token ID2936
Feature activation+1.32e+00

Pos logit contributions
rum+0.074
Jo+0.072
and+0.065
ud+0.065
 Pen+0.063
Neg logit contributions
-0.051
 surely-0.042
 sack-0.041
idents-0.040
ory-0.040
Token so
Token ID523
Feature activation-4.72e-01

Pos logit contributions
+0.118
idents+0.098
 surely+0.097
 hotter+0.096
 sack+0.096
Neg logit contributions
Jo-0.126
rum-0.122
ud-0.109
 Pen-0.106
 Ali-0.106
Token proud
Token ID6613
Feature activation+3.68e+00

Pos logit contributions
Jo+0.052
rum+0.050
ud+0.045
 Pen+0.045
 Ali+0.045
Neg logit contributions
-0.036
idents-0.029
 surely-0.028
 sack-0.028
 hotter-0.027
Token!
Token ID0
Feature activation+1.45e-01

Pos logit contributions
+0.314
 cooler+0.261
ory+0.259
 sack+0.256
idents+0.252
Neg logit contributions
rum-0.354
Jo-0.342
 Pen-0.304
Jamie-0.296
jo-0.296
Token<|endoftext|>
Token ID50256
Feature activation-4.07e-01

Pos logit contributions
+0.012
idents+0.009
 surely+0.008
ory+0.008
 Dino+0.008
Neg logit contributions
rum-0.015
Jo-0.015
ud-0.014
and-0.013
jo-0.013
TokenJo
Token ID9908
Feature activation-1.06e+01

Pos logit contributions
rum+0.051
Jo+0.051
ud+0.045
 Ali+0.045
 Pen+0.045
Neg logit contributions
-0.024
 sack-0.016
idents-0.016
 hotter-0.015
ory-0.015
Token was
Token ID373
Feature activation-7.60e-01

Pos logit contributions
rum+1.016
and+0.947
Jo+0.915
ud+0.868
 Pen+0.848
Neg logit contributions
-0.846
ory-0.762
 surely-0.719
 sack-0.686
idents-0.684
Token a
Token ID257
Feature activation-3.72e-01

Pos logit contributions
rum+0.085
Jo+0.081
jo+0.072
ud+0.072
and+0.071
Neg logit contributions
-0.059
 surely-0.050
 hotter-0.049
 cooler-0.048
 prett-0.047
Token lively
Token ID29696
Feature activation+1.36e+00

Pos logit contributions
Jo+0.034
rum+0.033
 Pen+0.029
ud+0.029
 Ali+0.028
Neg logit contributions
-0.035
idents-0.030
 hotter-0.028
 sack-0.028
 surely-0.028
Token three
Token ID1115
Feature activation-4.46e+00

Pos logit contributions
+0.105
 sack+0.091
ory+0.088
 cooler+0.086
 surely+0.079
Neg logit contributions
rum-0.154
Jo-0.143
and-0.133
ud-0.126
jo-0.122
Token-
Token ID12
Feature activation+1.79e-01

Pos logit contributions
rum+0.383
Jo+0.347
 Pen+0.329
 Ali+0.328
and+0.326
Neg logit contributions
-0.376
ory-0.352
 sack-0.337
 cooler-0.331
ized-0.325
Token friend
Token ID1545
Feature activation+8.10e-02

Pos logit contributions
+0.027
 sack+0.025
ory+0.023
 cooler+0.022
 surely+0.020
Neg logit contributions
rum-0.039
Jo-0.038
 Pen-0.035
 Ali-0.034
 Jacob-0.034
Token Jo
Token ID5302
Feature activation-7.08e+00

Pos logit contributions
+0.006
 sack+0.005
 Dino+0.005
ory+0.005
 cooler+0.005
Neg logit contributions
rum-0.009
Jo-0.008
ud-0.008
Jamie-0.007
 Pen-0.007
TokenJo
Token ID9908
Feature activation-1.06e+01

Pos logit contributions
rum+0.680
ud+0.574
and+0.549
Jo+0.529
Jamie+0.510
Neg logit contributions
-0.564
ory-0.513
 surely-0.467
 finally-0.451
ized-0.442
Token.
Token ID13
Feature activation-3.41e-01

Pos logit contributions
rum+1.054
and+0.946
ud+0.897
Jo+0.869
 Ali+0.841
Neg logit contributions
-0.842
 surely-0.696
ory-0.685
ized-0.662
 continued-0.652
Token Jo
Token ID5302
Feature activation-7.07e+00

Pos logit contributions
rum+0.036
ud+0.033
ggie+0.031
rd+0.031
e+0.030
Neg logit contributions
-0.025
 surely-0.018
 Dino-0.017
idents-0.017
 Ros-0.017
TokenJo
Token ID9908
Feature activation-1.06e+01

Pos logit contributions
rum+0.371
and+0.252
uzzle+0.251
ud+0.250
 liar+0.231
Neg logit contributions
-0.832
 surely-0.784
 still-0.772
 continued-0.769
 finally-0.769
Token was
Token ID373
Feature activation-8.11e-01

Pos logit contributions
rum+1.099
and+0.984
ud+0.928
uzzle+0.887
Jo+0.885
Neg logit contributions
-0.810
 surely-0.691
ized-0.686
 continued-0.648
ory-0.645
Token thrilled
Token ID20536
Feature activation-1.09e+00

Pos logit contributions
rum+0.094
Jo+0.086
ud+0.084
jo+0.082
and+0.080
Neg logit contributions
-0.055
 surely-0.051
 still-0.048
 cooler-0.046
 hotter-0.046
Token to
Token ID284
Feature activation-9.25e-01

Pos logit contributions
rum+0.110
Jo+0.108
ud+0.098
 Pen+0.095
 Ali+0.092
Neg logit contributions
-0.091
idents-0.080
ory-0.073
 surely-0.072
 sack-0.072
Token see
Token ID766
Feature activation+5.46e-01

Pos logit contributions
Jo+0.096
rum+0.093
ud+0.086
and+0.083
 Pen+0.083
Neg logit contributions
-0.076
idents-0.060
 surely-0.060
 sack-0.060
ory-0.057
Token Big
Token ID4403
Feature activation-2.43e+00

Pos logit contributions
 Dino+0.025
 cooler+0.024
 prett+0.024
 brand+0.023
 Ros+0.022
Neg logit contributions
rum-0.069
ud-0.062
rd-0.060
and-0.057
anne-0.057
Token've
Token ID1053
Feature activation+7.29e-01

Pos logit contributions
+0.139
idents+0.113
 surely+0.113
 sack+0.111
ory+0.108
Neg logit contributions
Jo-0.154
rum-0.152
and-0.138
 Pen-0.137
 Ali-0.133
Token got
Token ID1392
Feature activation+1.81e+00

Pos logit contributions
+0.068
 surely+0.058
 sack+0.058
idents+0.056
 cooler+0.055
Neg logit contributions
rum-0.064
Jo-0.063
jo-0.056
and-0.056
 Ali-0.056
Token an
Token ID281
Feature activation+3.51e-01

Pos logit contributions
+0.173
idents+0.147
 sack+0.139
 hotter+0.138
ory+0.138
Neg logit contributions
Jo-0.162
rum-0.156
 Pen-0.136
ud-0.135
and-0.134
Token idea
Token ID2126
Feature activation+1.31e+00

Pos logit contributions
+0.029
idents+0.024
 sack+0.023
 surely+0.023
 hotter+0.023
Neg logit contributions
Jo-0.036
rum-0.035
 Pen-0.031
 Ali-0.031
ud-0.031
Token Jo
Token ID5302
Feature activation-7.08e+00

Pos logit contributions
+0.084
 sack+0.075
 surely+0.073
 cooler+0.072
 reward+0.068
Neg logit contributions
Jo-0.136
ud-0.134
rum-0.121
jo-0.119
 Pen-0.119
TokenJo
Token ID9908
Feature activation-1.06e+01

Pos logit contributions
ud+0.619
rum+0.613
Jo+0.556
and+0.534
Jamie+0.526
Neg logit contributions
-0.566
 surely-0.513
ory-0.497
 sack-0.473
idents-0.460
Token.
Token ID13
Feature activation-3.53e-01

Pos logit contributions
ud+0.942
rum+0.936
Jo+0.894
and+0.892
Jamie+0.851
Neg logit contributions
-0.885
 surely-0.770
 sack-0.740
ory-0.719
idents-0.697
Token Maybe
Token ID6674
Feature activation+2.15e-01

Pos logit contributions
Jo+0.033
rum+0.033
ud+0.032
and+0.030
jo+0.028
Neg logit contributions
-0.030
 Dino-0.024
 surely-0.024
idents-0.024
 sack-0.023
Token next
Token ID1306
Feature activation+2.93e+00

Pos logit contributions
+0.012
 Dino+0.011
 cooler+0.011
 surely+0.011
 sack+0.010
Neg logit contributions
rum-0.025
ud-0.024
Jo-0.023
jo-0.022
and-0.021
Token time
Token ID640
Feature activation-1.08e+00

Pos logit contributions
+0.253
 surely+0.219
idents+0.209
 cooler+0.208
 sack+0.202
Neg logit contributions
rum-0.277
Jo-0.267
and-0.252
 Pen-0.244
ud-0.242
Token we
Token ID356
Feature activation+1.21e+00

Pos logit contributions
rum+0.115
Jo+0.111
ud+0.110
and+0.099
jo+0.097
Neg logit contributions
-0.073
 surely-0.067
idents-0.067
 Dino-0.066
 sack-0.066
TokenDon
Token ID3987
Feature activation+1.91e+00

Pos logit contributions
rum+0.087
Jo+0.072
 Jacob+0.072
ud+0.071
 Pen+0.071
Neg logit contributions
-0.072
Sorry-0.070
 hotter-0.069
idents-0.065
 surely-0.064
Token't
Token ID470
Feature activation+1.73e+00

Pos logit contributions
+0.143
idents+0.114
 surely+0.110
 sack+0.106
 hotter+0.105
Neg logit contributions
Jo-0.207
rum-0.206
ud-0.186
and-0.183
 Pen-0.182
Token worry
Token ID5490
Feature activation-1.37e+00

Pos logit contributions
+0.135
idents+0.120
 sack+0.115
 hotter+0.110
ory+0.110
Neg logit contributions
Jo-0.180
rum-0.174
ud-0.161
 Pen-0.157
jo-0.154
Token,
Token ID11
Feature activation-1.04e-01

Pos logit contributions
rum+0.140
ud+0.137
Jo+0.136
e+0.135
old+0.131
Neg logit contributions
idents-0.082
 cooler-0.069
-0.064
 Dino-0.062
ory-0.062
Token Jo
Token ID5302
Feature activation-7.02e+00

Pos logit contributions
rum+0.009
ud+0.009
old+0.008
anne+0.008
e+0.008
Neg logit contributions
idents-0.008
 cooler-0.008
 surely-0.007
 hotter-0.007
-0.007
TokenJo
Token ID9908
Feature activation-1.06e+01

Pos logit contributions
and+0.562
ud+0.547
rum+0.531
Jo+0.518
 Jacob+0.485
Neg logit contributions
-0.567
idents-0.512
 Dino-0.508
 surely-0.503
ory-0.501
Token.
Token ID13
Feature activation-1.95e-01

Pos logit contributions
and+1.017
Jo+1.007
rum+0.982
ud+0.958
Jamie+0.917
Neg logit contributions
-0.831
idents-0.710
 sack-0.701
 surely-0.678
ory-0.663
Token I
Token ID314
Feature activation-1.78e+00

Pos logit contributions
Jo+0.018
rum+0.018
ud+0.016
and+0.015
 Pen+0.015
Neg logit contributions
-0.018
idents-0.015
 Dino-0.015
 surely-0.014
 sack-0.014
Token can
Token ID460
Feature activation+1.78e+00

Pos logit contributions
Jo+0.168
rum+0.162
ud+0.142
 Pen+0.142
and+0.140
Neg logit contributions
-0.162
idents-0.137
 hotter-0.131
 sack-0.130
ory-0.129
Token help
Token ID1037
Feature activation+1.09e+00

Pos logit contributions
+0.137
idents+0.112
 sack+0.105
 hotter+0.105
 surely+0.104
Neg logit contributions
Jo-0.192
rum-0.187
ud-0.167
 Pen-0.167
and-0.165
Token you
Token ID345
Feature activation+1.58e-01

Pos logit contributions
+0.063
idents+0.057
 sack+0.053
 Dino+0.050
 hotter+0.049
Neg logit contributions
Jo-0.126
rum-0.123
ud-0.120
jo-0.115
rd-0.113
Token into
Token ID656
Feature activation+3.01e+00

Pos logit contributions
Jo+0.221
rum+0.215
ud+0.191
 Pen+0.191
 Ali+0.188
Neg logit contributions
-0.163
idents-0.134
 sack-0.127
 hotter-0.126
 surely-0.126
Token his
Token ID465
Feature activation-1.38e+00

Pos logit contributions
+0.193
 sack+0.169
 cooler+0.161
 Dino+0.143
 hotter+0.137
Neg logit contributions
rum-0.344
Jo-0.329
jo-0.315
ud-0.309
and-0.308
Token best
Token ID1266
Feature activation+3.61e-01

Pos logit contributions
Jo+0.139
rum+0.136
ud+0.119
and+0.118
 Pen+0.115
Neg logit contributions
-0.121
 sack-0.102
idents-0.099
 cooler-0.096
 surely-0.094
Token friend
Token ID1545
Feature activation+8.10e-02

Pos logit contributions
+0.027
 sack+0.025
ory+0.023
 cooler+0.022
 surely+0.020
Neg logit contributions
rum-0.039
Jo-0.038
 Pen-0.035
 Ali-0.034
 Jacob-0.034
Token Jo
Token ID5302
Feature activation-7.08e+00

Pos logit contributions
+0.006
 sack+0.005
 Dino+0.005
ory+0.005
 cooler+0.005
Neg logit contributions
rum-0.009
Jo-0.008
ud-0.008
Jamie-0.007
 Pen-0.007
TokenJo
Token ID9908
Feature activation-1.06e+01

Pos logit contributions
rum+0.680
ud+0.574
and+0.549
Jo+0.529
Jamie+0.510
Neg logit contributions
-0.564
ory-0.513
 surely-0.467
 finally-0.451
ized-0.442
Token.
Token ID13
Feature activation-3.41e-01

Pos logit contributions
rum+1.054
and+0.946
ud+0.897
Jo+0.869
 Ali+0.841
Neg logit contributions
-0.842
 surely-0.696
ory-0.685
ized-0.662
 continued-0.652
Token Jo
Token ID5302
Feature activation-7.07e+00

Pos logit contributions
rum+0.036
ud+0.033
ggie+0.031
rd+0.031
e+0.030
Neg logit contributions
-0.025
 surely-0.018
 Dino-0.017
idents-0.017
 Ros-0.017
TokenJo
Token ID9908
Feature activation-1.06e+01

Pos logit contributions
rum+0.371
and+0.252
uzzle+0.251
ud+0.250
 liar+0.231
Neg logit contributions
-0.832
 surely-0.784
 still-0.772
 continued-0.769
 finally-0.769
Token was
Token ID373
Feature activation-8.11e-01

Pos logit contributions
rum+1.099
and+0.984
ud+0.928
uzzle+0.887
Jo+0.885
Neg logit contributions
-0.810
 surely-0.691
ized-0.686
 continued-0.648
ory-0.645
Token thrilled
Token ID20536
Feature activation-1.09e+00

Pos logit contributions
rum+0.094
Jo+0.086
ud+0.084
jo+0.082
and+0.080
Neg logit contributions
-0.055
 surely-0.051
 still-0.048
 cooler-0.046
 hotter-0.046
TokenHis
Token ID6653
Feature activation+3.63e-03

Pos logit contributions
+0.011
Sorry+0.010
 surely+0.010
 hotter+0.009
 still+0.009
Neg logit contributions
rum-0.013
 Pen-0.012
 Jacob-0.012
ud-0.012
 Mae-0.011
Token mom
Token ID1995
Feature activation+1.37e+00

Pos logit contributions
+0.000
idents+0.000
 hotter+0.000
 surely+0.000
ory+0.000
Neg logit contributions
Jo-0.000
rum-0.000
 Pen-0.000
 Ali-0.000
ud-0.000
Token looked
Token ID3114
Feature activation+7.44e-01

Pos logit contributions
+0.087
 sack+0.075
 hotter+0.070
ory+0.069
 surely+0.069
Neg logit contributions
rum-0.162
Jo-0.148
and-0.139
 Pen-0.136
ud-0.135
Token at
Token ID379
Feature activation-6.90e-02

Pos logit contributions
+0.065
idents+0.054
 hotter+0.051
 sack+0.051
 surely+0.051
Neg logit contributions
Jo-0.073
rum-0.070
 Pen-0.062
ud-0.062
and-0.062
Token Jo
Token ID5302
Feature activation-7.03e+00

Pos logit contributions
rum+0.008
and+0.008
Jo+0.007
rd+0.007
ud+0.007
Neg logit contributions
-0.003
 Dino-0.003
idents-0.003
 sack-0.003
 surely-0.003
TokenJo
Token ID9908
Feature activation-1.06e+01

Pos logit contributions
rum+0.721
Jo+0.691
ud+0.690
Jamie+0.639
and+0.638
Neg logit contributions
-0.451
idents-0.377
ory-0.371
 sack-0.370
 surely-0.361
Token and
Token ID290
Feature activation+2.52e-01

Pos logit contributions
rum+1.115
Jo+1.030
ud+1.017
and+0.984
Jamie+0.966
Neg logit contributions
-0.733
idents-0.625
 sack-0.620
ized-0.606
ory-0.598
Token said
Token ID531
Feature activation+6.26e-01

Pos logit contributions
+0.017
idents+0.014
 sack+0.013
 hotter+0.013
ory+0.013
Neg logit contributions
rum-0.029
Jo-0.029
ud-0.026
and-0.026
 Pen-0.025
Token "
Token ID366
Feature activation-9.13e-01

Pos logit contributions
+0.041
idents+0.034
 sack+0.032
 cooler+0.030
 surely+0.030
Neg logit contributions
Jo-0.072
rum-0.070
ud-0.069
and-0.064
jo-0.064
TokenDon
Token ID3987
Feature activation+1.91e+00

Pos logit contributions
rum+0.087
Jo+0.072
 Jacob+0.072
ud+0.071
 Pen+0.071
Neg logit contributions
-0.072
Sorry-0.070
 hotter-0.069
idents-0.065
 surely-0.064
Token't
Token ID470
Feature activation+1.73e+00

Pos logit contributions
+0.143
idents+0.114
 surely+0.110
 sack+0.106
 hotter+0.105
Neg logit contributions
Jo-0.207
rum-0.206
ud-0.186
and-0.183
 Pen-0.182
Token the
Token ID262
Feature activation+4.06e-01

Pos logit contributions
Jo+0.005
rum+0.004
ud+0.004
and+0.004
jo+0.004
Neg logit contributions
-0.004
 surely-0.003
 sack-0.003
 cooler-0.003
idents-0.003
Token same
Token ID976
Feature activation-8.83e-01

Pos logit contributions
+0.033
idents+0.028
 sack+0.027
 hotter+0.026
 cooler+0.026
Neg logit contributions
Jo-0.042
rum-0.042
ud-0.037
 Pen-0.036
and-0.036
Token time
Token ID640
Feature activation-1.03e+00

Pos logit contributions
rum+0.087
Jo+0.085
 Pen+0.078
ud+0.075
and+0.075
Neg logit contributions
-0.074
 sack-0.065
 cooler-0.064
 surely-0.060
idents-0.059
Token.
Token ID13
Feature activation-2.22e-01

Pos logit contributions
rum+0.110
Jo+0.108
 Pen+0.098
ud+0.095
 Ali+0.093
Neg logit contributions
-0.079
 surely-0.061
 cooler-0.061
idents-0.060
 sack-0.060
Token<|endoftext|>
Token ID50256
Feature activation-2.59e-01

Pos logit contributions
Jo+0.025
rum+0.024
ud+0.022
 Pen+0.022
and+0.022
Neg logit contributions
-0.016
idents-0.012
 Dino-0.011
 surely-0.011
 sack-0.011
TokenJo
Token ID9908
Feature activation-1.06e+01

Pos logit contributions
Jo+0.030
rum+0.030
ud+0.026
 Pen+0.026
and+0.026
Neg logit contributions
-0.018
idents-0.013
 sack-0.013
 hotter-0.013
ory-0.013
TokenJo
Token ID9908
Feature activation-1.06e+01

Pos logit contributions
rum+1.057
and+0.973
Jo+0.955
ud+0.900
 Pen+0.899
Neg logit contributions
-0.835
ory-0.737
 surely-0.686
 sack-0.667
idents-0.650
Token was
Token ID373
Feature activation-6.47e-01

Pos logit contributions
rum+1.072
and+0.984
Jo+0.970
 Pen+0.908
ud+0.907
Neg logit contributions
-0.833
ory-0.715
 surely-0.674
 sack-0.662
idents-0.641
Token a
Token ID257
Feature activation-2.88e-01

Pos logit contributions
rum+0.072
Jo+0.071
jo+0.063
and+0.062
ud+0.062
Neg logit contributions
-0.049
 surely-0.041
 hotter-0.041
 cooler-0.041
 prett-0.038
Token clever
Token ID14169
Feature activation+1.89e+00

Pos logit contributions
Jo+0.028
rum+0.027
ud+0.023
 Pen+0.023
and+0.023
Neg logit contributions
-0.026
idents-0.022
 sack-0.021
 hotter-0.021
 surely-0.020
Token little
Token ID1310
Feature activation-1.94e+00

Pos logit contributions
+0.140
 sack+0.122
ory+0.122
 cooler+0.118
 surely+0.109
Neg logit contributions
rum-0.213
Jo-0.200
and-0.188
ud-0.173
rd-0.171
Token same
Token ID976
Feature activation-8.83e-01

Pos logit contributions
+0.033
idents+0.028
 sack+0.027
 hotter+0.026
 cooler+0.026
Neg logit contributions
Jo-0.042
rum-0.042
ud-0.037
 Pen-0.036
and-0.036
Token time
Token ID640
Feature activation-1.03e+00

Pos logit contributions
rum+0.087
Jo+0.085
 Pen+0.078
ud+0.075
and+0.075
Neg logit contributions
-0.074
 sack-0.065
 cooler-0.064
 surely-0.060
idents-0.059
Token.
Token ID13
Feature activation-2.22e-01

Pos logit contributions
rum+0.110
Jo+0.108
 Pen+0.098
ud+0.095
 Ali+0.093
Neg logit contributions
-0.079
 surely-0.061
 cooler-0.061
idents-0.060
 sack-0.060
Token<|endoftext|>
Token ID50256
Feature activation-2.59e-01

Pos logit contributions
Jo+0.025
rum+0.024
ud+0.022
 Pen+0.022
and+0.022
Neg logit contributions
-0.016
idents-0.012
 Dino-0.011
 surely-0.011
 sack-0.011
TokenJo
Token ID9908
Feature activation-1.06e+01

Pos logit contributions
Jo+0.030
rum+0.030
ud+0.026
 Pen+0.026
and+0.026
Neg logit contributions
-0.018
idents-0.013
 sack-0.013
 hotter-0.013
ory-0.013
TokenJo
Token ID9908
Feature activation-1.06e+01

Pos logit contributions
rum+1.057
and+0.973
Jo+0.955
ud+0.900
 Pen+0.899
Neg logit contributions
-0.835
ory-0.737
 surely-0.686
 sack-0.667
idents-0.650
Token was
Token ID373
Feature activation-6.47e-01

Pos logit contributions
rum+1.072
and+0.984
Jo+0.970
 Pen+0.908
ud+0.907
Neg logit contributions
-0.833
ory-0.715
 surely-0.674
 sack-0.662
idents-0.641
Token a
Token ID257
Feature activation-2.88e-01

Pos logit contributions
rum+0.072
Jo+0.071
jo+0.063
and+0.062
ud+0.062
Neg logit contributions
-0.049
 surely-0.041
 hotter-0.041
 cooler-0.041
 prett-0.038
Token clever
Token ID14169
Feature activation+1.89e+00

Pos logit contributions
Jo+0.028
rum+0.027
ud+0.023
 Pen+0.023
and+0.023
Neg logit contributions
-0.026
idents-0.022
 sack-0.021
 hotter-0.021
 surely-0.020
Token little
Token ID1310
Feature activation-1.94e+00

Pos logit contributions
+0.140
 sack+0.122
ory+0.122
 cooler+0.118
 surely+0.109
Neg logit contributions
rum-0.213
Jo-0.200
and-0.188
ud-0.173
rd-0.171
Token boy
Token ID2933
Feature activation-6.18e-03

Pos logit contributions
rum+0.226
Jo+0.223
and+0.196
ud+0.194
Jamie+0.191
Neg logit contributions
-0.137
 sack-0.111
idents-0.109
ory-0.109
 cooler-0.109
Tokenâ
Token ID22940
Feature activation-2.38e+00

Pos logit contributions
Jo+0.033
rum+0.032
ud+0.029
and+0.028
jo+0.027
Neg logit contributions
-0.027
idents-0.021
 Dino-0.020
 surely-0.019
 sack-0.019
Token
Token ID26391
Feature activation+1.54e+00

Pos logit contributions
Jo+0.234
rum+0.219
jo+0.194
 Pen+0.190
 Ali+0.186
Neg logit contributions
-0.215
idents-0.183
 sack-0.179
ory-0.177
 hotter-0.177
Token
Token ID220
Feature activation-1.44e+00

Pos logit contributions
+0.136
idents+0.104
 Dino+0.091
 sack+0.088
+0.088
Neg logit contributions
rum-0.160
Jo-0.149
and-0.142
ud-0.139
 Pen-0.136
Token
Token ID198
Feature activation+1.45e-01

Pos logit contributions
Jo+0.147
rum+0.145
ud+0.127
 Pen+0.125
jo+0.123
Neg logit contributions
-0.119
idents-0.094
 hotter-0.089
 Dino-0.089
 surely-0.088
Token
Token ID198
Feature activation+7.44e-02

Pos logit contributions
+0.011
 Dino+0.008
Sorry+0.007
ory+0.007
 surely+0.007
Neg logit contributions
rum-0.016
Jo-0.015
ud-0.014
 Pen-0.014
 Jacob-0.014
TokenJo
Token ID9908
Feature activation-1.06e+01

Pos logit contributions
+0.006
Sorry+0.004
 surely+0.004
 Dino+0.004
Ros+0.004
Neg logit contributions
rum-0.008
Jo-0.007
ud-0.007
 Jacob-0.007
 Pen-0.007
Token hopped
Token ID45230
Feature activation-8.82e-01

Pos logit contributions
rum+0.816
and+0.727
ud+0.666
uzzle+0.649
Jo+0.642
Neg logit contributions
-1.000
 surely-0.948
ory-0.890
ized-0.882
idents-0.870
Token on
Token ID319
Feature activation+5.54e-01

Pos logit contributions
Jo+0.091
rum+0.087
 Pen+0.079
and+0.078
 Ali+0.077
Neg logit contributions
-0.073
idents-0.062
 hotter-0.057
 sack-0.057
ory-0.056
Token the
Token ID262
Feature activation+2.58e-01

Pos logit contributions
+0.044
 sack+0.036
 cooler+0.036
idents+0.035
 surely+0.034
Neg logit contributions
rum-0.058
Jo-0.055
ud-0.051
jo-0.050
and-0.049
Token bike
Token ID7161
Feature activation-8.07e-02

Pos logit contributions
+0.022
 sack+0.019
idents+0.018
 cooler+0.018
 hotter+0.018
Neg logit contributions
rum-0.026
Jo-0.025
ud-0.023
and-0.022
 Pen-0.022
Token and
Token ID290
Feature activation+7.66e-02

Pos logit contributions
rum+0.009
Jo+0.009
ud+0.008
Jamie+0.008
 Pen+0.007
Neg logit contributions
-0.006
 sack-0.005
 surely-0.005
 cooler-0.005
idents-0.005
Token Jo
Token ID5302
Feature activation-7.00e+00

Pos logit contributions
rum+0.334
ud+0.310
and+0.288
Jo+0.283
rd+0.269
Neg logit contributions
-0.202
idents-0.179
 sack-0.170
 cooler-0.165
 Dino-0.162
Token shouted
Token ID17293
Feature activation-2.70e+00

Pos logit contributions
rum+0.537
ud+0.498
 lions+0.468
 living+0.439
and+0.431
Neg logit contributions
-0.581
 finally-0.555
 surely-0.540
ory-0.538
 continued-0.531
Token.
Token ID13
Feature activation-1.76e-01

Pos logit contributions
Jo+0.257
rum+0.247
ud+0.224
 Pen+0.215
and+0.215
Neg logit contributions
-0.239
idents-0.203
 sack-0.194
 surely-0.193
 hotter-0.193
Token
Token ID198
Feature activation+1.42e-01

Pos logit contributions
rum+0.021
ud+0.019
rd+0.017
Jo+0.017
old+0.017
Neg logit contributions
-0.012
idents-0.009
 sack-0.008
 surely-0.008
 Dino-0.008
Token
Token ID198
Feature activation+1.29e-01

Pos logit contributions
+0.007
Sorry+0.005
 Dino+0.005
Ros+0.004
 surely+0.004
Neg logit contributions
rum-0.018
ud-0.016
rd-0.015
abel-0.015
 ounces-0.015
TokenJo
Token ID9908
Feature activation-1.06e+01

Pos logit contributions
+0.010
Sorry+0.010
 surely+0.008
Ros+0.008
There+0.008
Neg logit contributions
rum-0.012
ud-0.011
 supposed-0.010
eer-0.010
 Jacob-0.009
Token opened
Token ID4721
Feature activation+2.00e+00

Pos logit contributions
rum+1.128
Jo+1.015
and+0.990
ud+0.975
 Pen+0.939
Neg logit contributions
-0.785
 surely-0.645
ory-0.642
 sack-0.641
idents-0.629
Token the
Token ID262
Feature activation+4.47e-01

Pos logit contributions
+0.149
idents+0.124
 sack+0.123
 surely+0.120
 hotter+0.119
Neg logit contributions
Jo-0.210
rum-0.208
and-0.192
ud-0.190
jo-0.182
Token book
Token ID1492
Feature activation-8.20e-01

Pos logit contributions
+0.050
idents+0.044
 sack+0.043
 surely+0.042
 hotter+0.042
Neg logit contributions
Jo-0.033
rum-0.031
ud-0.027
 Pen-0.026
and-0.026
Token and
Token ID290
Feature activation+2.44e-01

Pos logit contributions
Jo+0.078
rum+0.077
ud+0.067
 Pen+0.066
and+0.065
Neg logit contributions
-0.075
idents-0.062
 sack-0.061
 surely-0.060
 hotter-0.058
Token saw
Token ID2497
Feature activation-2.57e-01

Pos logit contributions
+0.021
idents+0.017
 sack+0.017
 hotter+0.016
 surely+0.016
Neg logit contributions
Jo-0.024
rum-0.024
ud-0.021
 Pen-0.021
and-0.021
Token thing
Token ID1517
Feature activation-3.91e-01

Pos logit contributions
 sack+0.168
 cooler+0.150
 gem+0.144
idents+0.134
+0.133
Neg logit contributions
Jo-0.262
Jamie-0.248
ud-0.247
and-0.237
rum-0.237
Token to
Token ID284
Feature activation-8.11e-01

Pos logit contributions
Jo+0.043
rum+0.041
ud+0.038
Jamie+0.038
 Pen+0.036
Neg logit contributions
-0.027
 sack-0.023
idents-0.023
 Dino-0.022
 surely-0.022
Token do
Token ID466
Feature activation+1.10e-01

Pos logit contributions
Jo+0.082
rum+0.079
ud+0.073
 Pen+0.071
and+0.071
Neg logit contributions
-0.068
idents-0.057
 sack-0.056
 surely-0.053
ory-0.053
Token.
Token ID13
Feature activation-2.09e-01

Pos logit contributions
+0.009
idents+0.008
 sack+0.008
 surely+0.008
 hotter+0.007
Neg logit contributions
Jo-0.011
rum-0.010
 Pen-0.009
ud-0.009
 Ali-0.009
Token<|endoftext|>
Token ID50256
Feature activation-3.30e-01

Pos logit contributions
Jo+0.025
rum+0.024
ud+0.023
 Pen+0.022
isa+0.021
Neg logit contributions
-0.013
idents-0.010
 Dino-0.009
 surely-0.009
 sack-0.008
TokenJo
Token ID9908
Feature activation-1.06e+01

Pos logit contributions
Jo+0.037
rum+0.036
 Pen+0.032
ud+0.032
 Ali+0.032
Neg logit contributions
-0.024
idents-0.019
 sack-0.018
 hotter-0.018
ory-0.018
Tokenel
Token ID417
Feature activation+1.52e+00

Pos logit contributions
rum+1.010
Jo+0.960
and+0.925
 Pen+0.884
ud+0.878
Neg logit contributions
-0.861
ory-0.747
 surely-0.709
 sack-0.703
idents-0.700
Token saw
Token ID2497
Feature activation-3.21e-01

Pos logit contributions
+0.112
 sack+0.101
ory+0.099
 Dino+0.099
idents+0.097
Neg logit contributions
rum-0.154
Jo-0.151
and-0.138
 Pen-0.134
ud-0.130
Token a
Token ID257
Feature activation-3.45e-01

Pos logit contributions
rum+0.036
Jo+0.035
ud+0.032
and+0.032
jo+0.031
Neg logit contributions
-0.022
 sack-0.020
 cooler-0.019
 Dino-0.019
 hotter-0.019
Token banana
Token ID25996
Feature activation-1.94e+00

Pos logit contributions
Jo+0.031
rum+0.028
 Pen+0.027
 Ali+0.026
 Jacob+0.026
Neg logit contributions
-0.032
idents-0.027
 surely-0.026
 hotter-0.025
ory-0.025
Token in
Token ID287
Feature activation-3.29e-02

Pos logit contributions
Jo+0.179
rum+0.172
 Pen+0.151
ud+0.150
and+0.149
Neg logit contributions
-0.181
idents-0.154
 hotter-0.147
 sack-0.146
 surely-0.145
Token't
Token ID470
Feature activation+1.78e+00

Pos logit contributions
+0.211
idents+0.192
ory+0.191
 sack+0.182
 hotter+0.181
Neg logit contributions
Jo-0.217
rum-0.207
 Pen-0.187
 Ali-0.181
ud-0.181
Token bud
Token ID3600
Feature activation+1.11e+00

Pos logit contributions
+0.152
idents+0.124
ory+0.119
 hotter+0.117
 Dino+0.113
Neg logit contributions
Jo-0.182
rum-0.179
 Pen-0.157
 Ali-0.155
and-0.153
Tokenge
Token ID469
Feature activation-1.46e+00

Pos logit contributions
+0.090
idents+0.075
ory+0.073
 hotter+0.073
 sack+0.072
Neg logit contributions
Jo-0.113
rum-0.107
 Pen-0.100
 Jacob-0.098
 Ali-0.097
Token!
Token ID0
Feature activation+2.06e-01

Pos logit contributions
Jo+0.169
rum+0.154
Jamie+0.146
 Pen+0.144
ud+0.143
Neg logit contributions
-0.094
 sack-0.081
idents-0.079
 cooler-0.075
 surely-0.074
Token Jo
Token ID5302
Feature activation-7.05e+00

Pos logit contributions
+0.018
idents+0.015
 surely+0.013
 sack+0.013
 hotter+0.013
Neg logit contributions
rum-0.021
Jo-0.018
ud-0.017
and-0.016
 Jacob-0.016
TokenJo
Token ID9908
Feature activation-1.06e+01

Pos logit contributions
rum+0.438
uzzle+0.334
and+0.334
 lions+0.317
weet+0.312
Neg logit contributions
-0.761
 still-0.690
ized-0.690
 surely-0.686
 finally-0.682
Token was
Token ID373
Feature activation-7.38e-01

Pos logit contributions
rum+1.165
and+1.050
Jo+1.044
 Pen+0.973
 Jacob+0.968
Neg logit contributions
-0.764
 surely-0.601
idents-0.595
ized-0.593
ory-0.588
Token getting
Token ID1972
Feature activation-6.02e-01

Pos logit contributions
Jo+0.085
rum+0.084
jo+0.076
ud+0.075
and+0.074
Neg logit contributions
-0.051
 surely-0.042
 hotter-0.041
 cooler-0.040
 sack-0.039
Token frustrated
Token ID14718
Feature activation+4.07e+00

Pos logit contributions
Jo+0.040
and+0.039
old+0.038
 Pen+0.038
rum+0.037
Neg logit contributions
-0.065
idents-0.058
actus-0.051
ory-0.051
ols-0.050
Token.
Token ID13
Feature activation-2.10e-01

Pos logit contributions
+0.334
idents+0.274
 hotter+0.264
 sack+0.263
 cooler+0.260
Neg logit contributions
Jo-0.413
rum-0.406
 Pen-0.364
 Ali-0.353
Jamie-0.349
Token She
Token ID1375
Feature activation-6.00e-01

Pos logit contributions
rum+0.024
Jo+0.021
ud+0.021
e+0.020
and+0.019
Neg logit contributions
-0.015
idents-0.011
 surely-0.010
 hotter-0.010
 sack-0.010
Token very
Token ID845
Feature activation+9.56e-01

Pos logit contributions
Jo+0.328
rum+0.328
ud+0.304
jo+0.301
 Ali+0.281
Neg logit contributions
-0.245
 cooler-0.210
 hotter-0.210
 surely-0.208
 sack-0.203
Token reliable
Token ID9314
Feature activation+1.69e+00

Pos logit contributions
+0.083
idents+0.069
 surely+0.068
ory+0.067
 hotter+0.067
Neg logit contributions
Jo-0.094
rum-0.090
ud-0.081
 Pen-0.079
 Ali-0.079
Token."
Token ID526
Feature activation-2.37e+00

Pos logit contributions
+0.127
 sack+0.112
ory+0.111
 cooler+0.108
idents+0.107
Neg logit contributions
Jo-0.181
rum-0.162
jo-0.153
 Ali-0.153
Jamie-0.151
Token<|endoftext|>
Token ID50256
Feature activation-3.90e-01

Pos logit contributions
Jo+0.237
rum+0.230
ud+0.203
 Pen+0.201
and+0.198
Neg logit contributions
-0.211
idents-0.172
 sack-0.161
 Dino-0.159
ory-0.158
TokenJo
Token ID9908
Feature activation-1.06e+01

Pos logit contributions
Jo+0.046
rum+0.045
 Pen+0.040
ud+0.040
and+0.040
Neg logit contributions
-0.027
idents-0.020
 sack-0.019
 hotter-0.019
ory-0.019
TokenJo
Token ID9908
Feature activation-1.06e+01

Pos logit contributions
rum+1.062
Jo+0.988
and+0.987
ud+0.919
 Pen+0.904
Neg logit contributions
-0.824
ory-0.711
 surely-0.672
 sack-0.657
idents-0.652
Token was
Token ID373
Feature activation-7.72e-01

Pos logit contributions
rum+1.062
Jo+0.985
and+0.984
ud+0.915
 Pen+0.905
Neg logit contributions
-0.830
ory-0.704
 surely-0.673
 sack-0.660
idents-0.654
Token playing
Token ID2712
Feature activation-2.52e+00

Pos logit contributions
rum+0.084
Jo+0.082
ud+0.072
jo+0.071
and+0.071
Neg logit contributions
-0.061
 surely-0.051
 cooler-0.050
 hotter-0.050
 prett-0.048
Token in
Token ID287
Feature activation-1.02e-01

Pos logit contributions
Jo+0.270
rum+0.266
jo+0.238
ud+0.235
 Pen+0.228
Neg logit contributions
-0.203
 sack-0.168
idents-0.159
 cooler-0.158
 surely-0.155
Token the
Token ID262
Feature activation+4.17e-01

Pos logit contributions
rum+0.014
Jo+0.013
ud+0.013
jo+0.012
and+0.012
Neg logit contributions
-0.005
 sack-0.004
 cooler-0.004
 golf-0.004
 surely-0.003
Token park
Token ID3952
Feature activation-2.70e-01

Pos logit contributions
+0.030
 sack+0.027
 cooler+0.026
 hotter+0.025
idents+0.024
Neg logit contributions
rum-0.047
Jo-0.045
ud-0.040
jo-0.040
and-0.039
Token been
Token ID587
Feature activation-3.20e+00

Pos logit contributions
+0.078
 surely+0.068
 sack+0.067
idents+0.065
 cooler+0.063
Neg logit contributions
rum-0.077
Jo-0.074
ud-0.068
and-0.066
 Ali-0.066
Token very
Token ID845
Feature activation+9.56e-01

Pos logit contributions
Jo+0.328
rum+0.328
ud+0.304
jo+0.301
 Ali+0.281
Neg logit contributions
-0.245
 cooler-0.210
 hotter-0.210
 surely-0.208
 sack-0.203
Token reliable
Token ID9314
Feature activation+1.69e+00

Pos logit contributions
+0.083
idents+0.069
 surely+0.068
ory+0.067
 hotter+0.067
Neg logit contributions
Jo-0.094
rum-0.090
ud-0.081
 Pen-0.079
 Ali-0.079
Token."
Token ID526
Feature activation-2.37e+00

Pos logit contributions
+0.127
 sack+0.112
ory+0.111
 cooler+0.108
idents+0.107
Neg logit contributions
Jo-0.181
rum-0.162
jo-0.153
 Ali-0.153
Jamie-0.151
Token<|endoftext|>
Token ID50256
Feature activation-3.90e-01

Pos logit contributions
Jo+0.237
rum+0.230
ud+0.203
 Pen+0.201
and+0.198
Neg logit contributions
-0.211
idents-0.172
 sack-0.161
 Dino-0.159
ory-0.158
TokenJo
Token ID9908
Feature activation-1.06e+01

Pos logit contributions
Jo+0.046
rum+0.045
 Pen+0.040
ud+0.040
and+0.040
Neg logit contributions
-0.027
idents-0.020
 sack-0.019
 hotter-0.019
ory-0.019
TokenJo
Token ID9908
Feature activation-1.06e+01

Pos logit contributions
rum+1.062
Jo+0.988
and+0.987
ud+0.919
 Pen+0.904
Neg logit contributions
-0.824
ory-0.711
 surely-0.672
 sack-0.657
idents-0.652
Token was
Token ID373
Feature activation-7.72e-01

Pos logit contributions
rum+1.062
Jo+0.985
and+0.984
ud+0.915
 Pen+0.905
Neg logit contributions
-0.830
ory-0.704
 surely-0.673
 sack-0.660
idents-0.654
Token playing
Token ID2712
Feature activation-2.52e+00

Pos logit contributions
rum+0.084
Jo+0.082
ud+0.072
jo+0.071
and+0.071
Neg logit contributions
-0.061
 surely-0.051
 cooler-0.050
 hotter-0.050
 prett-0.048
Token in
Token ID287
Feature activation-1.02e-01

Pos logit contributions
Jo+0.270
rum+0.266
jo+0.238
ud+0.235
 Pen+0.228
Neg logit contributions
-0.203
 sack-0.168
idents-0.159
 cooler-0.158
 surely-0.155
Token the
Token ID262
Feature activation+4.17e-01

Pos logit contributions
rum+0.014
Jo+0.013
ud+0.013
jo+0.012
and+0.012
Neg logit contributions
-0.005
 sack-0.004
 cooler-0.004
 golf-0.004
 surely-0.003
Token said
Token ID531
Feature activation+4.84e-01

Pos logit contributions
+0.066
 sack+0.053
idents+0.053
ory+0.052
 surely+0.051
Neg logit contributions
Jo-0.106
rum-0.105
ud-0.094
and-0.093
 Pen-0.092
Token together
Token ID1978
Feature activation-2.52e-01

Pos logit contributions
+0.037
 surely+0.030
idents+0.028
 sack+0.028
 hotter+0.027
Neg logit contributions
Jo-0.051
rum-0.051
ud-0.049
jo-0.045
and-0.044
Token.
Token ID13
Feature activation-3.60e-01

Pos logit contributions
rum+0.027
Jo+0.026
ud+0.024
 Pen+0.023
jo+0.023
Neg logit contributions
-0.019
 surely-0.016
 sack-0.015
idents-0.015
 cooler-0.015
Token
Token ID198
Feature activation-6.93e-02

Pos logit contributions
rum+0.037
Jo+0.033
ud+0.032
and+0.030
rd+0.030
Neg logit contributions
-0.031
 surely-0.022
idents-0.022
 Dino-0.021
ols-0.020
Token
Token ID198
Feature activation-6.42e-02

Pos logit contributions
rum+0.008
ud+0.007
 clim+0.007
Jo+0.007
 Pen+0.007
Neg logit contributions
-0.005
 surely-0.003
Sorry-0.003
 Dino-0.003
Ros-0.003
TokenJo
Token ID9908
Feature activation-1.06e+01

Pos logit contributions
rum+0.006
ud+0.005
 Pen+0.005
jo+0.005
eer+0.005
Neg logit contributions
-0.005
Sorry-0.004
 surely-0.004
Ros-0.004
 Dino-0.004
Token smiled
Token ID13541
Feature activation-1.62e-01

Pos logit contributions
rum+1.074
Jo+0.985
and+0.948
ud+0.934
 Pen+0.930
Neg logit contributions
-0.825
ory-0.696
 surely-0.693
idents-0.678
ized-0.647
Token and
Token ID290
Feature activation+2.83e-02

Pos logit contributions
Jo+0.014
rum+0.013
 Pen+0.012
 Ali+0.011
 Jacob+0.011
Neg logit contributions
-0.016
idents-0.014
 hotter-0.013
 sack-0.013
 surely-0.013
Token took
Token ID1718
Feature activation-4.11e-01

Pos logit contributions
+0.002
idents+0.002
 surely+0.002
 sack+0.002
ory+0.002
Neg logit contributions
rum-0.003
Jo-0.003
ud-0.003
and-0.003
 Pen-0.003
Token them
Token ID606
Feature activation+5.09e-01

Pos logit contributions
rum+0.044
Jo+0.042
ud+0.038
and+0.037
 Pen+0.036
Neg logit contributions
-0.031
 surely-0.026
 sack-0.026
 Dino-0.025
ory-0.025
Token to
Token ID284
Feature activation-8.32e-01

Pos logit contributions
+0.037
idents+0.030
 sack+0.029
 surely+0.028
ory+0.028
Neg logit contributions
Jo-0.057
rum-0.056
ud-0.050
 Pen-0.049
 Ali-0.048
Token her
Token ID607
Feature activation-5.02e-01

Pos logit contributions
+0.039
idents+0.034
 sack+0.032
 surely+0.031
ory+0.031
Neg logit contributions
rum-0.055
Jo-0.055
ud-0.049
 Pen-0.047
and-0.047
Token teacher
Token ID4701
Feature activation+1.57e+00

Pos logit contributions
Jo+0.045
rum+0.039
 Ali+0.039
 Pen+0.038
 Jacob+0.038
Neg logit contributions
-0.046
 hotter-0.042
idents-0.039
 surely-0.039
ory-0.038
Token gave
Token ID2921
Feature activation+2.22e+00

Pos logit contributions
+0.104
 sack+0.087
ory+0.087
idents+0.080
 cooler+0.077
Neg logit contributions
rum-0.190
Jo-0.169
ud-0.161
and-0.151
 Pen-0.151
Token her
Token ID607
Feature activation-5.01e-01

Pos logit contributions
+0.213
idents+0.184
 sack+0.177
 hotter+0.175
ory+0.175
Neg logit contributions
Jo-0.198
rum-0.192
ud-0.165
 Pen-0.164
 Ali-0.162
Token a
Token ID257
Feature activation-1.26e-01

Pos logit contributions
Jo+0.042
rum+0.040
 Pen+0.035
and+0.035
 Ali+0.035
Neg logit contributions
-0.051
idents-0.043
 hotter-0.042
 surely-0.041
ory-0.041
Token folder
Token ID9483
Feature activation+5.57e+00

Pos logit contributions
Jo+0.012
rum+0.012
 Pen+0.011
and+0.010
 Jacob+0.010
Neg logit contributions
-0.011
idents-0.009
 hotter-0.009
 surely-0.008
ory-0.008
Token to
Token ID284
Feature activation-6.03e-01

Pos logit contributions
+0.555
idents+0.478
 hotter+0.459
 sack+0.454
 surely+0.452
Neg logit contributions
Jo-0.473
rum-0.455
 Pen-0.394
ud-0.392
and-0.391
Token keep
Token ID1394
Feature activation+2.33e-01

Pos logit contributions
Jo+0.051
rum+0.047
 Ann+0.044
 Pen+0.044
 Ali+0.043
Neg logit contributions
-0.058
 hotter-0.052
idents-0.051
oming-0.046
ory-0.046
Token her
Token ID607
Feature activation-4.89e-01

Pos logit contributions
+0.024
idents+0.020
 hotter+0.019
ory+0.019
 surely+0.019
Neg logit contributions
Jo-0.020
rum-0.019
 Pen-0.017
and-0.016
 Ali-0.016
Token papers
Token ID9473
Feature activation+3.26e+00

Pos logit contributions
Jo+0.044
rum+0.043
and+0.040
 Pen+0.040
 Ali+0.038
Neg logit contributions
-0.044
 hotter-0.036
 Dino-0.035
Sorry-0.035
idents-0.035
Token in
Token ID287
Feature activation+1.33e-01

Pos logit contributions
+0.370
idents+0.323
 hotter+0.314
Sorry+0.309
 Dino+0.308
Neg logit contributions
Jo-0.216
rum-0.213
and-0.203
 Pen-0.173
jo-0.169
Token Lily
Token ID20037
Feature activation+1.36e+00

Pos logit contributions
Jo+0.266
rum+0.254
 Pen+0.221
ud+0.220
and+0.218
Neg logit contributions
-0.265
idents-0.223
 sack-0.216
 hotter-0.215
ory-0.214
Token and
Token ID290
Feature activation+5.21e-01

Pos logit contributions
+0.125
 sack+0.115
idents+0.114
 cooler+0.110
ory+0.106
Neg logit contributions
Jo-0.122
rum-0.109
ud-0.099
Jamie-0.098
 Pen-0.097
Token Tom
Token ID4186
Feature activation-1.31e+00

Pos logit contributions
+0.054
idents+0.047
 hotter+0.045
 surely+0.045
ory+0.045
Neg logit contributions
Jo-0.042
rum-0.040
 Pen-0.036
 Ali-0.035
 Jacob-0.035
Token and
Token ID290
Feature activation+5.31e-01

Pos logit contributions
Jo+0.132
rum+0.118
ud+0.110
Jamie+0.108
jo+0.108
Neg logit contributions
-0.108
 sack-0.096
idents-0.096
 cooler-0.094
 hotter-0.091
Token w
Token ID266
Feature activation+1.63e+00

Pos logit contributions
+0.052
idents+0.045
 hotter+0.043
 sack+0.043
ory+0.042
Neg logit contributions
Jo-0.046
rum-0.045
 Pen-0.039
ud-0.038
 Ali-0.038
Tokenags
Token ID3775
Feature activation+4.36e+00

Pos logit contributions
+0.091
idents+0.068
 sack+0.062
ory+0.061
 hotter+0.060
Neg logit contributions
Jo-0.213
rum-0.204
 Pen-0.189
 Ali-0.187
ud-0.185
Token his
Token ID465
Feature activation-1.11e+00

Pos logit contributions
+0.319
 Dino+0.274
idents+0.271
 cooler+0.263
 sack+0.260
Neg logit contributions
Jo-0.454
rum-0.423
ud-0.408
 Pen-0.391
and-0.386
Token tail
Token ID7894
Feature activation-2.95e+00

Pos logit contributions
Jo+0.070
rum+0.068
 Pen+0.056
 Ali+0.054
ud+0.054
Neg logit contributions
-0.135
idents-0.119
 hotter-0.115
 surely-0.115
ory-0.114
Token.
Token ID13
Feature activation+2.85e-01

Pos logit contributions
Jo+0.340
rum+0.311
Jamie+0.286
 Ali+0.285
 Jamie+0.284
Neg logit contributions
-0.215
 cooler-0.177
 sack-0.174
idents-0.164
 surely-0.163
Token He
Token ID679
Feature activation+4.94e-01

Pos logit contributions
+0.023
idents+0.019
 hotter+0.018
 sack+0.018
 surely+0.018
Neg logit contributions
Jo-0.030
rum-0.029
 Pen-0.026
ud-0.026
and-0.026
Token forg
Token ID5784
Feature activation+3.56e+00

Pos logit contributions
+0.052
idents+0.046
 sack+0.044
 hotter+0.044
ory+0.043
Neg logit contributions
Jo-0.039
rum-0.037
ud-0.032
and-0.032
 Pen-0.032
Token help
Token ID1037
Feature activation+1.16e+00

Pos logit contributions
+0.054
idents+0.042
 sack+0.042
 hotter+0.041
 surely+0.041
Neg logit contributions
Jo-0.096
rum-0.091
ud-0.085
jo-0.085
 Pen-0.082
Token.
Token ID13
Feature activation+8.17e-02

Pos logit contributions
+0.077
 sack+0.068
 Dino+0.065
 hotter+0.064
idents+0.063
Neg logit contributions
Jo-0.133
rum-0.123
ud-0.114
jo-0.113
 Pen-0.112
Token
Token ID198
Feature activation+4.32e-01

Pos logit contributions
+0.008
idents+0.006
 hotter+0.006
 sack+0.006
 surely+0.006
Neg logit contributions
Jo-0.008
rum-0.007
 Pen-0.006
and-0.006
 Ali-0.006
Token
Token ID198
Feature activation+4.08e-01

Pos logit contributions
+0.037
idents+0.030
 sack+0.029
 hotter+0.029
 Dino+0.029
Neg logit contributions
Jo-0.043
rum-0.042
 Pen-0.037
ud-0.037
 Ali-0.036
TokenThe
Token ID464
Feature activation+3.88e-01

Pos logit contributions
+0.039
idents+0.035
ory+0.033
 hotter+0.032
 sack+0.032
Neg logit contributions
Jo-0.038
rum-0.036
and-0.032
ud-0.031
 Ali-0.030
Token moral
Token ID6573
Feature activation+5.08e+00

Pos logit contributions
+0.031
idents+0.028
ory+0.028
 hotter+0.026
ized+0.026
Neg logit contributions
Jo-0.036
rum-0.034
 living-0.033
 Pen-0.033
 Jacob-0.031
Token of
Token ID286
Feature activation-2.93e+00

Pos logit contributions
+0.537
 sack+0.481
 surely+0.473
 cooler+0.466
 Dino+0.464
Neg logit contributions
Jo-0.372
rum-0.369
 Pen-0.314
 Jacob-0.307
 Ali-0.303
Token the
Token ID262
Feature activation+4.86e-01

Pos logit contributions
Jo+0.315
rum+0.304
ud+0.275
jo+0.267
 Pen+0.267
Neg logit contributions
-0.222
idents-0.179
 sack-0.176
 surely-0.176
 Dino-0.174
Token story
Token ID1621
Feature activation+6.73e-01

Pos logit contributions
+0.057
idents+0.050
 hotter+0.049
ory+0.049
 surely+0.048
Neg logit contributions
Jo-0.033
rum-0.030
 Pen-0.026
and-0.025
ud-0.025
Token is
Token ID318
Feature activation-1.18e+00

Pos logit contributions
+0.068
idents+0.062
 surely+0.058
 sack+0.057
 hotter+0.055
Neg logit contributions
Jo-0.057
rum-0.051
 Pen-0.046
 Ali-0.044
ud-0.044
Token always
Token ID1464
Feature activation-3.21e+00

Pos logit contributions
Jo+0.094
rum+0.092
ud+0.078
 Pen+0.078
 Ali+0.078
Neg logit contributions
-0.124
idents-0.106
 hotter-0.104
 sack-0.102
ory-0.102
Token and
Token ID290
Feature activation+5.24e-01

Pos logit contributions
+0.047
idents+0.039
 sack+0.038
 hotter+0.038
 cooler+0.037
Neg logit contributions
Jo-0.058
rum-0.056
ud-0.050
jo-0.049
 Pen-0.049
Token drink
Token ID4144
Feature activation+1.56e+00

Pos logit contributions
+0.036
 sack+0.030
idents+0.029
 cooler+0.029
 surely+0.028
Neg logit contributions
Jo-0.060
rum-0.060
ud-0.057
and-0.053
jo-0.053
Token something
Token ID1223
Feature activation+1.77e+00

Pos logit contributions
+0.135
idents+0.112
 surely+0.106
ory+0.104
 sack+0.103
Neg logit contributions
Jo-0.151
rum-0.147
 Pen-0.134
and-0.131
 Jacob-0.130
Token good
Token ID922
Feature activation-5.92e-01

Pos logit contributions
+0.139
idents+0.116
 hotter+0.111
 sack+0.111
 cooler+0.109
Neg logit contributions
Jo-0.190
rum-0.184
ud-0.165
jo-0.162
 Ali-0.162
Token.
Token ID13
Feature activation+1.63e-01

Pos logit contributions
Jo+0.055
rum+0.053
ud+0.046
 Pen+0.046
 Ali+0.045
Neg logit contributions
-0.055
idents-0.047
 sack-0.045
 hotter-0.045
ory-0.044
Token A
Token ID317
Feature activation+4.52e+00

Pos logit contributions
+0.013
idents+0.009
 cooler+0.009
ory+0.008
 Dino+0.008
Neg logit contributions
rum-0.020
Jo-0.018
ud-0.016
jo-0.016
and-0.016
Token nice
Token ID3621
Feature activation-1.02e+00

Pos logit contributions
+0.353
 sack+0.308
 cooler+0.298
 hotter+0.279
ory+0.278
Neg logit contributions
rum-0.505
Jo-0.470
ud-0.426
and-0.416
jo-0.407
Token lady
Token ID10846
Feature activation+1.31e+00

Pos logit contributions
rum+0.124
Jo+0.117
ud+0.107
and+0.107
jo+0.102
Neg logit contributions
-0.069
 sack-0.064
 cooler-0.059
ory-0.055
idents-0.053
Token came
Token ID1625
Feature activation+1.10e+00

Pos logit contributions
+0.096
 sack+0.080
ory+0.079
 cooler+0.077
 surely+0.076
Neg logit contributions
rum-0.145
Jo-0.136
ud-0.126
and-0.122
Jamie-0.116
Token and
Token ID290
Feature activation+5.02e-01

Pos logit contributions
+0.077
 hotter+0.067
 sack+0.066
ory+0.066
idents+0.065
Neg logit contributions
rum-0.117
Jo-0.115
ud-0.100
 Jacob-0.099
rd-0.097
Token gave
Token ID2921
Feature activation+2.30e+00

Pos logit contributions
+0.036
idents+0.029
 hotter+0.028
 sack+0.028
 surely+0.027
Neg logit contributions
rum-0.057
Jo-0.056
ud-0.050
and-0.050
jo-0.048
Token,
Token ID11
Feature activation-2.34e-01

Pos logit contributions
rum+0.151
Jo+0.148
and+0.135
ud+0.133
jo+0.133
Neg logit contributions
-0.119
 sack-0.094
 Dino-0.093
ory-0.092
 cooler-0.092
Token she
Token ID673
Feature activation+1.71e-01

Pos logit contributions
Jo+0.022
rum+0.022
ud+0.019
and+0.019
jo+0.018
Neg logit contributions
-0.021
idents-0.018
 sack-0.017
 hotter-0.017
ory-0.017
Token joined
Token ID5399
Feature activation+5.64e-01

Pos logit contributions
+0.012
 sack+0.010
ory+0.010
 cooler+0.009
idents+0.009
Neg logit contributions
rum-0.020
Jo-0.019
and-0.017
 Pen-0.017
ud-0.016
Token a
Token ID257
Feature activation-3.00e-01

Pos logit contributions
+0.039
 sack+0.034
ory+0.033
 cooler+0.031
 Dino+0.031
Neg logit contributions
Jo-0.062
rum-0.062
jo-0.054
ud-0.054
and-0.052
Token special
Token ID2041
Feature activation+1.03e+00

Pos logit contributions
rum+0.030
Jo+0.030
ud+0.027
 Pen+0.026
and+0.025
Neg logit contributions
-0.025
idents-0.021
 sack-0.021
ory-0.020
 surely-0.020
Token club
Token ID3430
Feature activation+5.11e+00

Pos logit contributions
+0.085
 sack+0.074
 cooler+0.069
idents+0.067
ory+0.067
Neg logit contributions
rum-0.108
Jo-0.104
ud-0.098
and-0.093
Jamie-0.091
Token.
Token ID13
Feature activation-1.59e-01

Pos logit contributions
+0.399
 sack+0.350
 cooler+0.323
 surely+0.311
 golf+0.308
Neg logit contributions
rum-0.547
Jo-0.537
ud-0.474
 Pen-0.463
Jamie-0.461
Token They
Token ID1119
Feature activation-1.05e-01

Pos logit contributions
rum+0.018
Jo+0.017
ud+0.015
jo+0.015
rd+0.014
Neg logit contributions
-0.013
 sack-0.009
idents-0.009
 surely-0.009
 Dino-0.009
Token were
Token ID547
Feature activation-2.86e-01

Pos logit contributions
Jo+0.011
rum+0.011
ud+0.009
and+0.009
 Pen+0.009
Neg logit contributions
-0.008
idents-0.007
 sack-0.007
 surely-0.007
ory-0.007
Token celebrating
Token ID17499
Feature activation-1.14e+00

Pos logit contributions
rum+0.034
Jo+0.031
ud+0.029
jo+0.029
and+0.028
Neg logit contributions
-0.019
 cooler-0.017
 surely-0.017
 prett-0.017
 sack-0.016
Token by
Token ID416
Feature activation+1.31e+00

Pos logit contributions
rum+0.125
Jo+0.121
ud+0.113
jo+0.105
 Pen+0.103
Neg logit contributions
-0.082
idents-0.073
 sack-0.071
 cooler-0.068
 surely-0.067
Token a
Token ID257
Feature activation-1.44e-01

Pos logit contributions
+0.064
 sack+0.054
idents+0.053
 surely+0.053
 Dino+0.053
Neg logit contributions
rum-0.082
Jo-0.078
ud-0.072
jo-0.070
 Pen-0.069
Token good
Token ID922
Feature activation-5.67e-01

Pos logit contributions
Jo+0.014
rum+0.013
 Pen+0.012
 Ali+0.012
ud+0.011
Neg logit contributions
-0.013
idents-0.011
 hotter-0.010
ory-0.010
 surely-0.010
Token dream
Token ID4320
Feature activation-1.01e+00

Pos logit contributions
rum+0.067
Jo+0.065
 Pen+0.058
 Jacob+0.057
 Ali+0.056
Neg logit contributions
-0.035
 sack-0.032
ory-0.032
 cooler-0.031
idents-0.031
Token and
Token ID290
Feature activation+4.48e-01

Pos logit contributions
rum+0.092
Jo+0.092
ud+0.080
 Pen+0.080
 Ali+0.077
Neg logit contributions
-0.093
idents-0.078
 surely-0.078
 sack-0.077
 cooler-0.074
Token reminded
Token ID14516
Feature activation+1.05e+00

Pos logit contributions
+0.037
idents+0.032
 sack+0.031
 surely+0.031
 hotter+0.030
Neg logit contributions
rum-0.044
Jo-0.044
ud-0.040
 Pen-0.038
and-0.038
Token her
Token ID607
Feature activation-5.00e-01

Pos logit contributions
+0.137
idents+0.116
 hotter+0.113
 sack+0.113
clips+0.112
Neg logit contributions
Jo-0.061
rum-0.054
and-0.052
 Pen-0.048
old-0.048
Token to
Token ID284
Feature activation-5.74e-01

Pos logit contributions
Jo+0.049
rum+0.048
ud+0.044
 Pen+0.041
jo+0.041
Neg logit contributions
-0.041
idents-0.037
 sack-0.036
 surely-0.036
 cooler-0.035
Token always
Token ID1464
Feature activation-3.11e+00

Pos logit contributions
Jo+0.056
rum+0.055
ud+0.050
and+0.049
 Pen+0.048
Neg logit contributions
-0.049
 surely-0.042
 sack-0.041
idents-0.040
 cooler-0.039
Token be
Token ID307
Feature activation-2.07e-01

Pos logit contributions
Jo+0.325
rum+0.314
ud+0.293
and+0.281
 Pen+0.281
Neg logit contributions
-0.244
 surely-0.206
 sack-0.203
idents-0.201
 cooler-0.193
Token careful
Token ID8161
Feature activation-4.84e+00

Pos logit contributions
Jo+0.018
rum+0.017
ud+0.015
 Pen+0.015
 Ali+0.014
Neg logit contributions
-0.020
idents-0.018
 hotter-0.017
 sack-0.017
 surely-0.017
Token about
Token ID546
Feature activation-3.78e+00

Pos logit contributions
Jo+0.594
rum+0.560
ud+0.549
 Pen+0.535
 Ali+0.521
Neg logit contributions
 surely-0.238
-0.234
 still-0.230
idents-0.225
 hotter-0.218
Tokenthank
Token ID40716
Feature activation+3.84e+00

Pos logit contributions
Jo+0.092
rum+0.088
 Pen+0.079
ud+0.079
and+0.079
Neg logit contributions
-0.068
idents-0.057
 sack-0.054
 hotter-0.053
ory-0.052
Token you
Token ID345
Feature activation+2.81e-01

Pos logit contributions
+0.265
 Dino+0.202
idents+0.200
 sack+0.199
 surely+0.198
Neg logit contributions
rum-0.439
Jo-0.432
ud-0.410
jo-0.396
and-0.370
Token"
Token ID1
Feature activation+7.96e-03

Pos logit contributions
+0.026
 sack+0.022
idents+0.022
 surely+0.022
ory+0.021
Neg logit contributions
Jo-0.026
rum-0.024
ud-0.022
and-0.021
jo-0.021
Token and
Token ID290
Feature activation+2.31e-01

Pos logit contributions
+0.001
idents+0.001
 hotter+0.001
 sack+0.001
 surely+0.001
Neg logit contributions
Jo-0.001
rum-0.001
ud-0.001
 Pen-0.001
 Ali-0.001
Token smiled
Token ID13541
Feature activation+8.33e-02

Pos logit contributions
+0.017
idents+0.014
 sack+0.014
 surely+0.013
 cooler+0.013
Neg logit contributions
rum-0.026
Jo-0.025
ud-0.024
and-0.024
jo-0.023
Token.
Token ID13
Feature activation-7.78e-02

Pos logit contributions
+0.008
idents+0.007
 sack+0.007
 hotter+0.007
 surely+0.007
Neg logit contributions
Jo-0.007
rum-0.007
 Pen-0.006
and-0.006
 Ali-0.006
Token Mama
Token ID40084
Feature activation-9.21e-01

Pos logit contributions
rum+0.009
Jo+0.009
ud+0.008
jo+0.008
and+0.008
Neg logit contributions
-0.006
idents-0.004
 Dino-0.004
 surely-0.004
 Ros-0.004
Token p
Token ID279
Feature activation-1.47e+00

Pos logit contributions
rum+0.100
Jo+0.097
and+0.090
ud+0.088
jo+0.084
Neg logit contributions
-0.068
idents-0.055
ory-0.054
 sack-0.054
 cooler-0.053
Tokenatted
Token ID16898
Feature activation-4.87e-01

Pos logit contributions
Jo+0.136
rum+0.130
ud+0.116
 Pen+0.113
 Ali+0.113
Neg logit contributions
-0.135
idents-0.114
 hotter-0.113
 sack-0.112
 surely-0.111
Token her
Token ID607
Feature activation-6.70e-01

Pos logit contributions
Jo+0.048
rum+0.047
ud+0.042
and+0.041
jo+0.039
Neg logit contributions
-0.040
idents-0.036
 hotter-0.035
 surely-0.034
 sack-0.034
Token head
Token ID1182
Feature activation-1.63e+00

Pos logit contributions
Jo+0.072
rum+0.069
ud+0.064
and+0.062
jo+0.061
Neg logit contributions
-0.052
 sack-0.043
idents-0.043
 hotter-0.042
 surely-0.041
Token to
Token ID284
Feature activation-7.90e-01

Pos logit contributions
+0.082
idents+0.076
 sack+0.074
 cooler+0.071
 surely+0.071
Neg logit contributions
rum-0.109
Jo-0.107
ud-0.103
 Pen-0.093
jo-0.092
Token go
Token ID467
Feature activation+8.24e-01

Pos logit contributions
rum+0.096
Jo+0.094
ud+0.090
and+0.089
jo+0.086
Neg logit contributions
-0.049
 sack-0.045
 surely-0.039
 cooler-0.037
idents-0.035
Token for
Token ID329
Feature activation+7.49e-01

Pos logit contributions
+0.078
idents+0.067
 hotter+0.063
 surely+0.063
ory+0.062
Neg logit contributions
Jo-0.075
rum-0.072
 Pen-0.063
and-0.063
 Ali-0.062
Token a
Token ID257
Feature activation-3.47e-01

Pos logit contributions
+0.061
 cooler+0.049
 Dino+0.049
 sack+0.049
idents+0.047
Neg logit contributions
rum-0.077
Jo-0.075
ud-0.069
and-0.067
jo-0.066
Token walk
Token ID2513
Feature activation+7.01e-01

Pos logit contributions
rum+0.042
Jo+0.041
ud+0.037
 Pen+0.036
 Ali+0.036
Neg logit contributions
-0.023
idents-0.018
 sack-0.017
 surely-0.017
ory-0.017
Token.
Token ID13
Feature activation-2.49e-01

Pos logit contributions
+0.052
 sack+0.043
 cooler+0.042
 surely+0.042
ory+0.041
Neg logit contributions
rum-0.076
Jo-0.074
ud-0.067
 Pen-0.065
 Ali-0.064
Token He
Token ID679
Feature activation+1.62e-01

Pos logit contributions
rum+0.028
Jo+0.027
ud+0.025
 Pen+0.025
rd+0.023
Neg logit contributions
-0.017
idents-0.014
 Dino-0.013
 sack-0.013
 surely-0.013
Token looked
Token ID3114
Feature activation+7.68e-01

Pos logit contributions
+0.010
 sack+0.009
 cooler+0.009
ory+0.009
 surely+0.009
Neg logit contributions
rum-0.020
Jo-0.017
and-0.016
ud-0.016
 Pen-0.015
Token around
Token ID1088
Feature activation-1.21e+00

Pos logit contributions
+0.064
idents+0.053
 hotter+0.050
 sack+0.050
 surely+0.049
Neg logit contributions
Jo-0.079
rum-0.076
 Pen-0.068
ud-0.068
and-0.067
Token and
Token ID290
Feature activation+8.24e-02

Pos logit contributions
rum+0.127
Jo+0.125
ud+0.112
jo+0.106
and+0.106
Neg logit contributions
-0.094
 surely-0.078
idents-0.077
 sack-0.077
 hotter-0.076
Token saw
Token ID2497
Feature activation-2.88e-01

Pos logit contributions
+0.006
idents+0.005
 hotter+0.005
 sack+0.005
 surely+0.005
Neg logit contributions
rum-0.009
Jo-0.009
ud-0.008
 Pen-0.007
and-0.007
Token anytime
Token ID17949
Feature activation+1.61e+00

Pos logit contributions
+0.244
idents+0.205
 surely+0.200
ory+0.200
 sack+0.199
Neg logit contributions
Jo-0.308
rum-0.303
ud-0.267
jo-0.253
 Pen-0.252
Token.
Token ID13
Feature activation+5.47e-02

Pos logit contributions
+0.137
ory+0.116
 cooler+0.114
idents+0.114
 sack+0.114
Neg logit contributions
rum-0.160
Jo-0.158
ud-0.136
jo-0.130
and-0.129
Token And
Token ID843
Feature activation-1.01e+00

Pos logit contributions
+0.005
idents+0.004
 Dino+0.004
 surely+0.004
 sack+0.004
Neg logit contributions
Jo-0.005
rum-0.005
ud-0.005
jo-0.004
and-0.004
Token don
Token ID836
Feature activation+1.43e+00

Pos logit contributions
Jo+0.098
rum+0.095
 Pen+0.084
ud+0.083
and+0.083
Neg logit contributions
-0.089
idents-0.074
 hotter-0.071
 sack-0.071
ory-0.070
Token't
Token ID470
Feature activation+1.90e+00

Pos logit contributions
+0.131
ory+0.124
idents+0.117
 hotter+0.116
 sack+0.112
Neg logit contributions
Jo-0.125
rum-0.117
 Pen-0.107
 Jacob-0.103
 Ali-0.103
Token forget
Token ID6044
Feature activation+2.98e+00

Pos logit contributions
+0.155
idents+0.128
 sack+0.121
 hotter+0.121
 surely+0.119
Neg logit contributions
Jo-0.197
rum-0.191
 Pen-0.169
ud-0.169
and-0.168
Token to
Token ID284
Feature activation-6.18e-01

Pos logit contributions
idents+0.189
+0.183
 cooler+0.176
 sack+0.174
 Dino+0.165
Neg logit contributions
Jo-0.329
rum-0.325
ud-0.301
and-0.276
jo-0.275
Token share
Token ID2648
Feature activation+2.77e+00

Pos logit contributions
Jo+0.067
rum+0.064
ud+0.058
 Pen+0.057
and+0.057
Neg logit contributions
-0.048
idents-0.039
 sack-0.038
 hotter-0.037
 surely-0.037
Token your
Token ID534
Feature activation-2.82e+00

Pos logit contributions
+0.260
idents+0.223
 sack+0.215
 hotter+0.214
ory+0.212
Neg logit contributions
Jo-0.252
rum-0.240
ud-0.210
 Pen-0.209
 Ali-0.208
Token blue
Token ID4171
Feature activation+2.52e-02

Pos logit contributions
rum+0.249
Jo+0.244
 Pen+0.219
and+0.217
rd+0.210
Neg logit contributions
-0.255
idents-0.222
 surely-0.218
 hotter-0.216
Sorry-0.206
Tokenberries
Token ID20853
Feature activation+4.36e+00

Pos logit contributions
+0.002
 surely+0.002
 hotter+0.002
idents+0.002
Sorry+0.001
Neg logit contributions
Jo-0.003
rum-0.003
ud-0.002
 Pen-0.002
and-0.002
Token big
Token ID1263
Feature activation+3.23e-01

Pos logit contributions
Jo+0.034
rum+0.032
 Pen+0.028
ud+0.028
 Ali+0.028
Neg logit contributions
-0.042
idents-0.036
 hotter-0.035
 surely-0.034
 sack-0.034
Token lion
Token ID18744
Feature activation-6.77e-02

Pos logit contributions
+0.029
idents+0.025
 hotter+0.024
 sack+0.024
 surely+0.023
Neg logit contributions
Jo-0.030
rum-0.029
 Pen-0.026
ud-0.026
 Ali-0.025
Token.
Token ID13
Feature activation-2.79e-01

Pos logit contributions
rum+0.008
Jo+0.008
Jamie+0.007
and+0.007
 Jamie+0.007
Neg logit contributions
-0.004
 Dino-0.004
 sack-0.003
 still-0.003
 cooler-0.003
Token He
Token ID679
Feature activation+2.29e-01

Pos logit contributions
Jo+0.033
rum+0.032
ud+0.030
and+0.030
old+0.028
Neg logit contributions
-0.018
 Dino-0.015
idents-0.014
 sack-0.013
 surely-0.013
Token was
Token ID373
Feature activation-7.20e-01

Pos logit contributions
+0.021
 Dino+0.019
 sack+0.018
idents+0.018
 cooler+0.018
Neg logit contributions
rum-0.020
Jo-0.020
and-0.018
ud-0.017
 Pen-0.017
Token huge
Token ID3236
Feature activation+1.90e+00

Pos logit contributions
Jo+0.083
rum+0.083
ud+0.074
and+0.074
jo+0.070
Neg logit contributions
-0.048
 Dino-0.045
 cooler-0.042
 sack-0.041
 hotter-0.041
Token and
Token ID290
Feature activation+1.94e-01

Pos logit contributions
+0.129
 cooler+0.119
 Dino+0.119
 sack+0.118
idents+0.111
Neg logit contributions
Jo-0.213
rum-0.205
and-0.184
Jamie-0.181
 Pen-0.176
Token very
Token ID845
Feature activation+8.89e-01

Pos logit contributions
+0.013
 Dino+0.011
 sack+0.010
 surely+0.010
 cooler+0.010
Neg logit contributions
Jo-0.022
rum-0.022
ud-0.021
and-0.020
old-0.019
Token strong
Token ID1913
Feature activation+2.34e+00

Pos logit contributions
+0.055
 Dino+0.045
ory+0.045
 cooler+0.045
 sack+0.044
Neg logit contributions
Jo-0.107
rum-0.104
ud-0.095
and-0.095
 Pen-0.090
Token.
Token ID13
Feature activation-2.46e-01

Pos logit contributions
+0.106
 cooler+0.100
 Dino+0.099
 sack+0.087
 still+0.080
Neg logit contributions
Jo-0.310
rum-0.289
Jamie-0.286
and-0.269
Mary-0.268
Token He
Token ID679
Feature activation+2.45e-01

Pos logit contributions
Jo+0.033
rum+0.032
ud+0.029
a+0.029
and+0.028
Neg logit contributions
-0.013
 Dino-0.010
 cooler-0.008
 Cr-0.008
 sack-0.008
Token started
Token ID2067
Feature activation+2.82e+00

Pos logit contributions
Jo+0.469
rum+0.447
 Pen+0.400
ud+0.396
 Ali+0.395
Neg logit contributions
-0.389
idents-0.324
 hotter-0.305
 sack-0.302
ory-0.301
Token to
Token ID284
Feature activation-8.09e-01

Pos logit contributions
+0.243
idents+0.203
 surely+0.203
 sack+0.201
 hotter+0.200
Neg logit contributions
Jo-0.266
rum-0.265
ud-0.238
 Pen-0.237
and-0.234
Token float
Token ID12178
Feature activation+9.87e-01

Pos logit contributions
Jo+0.092
rum+0.090
ud+0.082
and+0.081
 Pen+0.080
Neg logit contributions
-0.057
idents-0.046
 sack-0.045
 surely-0.044
 hotter-0.044
Token away
Token ID1497
Feature activation+1.82e+00

Pos logit contributions
+0.080
idents+0.064
 hotter+0.059
 sack+0.058
 surely+0.058
Neg logit contributions
Jo-0.104
rum-0.101
 Pen-0.091
 Ali-0.090
and-0.090
Token,
Token ID11
Feature activation-6.22e-02

Pos logit contributions
+0.168
idents+0.143
 hotter+0.136
 sack+0.136
 surely+0.135
Neg logit contributions
Jo-0.168
rum-0.162
 Pen-0.142
ud-0.141
and-0.140
Token taking
Token ID2263
Feature activation-1.66e+00

Pos logit contributions
Jo+0.006
rum+0.006
ud+0.005
and+0.005
 Pen+0.005
Neg logit contributions
-0.005
idents-0.005
 surely-0.005
 hotter-0.005
 sack-0.004
Token the
Token ID262
Feature activation+4.40e-01

Pos logit contributions
rum+0.190
Jo+0.189
ud+0.172
 Pen+0.167
and+0.164
Neg logit contributions
-0.105
 sack-0.090
 surely-0.087
idents-0.085
 hotter-0.083
Token people
Token ID661
Feature activation+2.70e-02

Pos logit contributions
+0.034
 sack+0.029
idents+0.028
 hotter+0.028
 surely+0.027
Neg logit contributions
rum-0.047
Jo-0.047
ud-0.043
and-0.041
 Pen-0.040
Token with
Token ID351
Feature activation+1.13e-01

Pos logit contributions
+0.002
 sack+0.002
 surely+0.002
 cooler+0.002
 hotter+0.002
Neg logit contributions
Jo-0.003
rum-0.003
ud-0.003
 Pen-0.002
 Ali-0.002
Token it
Token ID340
Feature activation-1.28e+00

Pos logit contributions
+0.008
 sack+0.007
 surely+0.006
 cooler+0.006
idents+0.006
Neg logit contributions
Jo-0.013
rum-0.013
ud-0.012
and-0.011
jo-0.011
Token.
Token ID13
Feature activation-1.45e-01

Pos logit contributions
Jo+0.121
rum+0.116
ud+0.102
 Pen+0.101
 Ali+0.100
Neg logit contributions
-0.117
idents-0.098
 sack-0.097
 surely-0.095
 hotter-0.094
Tokeniness
Token ID1272
Feature activation-1.32e+00

Pos logit contributions
Jo+0.123
rum+0.115
 Pen+0.107
 Ali+0.105
 Jacob+0.104
Neg logit contributions
-0.123
idents-0.105
 hotter-0.105
 surely-0.104
ory-0.104
Token of
Token ID286
Feature activation-2.98e+00

Pos logit contributions
Jo+0.130
rum+0.127
ud+0.114
 Pen+0.111
 Jacob+0.109
Neg logit contributions
-0.110
idents-0.096
 surely-0.094
 sack-0.093
 hotter-0.092
Token the
Token ID262
Feature activation+3.95e-01

Pos logit contributions
Jo+0.322
rum+0.312
jo+0.291
ud+0.281
and+0.275
Neg logit contributions
-0.213
 sack-0.191
 cooler-0.185
 hotter-0.179
idents-0.176
Token toilet
Token ID16146
Feature activation-1.67e+00

Pos logit contributions
+0.034
idents+0.028
 sack+0.027
 hotter+0.027
 surely+0.026
Neg logit contributions
Jo-0.039
rum-0.038
 Pen-0.034
ud-0.034
and-0.033
Token.
Token ID13
Feature activation-3.34e-01

Pos logit contributions
Jo+0.164
rum+0.161
ud+0.143
 Pen+0.138
and+0.138
Neg logit contributions
-0.146
idents-0.124
 sack-0.121
 cooler-0.118
 hotter-0.117
Tokenâ
Token ID22940
Feature activation-2.24e+00

Pos logit contributions
rum+0.035
Jo+0.034
ud+0.030
jo+0.029
 Pen+0.029
Neg logit contributions
-0.028
 Dino-0.020
idents-0.020
ory-0.020
 surely-0.020
Token
Token ID26391
Feature activation+1.51e+00

Pos logit contributions
Jo+0.218
rum+0.207
 Pen+0.181
jo+0.178
ud+0.178
Neg logit contributions
-0.201
idents-0.170
 sack-0.167
 hotter-0.163
 cooler-0.159
Token
Token ID198
Feature activation+6.56e-02

Pos logit contributions
+0.144
idents+0.111
 Dino+0.095
 surely+0.095
+0.095
Neg logit contributions
rum-0.149
Jo-0.138
and-0.127
 Pen-0.125
ud-0.125
Token
Token ID198
Feature activation+3.18e-02

Pos logit contributions
+0.005
 Dino+0.003
 surely+0.003
Sorry+0.003
ory+0.003
Neg logit contributions
rum-0.007
Jo-0.007
 Pen-0.006
 Ali-0.006
 Jacob-0.006
TokenThe
Token ID464
Feature activation+1.57e-01

Pos logit contributions
+0.002
Sorry+0.002
 surely+0.002
ory+0.002
 Dino+0.002
Neg logit contributions
rum-0.004
Jo-0.003
 Ali-0.003
 Pen-0.003
 Jacob-0.003
Token little
Token ID1310
Feature activation-1.98e+00

Pos logit contributions
+0.011
idents+0.009
 sack+0.009
 hotter+0.009
ory+0.008
Neg logit contributions
Jo-0.018
rum-0.017
 Pen-0.015
ud-0.015
and-0.015
Token.
Token ID13
Feature activation+2.23e-01

Pos logit contributions
Jo+0.026
rum+0.024
 Pen+0.022
 Jacob+0.021
 Ali+0.021
Neg logit contributions
-0.023
idents-0.020
 sack-0.019
 hotter-0.019
 cooler-0.018
Token We
Token ID775
Feature activation+1.59e-01

Pos logit contributions
+0.023
idents+0.019
ory+0.019
 hotter+0.019
 sack+0.019
Neg logit contributions
Jo-0.018
rum-0.018
 Pen-0.015
 Ali-0.015
 Jacob-0.015
Token can
Token ID460
Feature activation+1.97e+00

Pos logit contributions
+0.014
idents+0.012
 sack+0.012
 hotter+0.012
 surely+0.011
Neg logit contributions
Jo-0.015
rum-0.014
 Pen-0.013
ud-0.013
and-0.013
Token help
Token ID1037
Feature activation+1.12e+00

Pos logit contributions
+0.174
 hotter+0.158
ory+0.158
idents+0.150
 Dino+0.148
Neg logit contributions
Jo-0.173
rum-0.164
 Pen-0.148
 Jacob-0.146
 Ali-0.145
Token you
Token ID345
Feature activation+3.09e-01

Pos logit contributions
+0.086
idents+0.076
 sack+0.070
 hotter+0.069
ory+0.068
Neg logit contributions
Jo-0.121
rum-0.118
ud-0.105
jo-0.104
 Pen-0.100
Token."
Token ID526
Feature activation-1.89e+00

Pos logit contributions
+0.027
idents+0.023
 sack+0.022
 hotter+0.022
 surely+0.022
Neg logit contributions
Jo-0.030
rum-0.029
ud-0.026
 Pen-0.026
 Ali-0.025
Token
Token ID198
Feature activation+5.36e-01

Pos logit contributions
Jo+0.152
rum+0.140
 Pen+0.132
 Ali+0.131
and+0.130
Neg logit contributions
-0.192
 hotter-0.168
idents-0.167
 surely-0.167
 sack-0.167
Token
Token ID198
Feature activation+5.22e-01

Pos logit contributions
+0.045
idents+0.037
 sack+0.035
 hotter+0.035
 Dino+0.035
Neg logit contributions
Jo-0.054
rum-0.052
ud-0.046
 Pen-0.046
 Ali-0.045
TokenL
Token ID43
Feature activation+1.58e+00

Pos logit contributions
+0.042
idents+0.034
 hotter+0.033
 sack+0.033
 surely+0.032
Neg logit contributions
Jo-0.055
rum-0.054
 Pen-0.048
ud-0.048
and-0.047
Tokenily
Token ID813
Feature activation-1.04e+00

Pos logit contributions
+0.127
ory+0.110
idents+0.106
 cooler+0.104
 hotter+0.104
Neg logit contributions
Jo-0.156
rum-0.136
jo-0.128
 Pen-0.127
 Jacob-0.120
Token stops
Token ID9911
Feature activation-2.07e-01

Pos logit contributions
Jo+0.082
rum+0.078
 Pen+0.069
ud+0.069
 Ali+0.068
Neg logit contributions
-0.110
idents-0.094
 surely-0.092
 hotter-0.091
ory-0.090
Token make
Token ID787
Feature activation+2.56e-01

Pos logit contributions
rum+0.084
Jo+0.082
ud+0.080
and+0.075
 Pen+0.072
Neg logit contributions
-0.056
idents-0.049
 surely-0.046
 sack-0.045
ory-0.043
Token history
Token ID2106
Feature activation+1.44e+00

Pos logit contributions
+0.019
idents+0.018
 sack+0.017
 hotter+0.017
 cooler+0.016
Neg logit contributions
rum-0.026
Jo-0.025
ud-0.024
jo-0.022
 Pen-0.022
Token.
Token ID13
Feature activation-1.84e-01

Pos logit contributions
+0.119
idents+0.101
 sack+0.097
 surely+0.097
 cooler+0.097
Neg logit contributions
Jo-0.143
rum-0.142
ud-0.129
 Pen-0.123
 Ali-0.120
Token They
Token ID1119
Feature activation+9.43e-04

Pos logit contributions
Jo+0.018
rum+0.018
ud+0.016
 Pen+0.016
and+0.015
Neg logit contributions
-0.016
idents-0.013
 sack-0.012
 surely-0.012
ory-0.012
Token both
Token ID1111
Feature activation+9.61e-01

Pos logit contributions
+0.000
 sack+0.000
idents+0.000
 surely+0.000
ory+0.000
Neg logit contributions
rum-0.000
Jo-0.000
and-0.000
ud-0.000
 Pen-0.000
Token knew
Token ID2993
Feature activation-1.83e+00

Pos logit contributions
+0.051
 continued+0.050
 surely+0.049
ory+0.047
 sack+0.045
Neg logit contributions
rum-0.115
and-0.106
Jo-0.104
ud-0.102
 Pen-0.095
Token that
Token ID326
Feature activation-7.94e-01

Pos logit contributions
rum+0.202
Jo+0.198
ud+0.182
jo+0.175
and+0.174
Neg logit contributions
-0.129
 surely-0.109
idents-0.108
 sack-0.107
 Dino-0.105
Token their
Token ID511
Feature activation-9.71e-01

Pos logit contributions
rum+0.090
Jo+0.088
ud+0.083
jo+0.079
and+0.075
Neg logit contributions
-0.051
idents-0.046
 surely-0.046
 sack-0.046
 hotter-0.044
Token kiss
Token ID9245
Feature activation+6.69e-01

Pos logit contributions
Jo+0.092
rum+0.090
ud+0.078
and+0.076
 Pen+0.076
Neg logit contributions
-0.089
idents-0.078
 sack-0.075
 surely-0.073
ory-0.071
Token would
Token ID561
Feature activation-2.10e-01

Pos logit contributions
+0.062
idents+0.052
 hotter+0.050
ory+0.050
 sack+0.050
Neg logit contributions
Jo-0.061
rum-0.059
 Pen-0.052
ud-0.051
 Ali-0.051
Token always
Token ID1464
Feature activation-3.36e+00

Pos logit contributions
Jo+0.019
rum+0.018
 Pen+0.015
 Ali+0.015
and+0.015
Neg logit contributions
-0.020
idents-0.017
 hotter-0.017
ory-0.017
 sack-0.016
Token a
Token ID257
Feature activation-2.51e-01

Pos logit contributions
Jo+0.018
rum+0.018
ud+0.015
jo+0.015
and+0.015
Neg logit contributions
-0.015
 Dino-0.013
 hotter-0.013
idents-0.012
 sack-0.012
Token butterfly
Token ID35113
Feature activation+2.14e+00

Pos logit contributions
Jo+0.024
rum+0.022
 Pen+0.020
ud+0.020
 Ali+0.020
Neg logit contributions
-0.023
idents-0.019
 surely-0.018
ory-0.018
 hotter-0.018
Token and
Token ID290
Feature activation+2.53e-01

Pos logit contributions
+0.180
 sack+0.154
 cooler+0.147
idents+0.144
 hotter+0.141
Neg logit contributions
Jo-0.218
rum-0.212
Jamie-0.188
 Jamie-0.188
 Jacob-0.187
Token chased
Token ID26172
Feature activation-3.95e+00

Pos logit contributions
+0.020
 sack+0.018
 Dino+0.018
idents+0.018
 hotter+0.017
Neg logit contributions
rum-0.025
Jo-0.024
ud-0.023
and-0.022
jo-0.021
Token after
Token ID706
Feature activation+1.97e+00

Pos logit contributions
Jo+0.339
rum+0.330
and+0.301
 Pen+0.298
ud+0.289
Neg logit contributions
-0.398
idents-0.323
 hotter-0.322
 surely-0.315
 cooler-0.304
Token it
Token ID340
Feature activation-1.26e+00

Pos logit contributions
+0.199
idents+0.171
 hotter+0.164
 sack+0.164
ory+0.163
Neg logit contributions
Jo-0.167
rum-0.160
 Pen-0.138
ud-0.138
and-0.136
Token.
Token ID13
Feature activation-1.81e-01

Pos logit contributions
Jo+0.139
rum+0.129
Jamie+0.121
ud+0.120
jo+0.119
Neg logit contributions
-0.094
 sack-0.078
idents-0.077
 cooler-0.076
 surely-0.075
Token The
Token ID383
Feature activation+1.07e+00

Pos logit contributions
Jo+0.015
rum+0.015
 Pen+0.014
 Ali+0.013
 Jacob+0.013
Neg logit contributions
-0.017
 surely-0.015
 hotter-0.014
ory-0.014
idents-0.014
Token butterfly
Token ID35113
Feature activation+2.13e+00

Pos logit contributions
+0.097
idents+0.084
ory+0.084
 hotter+0.081
 surely+0.078
Neg logit contributions
Jo-0.096
rum-0.088
 Pen-0.084
 Ali-0.080
ud-0.080
Token flew
Token ID13112
Feature activation+3.66e-02

Pos logit contributions
+0.166
idents+0.137
 sack+0.134
 surely+0.130
 hotter+0.129
Neg logit contributions
Jo-0.224
rum-0.222
ud-0.197
and-0.197
 Pen-0.194
Token away
Token ID1497
Feature activation+1.78e+00

Pos logit contributions
+0.003
idents+0.002
ory+0.002
 hotter+0.002
 sack+0.002
Neg logit contributions
Jo-0.004
rum-0.004
 Pen-0.003
and-0.003
 Ali-0.003
Token completely
Token ID3190
Feature activation+2.30e+00

Pos logit contributions
Jo+0.073
rum+0.072
 Pen+0.064
 Jacob+0.063
ud+0.063
Neg logit contributions
-0.072
idents-0.063
ory-0.059
 Dino-0.057
Sorry-0.054
Token filled
Token ID5901
Feature activation-4.49e-01

Pos logit contributions
+0.196
idents+0.173
 Dino+0.159
ory+0.154
 trigger+0.148
Neg logit contributions
rum-0.214
Jo-0.213
ud-0.191
 Pen-0.183
and-0.181
Token.
Token ID13
Feature activation-4.01e-01

Pos logit contributions
Jo+0.045
rum+0.044
ud+0.039
 Pen+0.038
 Ali+0.038
Neg logit contributions
-0.038
idents-0.032
 surely-0.031
 hotter-0.031
 sack-0.031
Token
Token ID198
Feature activation-1.09e-01

Pos logit contributions
rum+0.045
Jo+0.043
ud+0.041
and+0.038
 clim+0.038
Neg logit contributions
-0.031
idents-0.024
 surely-0.022
 hotter-0.020
 Dino-0.020
Token
Token ID198
Feature activation-1.01e-01

Pos logit contributions
rum+0.012
Jo+0.011
ud+0.011
 Pen+0.010
 clim+0.010
Neg logit contributions
-0.008
idents-0.006
 surely-0.006
 sack-0.006
 Dino-0.006
TokenAnne
Token ID43227
Feature activation-6.45e+00

Pos logit contributions
rum+0.011
Jo+0.010
ud+0.010
 Pen+0.009
 Jacob+0.009
Neg logit contributions
-0.008
Sorry-0.006
 surely-0.006
idents-0.006
 sack-0.006
Token and
Token ID290
Feature activation+6.69e-03

Pos logit contributions
rum+0.699
Jo+0.652
and+0.627
ud+0.601
 Pen+0.588
Neg logit contributions
-0.487
 surely-0.398
ory-0.382
idents-0.379
 sack-0.375
Token Jack
Token ID3619
Feature activation+2.08e-01

Pos logit contributions
+0.001
 surely+0.001
 sack+0.001
idents+0.001
 Ros+0.001
Neg logit contributions
rum-0.001
ud-0.001
Jo-0.001
and-0.000
rd-0.000
Token were
Token ID547
Feature activation-4.86e-01

Pos logit contributions
+0.016
 surely+0.013
idents+0.013
 sack+0.013
ory+0.013
Neg logit contributions
rum-0.022
Jo-0.021
and-0.020
 Pen-0.019
ud-0.019
Token so
Token ID523
Feature activation-5.14e-01

Pos logit contributions
rum+0.055
Jo+0.053
ud+0.049
and+0.048
jo+0.048
Neg logit contributions
-0.035
 surely-0.031
 cooler-0.028
 hotter-0.028
 sack-0.027
Token happy
Token ID3772
Feature activation-1.24e+00

Pos logit contributions
Jo+0.052
rum+0.050
ud+0.045
 Pen+0.045
 Ali+0.044
Neg logit contributions
-0.044
idents-0.036
 hotter-0.035
 surely-0.034
 sack-0.034
Token special
Token ID2041
Feature activation+1.19e+00

Pos logit contributions
+0.061
 sack+0.054
 cooler+0.053
idents+0.049
 surely+0.047
Neg logit contributions
rum-0.085
Jo-0.084
ud-0.077
 Pen-0.074
 Jacob-0.073
Token game
Token ID983
Feature activation-7.62e-01

Pos logit contributions
+0.092
 sack+0.086
 cooler+0.081
 gem+0.076
idents+0.072
Neg logit contributions
rum-0.129
Jo-0.125
ud-0.120
Jamie-0.112
 Pen-0.110
Token of
Token ID286
Feature activation-2.92e+00

Pos logit contributions
Jo+0.086
rum+0.086
ud+0.078
Jamie+0.076
 Pen+0.075
Neg logit contributions
-0.052
 sack-0.043
 cooler-0.040
idents-0.039
 Dino-0.038
Token hide
Token ID7808
Feature activation-3.59e+00

Pos logit contributions
rum+0.287
Jo+0.284
ud+0.264
jo+0.261
and+0.239
Neg logit contributions
-0.249
 sack-0.224
 cooler-0.214
 golf-0.212
idents-0.206
Token-
Token ID12
Feature activation+2.55e-01

Pos logit contributions
Jo+0.368
rum+0.349
ud+0.312
 Jacob+0.309
jo+0.308
Neg logit contributions
-0.270
 sack-0.244
idents-0.236
ory-0.233
 cooler-0.233
Tokenand
Token ID392
Feature activation-6.16e+00

Pos logit contributions
+0.028
ory+0.027
 peanuts+0.027
 Dino+0.026
Sorry+0.026
Neg logit contributions
rum-0.015
Jo-0.013
 Pen-0.012
 Ali-0.011
 Jacob-0.011
Token-
Token ID12
Feature activation+2.63e-01

Pos logit contributions
rum+0.600
ud+0.576
Jo+0.568
 Pen+0.531
 Jacob+0.521
Neg logit contributions
-0.446
idents-0.417
ory-0.415
 sack-0.409
 Dino-0.391
Tokenseek
Token ID36163
Feature activation-1.67e+00

Pos logit contributions
+0.020
Sorry+0.017
idents+0.017
 Dino+0.017
 surely+0.017
Neg logit contributions
rum-0.026
Jo-0.024
 Pen-0.023
 Ali-0.022
ud-0.022
Token,
Token ID11
Feature activation+1.52e-01

Pos logit contributions
Jo+0.207
rum+0.202
ud+0.187
jo+0.186
 Pen+0.179
Neg logit contributions
-0.083
 cooler-0.073
 sack-0.067
idents-0.062
ized-0.062
Token so
Token ID523
Feature activation-4.63e-01

Pos logit contributions
+0.011
 sack+0.011
 cooler+0.011
idents+0.010
 surely+0.010
Neg logit contributions
rum-0.016
Jo-0.016
ud-0.015
jo-0.014
 Pen-0.013
Token she
Token ID673
Feature activation+1.59e-01

Pos logit contributions
rum+0.051
Jo+0.051
ud+0.046
and+0.045
 Pen+0.044
Neg logit contributions
-0.034
idents-0.028
 sack-0.027
 surely-0.026
 hotter-0.026
Token.
Token ID13
Feature activation+2.97e-01

Pos logit contributions
Jo+0.154
rum+0.147
 Pen+0.131
ud+0.129
 Ali+0.127
Neg logit contributions
-0.141
idents-0.120
 hotter-0.118
 sack-0.115
 surely-0.113
Token She
Token ID1375
Feature activation-3.01e-01

Pos logit contributions
+0.026
idents+0.021
 sack+0.020
 hotter+0.020
 surely+0.019
Neg logit contributions
Jo-0.030
rum-0.029
ud-0.026
and-0.025
jo-0.025
Token runs
Token ID4539
Feature activation-3.52e+00

Pos logit contributions
Jo+0.025
rum+0.025
and+0.022
ud+0.021
 Pen+0.021
Neg logit contributions
-0.029
idents-0.026
 sack-0.025
 hotter-0.025
 cooler-0.025
Token to
Token ID284
Feature activation-5.15e-01

Pos logit contributions
Jo+0.266
rum+0.256
and+0.221
 Pen+0.220
ud+0.219
Neg logit contributions
-0.388
idents-0.332
 hotter-0.320
ory-0.320
 sack-0.318
Token the
Token ID262
Feature activation+5.99e-01

Pos logit contributions
Jo+0.052
rum+0.050
ud+0.045
and+0.044
jo+0.044
Neg logit contributions
-0.044
idents-0.036
 sack-0.035
 hotter-0.034
 surely-0.034
Token living
Token ID2877
Feature activation-7.84e+00

Pos logit contributions
+0.053
idents+0.045
 sack+0.045
 hotter+0.043
 cooler+0.042
Neg logit contributions
Jo-0.058
rum-0.056
ud-0.049
and-0.049
 Pen-0.049
Token room
Token ID2119
Feature activation-1.64e+00

Pos logit contributions
Jo+0.833
rum+0.809
jo+0.724
weet+0.692
 Pen+0.691
Neg logit contributions
-0.548
 sack-0.532
idents-0.489
 cooler-0.486
 hotter-0.461
Token.
Token ID13
Feature activation+3.13e-01

Pos logit contributions
Jo+0.202
rum+0.186
jo+0.176
 Pen+0.172
ud+0.168
Neg logit contributions
-0.105
idents-0.081
 sack-0.079
 cooler-0.077
 surely-0.071
Token She
Token ID1375
Feature activation-2.85e-01

Pos logit contributions
+0.026
idents+0.021
 sack+0.020
 hotter+0.020
Sorry+0.019
Neg logit contributions
Jo-0.033
rum-0.032
ud-0.028
jo-0.028
and-0.027
Token sees
Token ID7224
Feature activation-4.16e-01

Pos logit contributions
Jo+0.029
rum+0.029
and+0.026
ud+0.025
jo+0.025
Neg logit contributions
-0.023
idents-0.020
 sack-0.020
 cooler-0.019
 hotter-0.019
Token the
Token ID262
Feature activation+6.31e-01

Pos logit contributions
Jo+0.040
rum+0.039
ud+0.034
 Pen+0.034
and+0.034
Neg logit contributions
-0.037
idents-0.031
 hotter-0.030
 sack-0.030
ory-0.029
Token
Token ID198
Feature activation+5.36e-01

Pos logit contributions
+0.037
 Dino+0.026
 surely+0.025
ory+0.024
 hotter+0.021
Neg logit contributions
rum-0.075
Jo-0.067
rd-0.062
ud-0.062
 Jacob-0.061
TokenOne
Token ID3198
Feature activation-2.47e-01

Pos logit contributions
+0.041
 surely+0.033
ory+0.032
Sorry+0.031
 Dino+0.031
Neg logit contributions
rum-0.058
Jo-0.054
 Jacob-0.049
ud-0.049
 Pen-0.048
Token day
Token ID1110
Feature activation-1.28e+00

Pos logit contributions
rum+0.029
Jo+0.027
ud+0.024
 Jacob+0.024
and+0.024
Neg logit contributions
-0.016
ory-0.014
 cooler-0.014
 surely-0.014
 sack-0.013
Token,
Token ID11
Feature activation+4.22e-02

Pos logit contributions
rum+0.121
Jo+0.121
and+0.105
jo+0.104
ud+0.104
Neg logit contributions
-0.114
ory-0.093
idents-0.093
 sack-0.090
 hotter-0.090
Token Mon
Token ID2892
Feature activation-1.15e+00

Pos logit contributions
+0.005
idents+0.004
 sack+0.004
 hotter+0.004
 surely+0.004
Neg logit contributions
Jo-0.003
rum-0.003
 Pen-0.003
 Ali-0.003
 Jacob-0.003
Tokena
Token ID64
Feature activation-6.86e+00

Pos logit contributions
Jo+0.045
rum+0.042
 Pen+0.029
ud+0.028
and+0.027
Neg logit contributions
-0.166
idents-0.150
ory-0.148
 sack-0.146
 hotter-0.146
Token was
Token ID373
Feature activation-4.69e-01

Pos logit contributions
rum+0.722
Jo+0.694
and+0.608
 Pen+0.605
ud+0.597
Neg logit contributions
-0.539
 sack-0.468
ory-0.460
idents-0.449
 cooler-0.428
Token playing
Token ID2712
Feature activation-2.39e+00

Pos logit contributions
rum+0.046
Jo+0.045
jo+0.040
ud+0.037
and+0.036
Neg logit contributions
-0.042
 hotter-0.037
 cooler-0.037
 surely-0.037
 sack-0.036
Token dolls
Token ID36062
Feature activation-1.43e+00

Pos logit contributions
Jo+0.243
rum+0.237
ud+0.210
jo+0.209
 Pen+0.204
Neg logit contributions
-0.203
 sack-0.166
idents-0.165
 hotter-0.159
 surely-0.159
Token with
Token ID351
Feature activation+2.64e-01

Pos logit contributions
rum+0.157
Jo+0.156
 Pen+0.134
jo+0.132
 Ali+0.131
Neg logit contributions
-0.115
 sack-0.092
 surely-0.089
idents-0.087
 cooler-0.085
Token T
Token ID309
Feature activation+3.72e-01

Pos logit contributions
+0.022
 sack+0.018
 Dino+0.018
 cooler+0.018
 hotter+0.017
Neg logit contributions
rum-0.027
Jo-0.026
jo-0.023
ud-0.022
and-0.022
Token at
Token ID379
Feature activation+2.73e-03

Pos logit contributions
+0.006
idents+0.005
 sack+0.005
 Dino+0.005
 hotter+0.004
Neg logit contributions
Jo-0.004
rum-0.003
 Pen-0.003
and-0.003
 Ali-0.003
Token the
Token ID262
Feature activation+4.99e-01

Pos logit contributions
 surely+0.000
 still+0.000
+0.000
idents+0.000
 finally+0.000
Neg logit contributions
rum-0.000
ud-0.000
and-0.000
rd-0.000
Jo-0.000
Token special
Token ID2041
Feature activation+1.16e+00

Pos logit contributions
+0.043
idents+0.036
 sack+0.034
 hotter+0.034
 surely+0.034
Neg logit contributions
Jo-0.050
rum-0.048
ud-0.042
 Pen-0.042
and-0.042
Token find
Token ID1064
Feature activation+8.39e-01

Pos logit contributions
+0.087
idents+0.071
 sack+0.071
ory+0.067
 hotter+0.067
Neg logit contributions
Jo-0.128
rum-0.126
and-0.113
ud-0.113
 Jacob-0.111
Token.
Token ID13
Feature activation-7.15e-02

Pos logit contributions
+0.058
 sack+0.051
 cooler+0.048
ory+0.047
idents+0.047
Neg logit contributions
rum-0.089
Jo-0.089
ud-0.081
jo-0.078
and-0.077
Token Ann
Token ID5506
Feature activation-6.45e+00

Pos logit contributions
rum+0.007
ud+0.006
weet+0.006
Jo+0.006
and+0.006
Neg logit contributions
-0.006
idents-0.004
 surely-0.004
 Finally-0.004
 Later-0.004
Tokenabel
Token ID9608
Feature activation-8.20e+00

Pos logit contributions
rum+0.506
and+0.429
Jo+0.379
uzzle+0.360
 outage+0.355
Neg logit contributions
-0.619
ory-0.619
 still-0.583
 surely-0.582
 continued-0.582
Tokenle
Token ID293
Feature activation-1.22e+00

Pos logit contributions
rum+0.874
Jo+0.803
and+0.758
ud+0.743
 Ali+0.740
Neg logit contributions
-0.586
ory-0.513
ized-0.505
 surely-0.497
 sack-0.463
Token taught
Token ID7817
Feature activation+1.58e+00

Pos logit contributions
rum+0.131
Jo+0.123
and+0.117
ud+0.114
 Pen+0.112
Neg logit contributions
-0.089
ory-0.073
 sack-0.072
 surely-0.070
idents-0.069
Token them
Token ID606
Feature activation+6.73e-01

Pos logit contributions
+0.090
idents+0.082
 Ros+0.080
 Dino+0.075
 sack+0.074
Neg logit contributions
rum-0.185
ud-0.166
Jo-0.164
and-0.156
rd-0.155
Token the
Token ID262
Feature activation+5.07e-01

Pos logit contributions
+0.047
idents+0.044
 sack+0.044
 cooler+0.043
 prett+0.040
Neg logit contributions
Jo-0.071
rum-0.070
ud-0.066
jo-0.063
 Pen-0.059