TOP ACTIVATIONS
MAX = 6.834

chains , glitter y snow fl akes , and a picture
It was covered with cob we bs and the paint was
They looked more closely and sure enough , there
took a seat and looked int ently at the chess board
ahead . She looked more closely and saw that it was
and send soft white snow fl akes into the sky .
She looked a bit closer and suddenly saw what she
huge garden filled with wild fl owers and trees !
the floor . She looked closer and saw that it was
The little girl looked closer and saw an old fox
the cave . She looked closer and saw a pink flower
the water . He looked closer and it was a diamond
ol anda took the sun fl owers and went back out
something funny . She looked closely and saw that it was
ks . It was a gru ff voice and it said
the biggest and brightest sun fl owers she could find .
the bushes . She looked closer and saw that her bag
tall grass . She looked closer and discovered it was a
red button . He looked closer and found a label that
Jimmy looked closer and asked , " What

MIN ACTIVATIONS
MIN = -7.730

friendship . When my wing heals , I will take you
your friendship . When my wing heals , I will take
Max felt helpless when his wing was injured . He couldn
in his nest until his wing got better .
couldn 't fly until his wing was healed . He had
it for us when she died . It had her most
care of it until its wing was better . The little
care of it until its wing healed . A
could not recover and eventually died due to the damage caused
share . We hope your wing will heal soon ," Sara
and find out why it died ." The teacher
a nail to help his wing heal ."
and find out why it died ." So Jim
it to me before he died . He said it was
what would happen when her tooth finally fell out . "
few days until his ankle healed . He felt sad not
became very weak and eventually died . The sad
is not happy when you hurt it . How about we
it to me before he died . I value it very
bug couldn 't survive and died . Tim my felt very

INTERVAL 3.193 - 6.834
CONTAINS 0.740%

where she was . He waited and waited .
The dog looked at him for a few seconds
amazing . Let 's go closer and take a better look
€ � � It â € ™ s okay , it
to grow . This made Jack very frustrated ! He asked

INTERVAL -0.448 - 3.193
CONTAINS 65.595%

proud of her for being brave and honest . They said
started running as fast as they could . As
boy named Tim my . Tim my had a tutor named
are happy and quiet . The old lady is
. She couldn 't wait to sing with Max again tomorrow

INTERVAL -4.089 - -0.448
CONTAINS 33.415%

in the oven . When it was done , it took
!" said her cat , Mitt ens . "
. â € � � Oh no ! â
to find a way to get home . She smiled and
, but the dog wouldn 't leave him alone .

INTERVAL -7.730 - -4.089
CONTAINS 0.250%

" Really ? Do you still want to play with me
being extra careful not to hurt it . Tad found a
" Can we still go to the park ?"
his mom 's love would never be harsh . <|endoftext|> Once
him , fascinated by how much fun he was having .
Token chains
Token ID14659
Feature activation+6.92e-01

Pos logit contributions
atively+0.035
agg+0.032
ya+0.032
eways+0.031
overed+0.031
Neg logit contributions
 Wh-0.017
 Snow-0.015
 still-0.014
 Teddy-0.013
 Brown-0.013
Token,
Token ID11
Feature activation+1.65e+00

Pos logit contributions
atively+0.048
agg+0.044
overed+0.043
eways+0.043
ya+0.042
Neg logit contributions
 Wh-0.024
 Snow-0.023
 Teddy-0.021
 still-0.020
 Brown-0.020
Token glitter
Token ID31133
Feature activation+2.85e-01

Pos logit contributions
atively+0.098
agg+0.092
ya+0.091
eways+0.088
overed+0.086
Neg logit contributions
 Wh-0.072
 Snow-0.069
 still-0.064
 Brown-0.064
 Teddy-0.063
Tokeny
Token ID88
Feature activation+9.62e-01

Pos logit contributions
atively+0.021
agg+0.020
ya+0.019
eways+0.019
overed+0.019
Neg logit contributions
 Wh-0.009
 Snow-0.008
 still-0.007
 Brown-0.007
 Teddy-0.007
Token snow
Token ID6729
Feature activation+4.58e-01

Pos logit contributions
atively+0.065
agg+0.061
ya+0.061
eways+0.059
overed+0.058
Neg logit contributions
 Wh-0.035
 Snow-0.033
 still-0.030
 Brown-0.030
 Teddy-0.030
Tokenfl
Token ID2704
Feature activation+6.48e+00

Pos logit contributions
atively+0.028
agg+0.025
overed+0.024
eways+0.024
ya+0.024
Neg logit contributions
 Wh-0.020
 Snow-0.018
 still-0.018
 Teddy-0.017
 Mitt-0.017
Tokenakes
Token ID1124
Feature activation+4.23e-01

Pos logit contributions
atively+0.277
agg+0.252
overed+0.236
aded+0.233
eways+0.232
Neg logit contributions
 Wh-0.393
 Snow-0.380
 still-0.364
 Teddy-0.357
 Brown-0.353
Token,
Token ID11
Feature activation+1.60e+00

Pos logit contributions
atively+0.031
agg+0.029
ya+0.028
overed+0.028
eways+0.028
Neg logit contributions
 Wh-0.013
 Snow-0.012
 Teddy-0.010
 Brown-0.010
 Mitt-0.010
Token and
Token ID290
Feature activation+3.46e-01

Pos logit contributions
atively+0.121
agg+0.115
ya+0.114
eways+0.111
overed+0.110
Neg logit contributions
 Wh-0.046
 Snow-0.042
 still-0.037
 Brown-0.037
 Teddy-0.037
Token a
Token ID257
Feature activation+9.08e-01

Pos logit contributions
atively+0.022
agg+0.021
ya+0.020
eways+0.020
aded+0.019
Neg logit contributions
 Wh-0.014
 Snow-0.013
 still-0.012
 Brown-0.012
 Teddy-0.012
Token picture
Token ID4286
Feature activation-1.01e+00

Pos logit contributions
atively+0.057
agg+0.054
ya+0.054
eways+0.050
 arom+0.050
Neg logit contributions
 Wh-0.036
 Snow-0.034
 Brown-0.031
 still-0.031
 Teddy-0.031
Token It
Token ID632
Feature activation+1.09e+00

Pos logit contributions
atively+0.133
agg+0.128
ya+0.127
eways+0.123
aded+0.123
Neg logit contributions
 Wh-0.038
 Snow-0.033
 Brown-0.029
 Teddy-0.028
 still-0.028
Token was
Token ID373
Feature activation+1.01e+00

Pos logit contributions
atively+0.067
agg+0.059
ya+0.058
overed+0.058
eways+0.058
Neg logit contributions
 Wh-0.045
 Snow-0.043
."-0.040
 Teddy-0.038
 Brown-0.038
Token covered
Token ID5017
Feature activation-5.62e-01

Pos logit contributions
atively+0.065
overed+0.059
agg+0.058
eways+0.057
aded+0.056
Neg logit contributions
."-0.034
 Wh-0.033
 Snow-0.032
 Teddy-0.028
 Brown-0.026
Token with
Token ID351
Feature activation+3.12e+00

Pos logit contributions
 Wh+0.014
 Snow+0.013
 still+0.013
 Brown+0.012
 Teddy+0.011
Neg logit contributions
atively-0.044
agg-0.044
ya-0.043
aded-0.041
overed-0.040
Token cob
Token ID22843
Feature activation-8.97e-01

Pos logit contributions
atively+0.185
agg+0.172
ya+0.172
eways+0.169
 flavours+0.163
Neg logit contributions
 Wh-0.131
 Snow-0.125
 still-0.118
."-0.114
 Teddy-0.113
Tokenwe
Token ID732
Feature activation+6.23e+00

Pos logit contributions
 Wh+0.053
 Snow+0.052
 Brown+0.049
 still+0.049
 Teddy+0.048
Neg logit contributions
atively-0.041
agg-0.038
ya-0.037
aded-0.035
eways-0.034
Tokenbs
Token ID1443
Feature activation-2.01e+00

Pos logit contributions
atively+0.305
agg+0.283
ya+0.279
eways+0.273
aded+0.269
Neg logit contributions
 Wh-0.336
 Snow-0.324
 Brown-0.304
 still-0.302
 Teddy-0.300
Token and
Token ID290
Feature activation+1.28e+00

Pos logit contributions
 Wh+0.059
 Snow+0.054
 Mitt+0.045
 Teddy+0.045
 Brown+0.044
Neg logit contributions
atively-0.150
eways-0.139
overed-0.135
ya-0.135
agg-0.135
Token the
Token ID262
Feature activation+9.45e-01

Pos logit contributions
atively+0.085
agg+0.079
ya+0.078
eways+0.077
overed+0.075
Neg logit contributions
 Wh-0.047
 Snow-0.044
 still-0.040
."-0.040
 Teddy-0.039
Token paint
Token ID7521
Feature activation+6.72e-01

Pos logit contributions
atively+0.050
ya+0.044
eways+0.042
agg+0.042
 arom+0.041
Neg logit contributions
 Wh-0.048
 Snow-0.046
 still-0.042
 Teddy-0.042
 Mitt-0.042
Token was
Token ID373
Feature activation+6.51e-01

Pos logit contributions
atively+0.046
agg+0.042
eways+0.041
overed+0.041
ya+0.041
Neg logit contributions
 Wh-0.024
 Snow-0.023
 Teddy-0.021
 still-0.021
 Brown-0.021
Token
Token ID198
Feature activation+4.59e-02

Pos logit contributions
 Wh+0.001
 Snow+0.001
 Brown+0.001
 Teddy+0.001
 still+0.001
Neg logit contributions
atively-0.008
ya-0.008
agg-0.007
eways-0.007
aded-0.007
Token
Token ID198
Feature activation-9.82e-02

Pos logit contributions
atively+0.004
ya+0.004
agg+0.004
overed+0.004
eways+0.004
Neg logit contributions
 Wh-0.001
 Snow-0.001
 still-0.000
 Brown-0.000
 Teddy-0.000
TokenThey
Token ID2990
Feature activation+1.77e+00

Pos logit contributions
 still+0.004
 Wh+0.004
 never+0.004
 Snow+0.004
 now+0.004
Neg logit contributions
atively-0.006
ya-0.006
overed-0.005
 arom-0.005
ement-0.005
Token looked
Token ID3114
Feature activation+3.21e+00

Pos logit contributions
atively+0.123
agg+0.118
ya+0.116
eways+0.115
overed+0.113
Neg logit contributions
 Wh-0.060
 Snow-0.057
 still-0.055
 Teddy-0.052
 Brown-0.051
Token more
Token ID517
Feature activation+2.07e+00

Pos logit contributions
atively+0.236
agg+0.229
eways+0.220
ya+0.219
aded+0.217
Neg logit contributions
 still-0.095
 Wh-0.095
 Snow-0.091
 Teddy-0.085
 Brown-0.081
Token closely
Token ID7173
Feature activation+6.20e+00

Pos logit contributions
atively+0.174
agg+0.163
ya+0.160
eways+0.160
overed+0.157
Neg logit contributions
 still-0.043
 Wh-0.039
 Snow-0.037
."-0.035
 hurt-0.032
Token and
Token ID290
Feature activation+1.88e+00

Pos logit contributions
agg+0.561
atively+0.557
aded+0.543
ya+0.535
mber+0.533
Neg logit contributions
 still-0.077
 too-0.063
 because-0.063
 all-0.059
 Snow-0.051
Token sure
Token ID1654
Feature activation+3.03e+00

Pos logit contributions
atively+0.142
agg+0.137
eways+0.137
eway+0.135
ades+0.132
Neg logit contributions
 still-0.062
 Wh-0.052
 Lily-0.050
 all-0.048
 Snow-0.047
Token enough
Token ID1576
Feature activation-1.14e+00

Pos logit contributions
atively+0.228
ya+0.213
agg+0.212
eways+0.210
overed+0.206
Neg logit contributions
 Wh-0.085
 Snow-0.082
 still-0.081
 Brown-0.072
 Teddy-0.070
Token,
Token ID11
Feature activation+3.99e-01

Pos logit contributions
 Wh+0.020
 Snow+0.018
 still+0.017
 Teddy+0.016
 Brown+0.015
Neg logit contributions
atively-0.100
ya-0.095
agg-0.095
overed-0.094
aded-0.093
Token there
Token ID612
Feature activation+1.66e+00

Pos logit contributions
atively+0.032
agg+0.030
ya+0.030
ued+0.029
eways+0.029
Neg logit contributions
 still-0.010
 Wh-0.010
 all-0.010
 Snow-0.010
 because-0.009
Token took
Token ID1718
Feature activation+1.71e+00

Pos logit contributions
atively+0.074
agg+0.071
ya+0.069
eways+0.068
overed+0.068
Neg logit contributions
 Wh-0.032
 Snow-0.030
 still-0.028
 Teddy-0.027
 Brown-0.026
Token a
Token ID257
Feature activation+1.60e+00

Pos logit contributions
atively+0.105
agg+0.098
ya+0.097
overed+0.094
eways+0.093
Neg logit contributions
 Wh-0.079
 Snow-0.077
 Teddy-0.076
 Brown-0.075
 all-0.072
Token seat
Token ID5852
Feature activation+2.60e-01

Pos logit contributions
atively+0.119
agg+0.117
overed+0.111
ya+0.111
aded+0.110
Neg logit contributions
 Wh-0.047
 Snow-0.045
 Teddy-0.044
 still-0.041
 Brown-0.040
Token and
Token ID290
Feature activation+1.14e+00

Pos logit contributions
atively+0.021
agg+0.020
ya+0.020
aded+0.020
eways+0.020
Neg logit contributions
 Wh-0.006
 Snow-0.006
 still-0.005
 Brown-0.005
 Teddy-0.005
Token looked
Token ID3114
Feature activation+1.87e+00

Pos logit contributions
atively+0.077
agg+0.074
ya+0.072
eways+0.072
overed+0.070
Neg logit contributions
 Wh-0.042
 Snow-0.041
 Teddy-0.038
 still-0.037
 Brown-0.037
Token int
Token ID493
Feature activation+6.11e+00

Pos logit contributions
atively+0.143
agg+0.141
aded+0.133
ya+0.132
eways+0.132
Neg logit contributions
 Wh-0.048
 still-0.047
 Snow-0.045
."-0.044
 Teddy-0.043
Tokenently
Token ID1473
Feature activation+9.66e-01

Pos logit contributions
atively+0.152
ya+0.149
agg+0.127
 arom+0.123
 traders+0.120
Neg logit contributions
 Wh-0.453
."-0.448
 still-0.447
 Snow-0.444
 Teddy-0.431
Token at
Token ID379
Feature activation+2.34e+00

Pos logit contributions
atively+0.083
agg+0.082
eways+0.078
ya+0.078
aded+0.078
Neg logit contributions
 still-0.017
."-0.015
 Snow-0.015
 Wh-0.015
 Teddy-0.013
Token the
Token ID262
Feature activation-3.24e-01

Pos logit contributions
atively+0.179
agg+0.169
ya+0.169
eways+0.164
overed+0.161
Neg logit contributions
 Wh-0.066
 Snow-0.061
 still-0.052
 Teddy-0.051
 Brown-0.050
Token chess
Token ID19780
Feature activation+1.22e+00

Pos logit contributions
 Wh+0.015
 Snow+0.015
 Brown+0.014
 Teddy+0.013
 still+0.013
Neg logit contributions
atively-0.019
agg-0.017
ya-0.017
eways-0.017
overed-0.016
Token board
Token ID3096
Feature activation+1.03e+00

Pos logit contributions
agg+0.068
atively+0.067
ya+0.065
aded+0.062
eways+0.062
Neg logit contributions
 Wh-0.055
 Snow-0.053
 still-0.053
."-0.053
 Teddy-0.051
Token ahead
Token ID4058
Feature activation+2.69e+00

Pos logit contributions
atively+0.332
agg+0.319
ya+0.314
eways+0.307
aded+0.307
Neg logit contributions
 Wh-0.117
 Snow-0.111
 still-0.109
."-0.098
 Brown-0.095
Token.
Token ID13
Feature activation+1.99e-01

Pos logit contributions
atively+0.232
agg+0.223
ya+0.221
aded+0.216
overed+0.214
Neg logit contributions
 Wh-0.046
 Snow-0.043
 still-0.038
."-0.034
 Brown-0.034
Token She
Token ID1375
Feature activation-8.82e-01

Pos logit contributions
ya+0.017
aded+0.016
atively+0.016
agg+0.016
ering+0.016
Neg logit contributions
 Lily-0.004
 Wh-0.004
 Snow-0.003
 Brown-0.003
-0.003
Token looked
Token ID3114
Feature activation+2.77e+00

Pos logit contributions
 still+0.034
 Snow+0.033
 Wh+0.033
 Teddy+0.029
 Brown+0.029
Neg logit contributions
atively-0.058
eways-0.054
agg-0.053
ya-0.052
overed-0.052
Token more
Token ID517
Feature activation+1.63e+00

Pos logit contributions
atively+0.187
agg+0.180
aded+0.172
eways+0.171
ya+0.169
Neg logit contributions
 Wh-0.100
 Snow-0.099
 still-0.099
 Teddy-0.091
 Brown-0.089
Token closely
Token ID7173
Feature activation+5.99e+00

Pos logit contributions
atively+0.111
agg+0.106
ya+0.105
eways+0.102
overed+0.101
Neg logit contributions
 Wh-0.060
 Snow-0.056
 Brown-0.050
 Teddy-0.050
 still-0.049
Token and
Token ID290
Feature activation+1.59e+00

Pos logit contributions
atively+0.536
agg+0.535
aded+0.530
ya+0.511
 traders+0.509
Neg logit contributions
 still-0.071
 because-0.057
 Snow-0.056
."-0.055
 too-0.053
Token saw
Token ID2497
Feature activation+1.42e+00

Pos logit contributions
atively+0.109
agg+0.106
aded+0.105
eways+0.101
eway+0.101
Neg logit contributions
 still-0.058
 Wh-0.050
 Snow-0.049
 Lily-0.047
my-0.046
Token that
Token ID326
Feature activation-1.33e+00

Pos logit contributions
atively+0.113
agg+0.108
ya+0.106
aded+0.104
eways+0.103
Neg logit contributions
 Wh-0.036
 Snow-0.035
 Brown-0.030
 still-0.030
 Teddy-0.029
Token it
Token ID340
Feature activation+7.83e-01

Pos logit contributions
 Wh+0.035
 Snow+0.035
 still+0.033
 Brown+0.031
 Teddy+0.030
Neg logit contributions
atively-0.103
agg-0.098
aded-0.096
ya-0.096
eways-0.094
Token was
Token ID373
Feature activation+3.62e-02

Pos logit contributions
atively+0.059
agg+0.056
ya+0.056
eways+0.054
aded+0.054
Neg logit contributions
 Wh-0.023
 Snow-0.022
 still-0.020
 Brown-0.019
 Teddy-0.019
Token and
Token ID290
Feature activation-2.84e-01

Pos logit contributions
 Wh+0.043
 Snow+0.039
 Teddy+0.034
 Brown+0.033
 Mitt+0.030
Neg logit contributions
atively-0.127
agg-0.120
ya-0.118
overed-0.116
eways-0.115
Token send
Token ID3758
Feature activation-1.60e+00

Pos logit contributions
 Wh+0.012
 Snow+0.011
 Brown+0.010
 Teddy+0.010
."+0.010
Neg logit contributions
atively-0.018
agg-0.017
ya-0.017
aded-0.016
eways-0.016
Token soft
Token ID2705
Feature activation-2.11e+00

Pos logit contributions
 Wh+0.047
 Snow+0.046
 Brown+0.041
 Teddy+0.039
."+0.039
Neg logit contributions
atively-0.123
agg-0.116
ya-0.115
overed-0.112
eways-0.112
Token white
Token ID2330
Feature activation-1.05e+00

Pos logit contributions
 Snow+0.086
 Wh+0.080
."+0.077
 Brown+0.077
 Teddy+0.076
Neg logit contributions
atively-0.144
agg-0.132
ya-0.129
overed-0.128
Kevin-0.125
Token snow
Token ID6729
Feature activation-1.63e-01

Pos logit contributions
 Snow+0.044
 Wh+0.044
 Brown+0.041
."+0.040
 Teddy+0.039
Neg logit contributions
atively-0.068
agg-0.063
ya-0.062
overed-0.060
eways-0.059
Tokenfl
Token ID2704
Feature activation+5.97e+00

Pos logit contributions
 Wh+0.008
 Snow+0.007
 still+0.007
 Teddy+0.007
 Brown+0.007
Neg logit contributions
atively-0.009
agg-0.008
ya-0.008
eways-0.008
overed-0.008
Tokenakes
Token ID1124
Feature activation+1.78e-01

Pos logit contributions
atively+0.285
agg+0.266
eways+0.248
aded+0.248
ya+0.247
Neg logit contributions
 Wh-0.334
 Snow-0.321
 still-0.307
 Teddy-0.305
 Brown-0.299
Token into
Token ID656
Feature activation+8.99e-01

Pos logit contributions
atively+0.013
ya+0.012
agg+0.012
overed+0.012
eways+0.012
Neg logit contributions
 Wh-0.005
 Snow-0.004
 Teddy-0.004
 Mitt-0.004
 still-0.004
Token the
Token ID262
Feature activation+5.41e-01

Pos logit contributions
agg+0.058
atively+0.058
ya+0.056
eways+0.056
aded+0.055
Neg logit contributions
 Wh-0.030
 Snow-0.027
 still-0.026
 Teddy-0.024
 Brown-0.024
Token sky
Token ID6766
Feature activation-3.14e-01

Pos logit contributions
atively+0.036
agg+0.034
ya+0.033
eways+0.032
aded+0.032
Neg logit contributions
 Wh-0.021
 Snow-0.019
 Brown-0.017
 Teddy-0.017
 still-0.017
Token.
Token ID13
Feature activation+3.24e-01

Pos logit contributions
 Wh+0.009
 Snow+0.008
 Teddy+0.007
 Brown+0.007
 Mitt+0.007
Neg logit contributions
atively-0.023
agg-0.022
ya-0.022
eways-0.022
overed-0.021
Token
Token ID198
Feature activation-3.83e-01

Pos logit contributions
 Wh+0.004
 Snow+0.004
 Brown+0.003
 still+0.003
 Teddy+0.003
Neg logit contributions
atively-0.016
agg-0.015
ya-0.015
eways-0.014
overed-0.014
TokenShe
Token ID3347
Feature activation-1.26e+00

Pos logit contributions
 Wh+0.017
 Snow+0.017
 still+0.016
 Brown+0.015
 Teddy+0.015
Neg logit contributions
atively-0.023
agg-0.021
ya-0.021
eways-0.020
overed-0.020
Token looked
Token ID3114
Feature activation+2.74e+00

Pos logit contributions
 Wh+0.047
 Snow+0.046
 still+0.044
 Brown+0.041
 Teddy+0.041
Neg logit contributions
atively-0.083
agg-0.078
eways-0.077
ya-0.077
overed-0.075
Token a
Token ID257
Feature activation+3.80e+00

Pos logit contributions
atively+0.197
agg+0.194
eways+0.185
aded+0.185
ya+0.183
Neg logit contributions
 still-0.085
 Wh-0.079
 Snow-0.077
 Teddy-0.075
 all-0.071
Token bit
Token ID1643
Feature activation+1.52e+00

Pos logit contributions
atively+0.241
agg+0.227
ya+0.223
eways+0.218
overed+0.216
Neg logit contributions
 Wh-0.155
 Snow-0.148
 still-0.138
 Brown-0.136
 Teddy-0.135
Token closer
Token ID5699
Feature activation+5.96e+00

Pos logit contributions
atively+0.109
agg+0.104
ya+0.102
eways+0.101
overed+0.099
Neg logit contributions
 Wh-0.049
 Snow-0.046
 still-0.045
 Teddy-0.042
."-0.041
Token and
Token ID290
Feature activation+2.05e-01

Pos logit contributions
atively+0.489
agg+0.475
ya+0.464
aded+0.461
eways+0.456
Neg logit contributions
 Wh-0.120
 Snow-0.115
 still-0.108
 Brown-0.099
."-0.098
Token suddenly
Token ID6451
Feature activation-3.72e-01

Pos logit contributions
eways+0.014
atively+0.014
agg+0.013
aded+0.013
eway+0.013
Neg logit contributions
 still-0.008
 Wh-0.007
 Snow-0.007
 Lily-0.006
 Teddy-0.006
Token saw
Token ID2497
Feature activation+9.60e-01

Pos logit contributions
 Wh+0.011
 Snow+0.011
 still+0.010
 Teddy+0.010
 Brown+0.010
Neg logit contributions
atively-0.027
agg-0.026
ya-0.026
eways-0.025
aded-0.025
Token what
Token ID644
Feature activation+2.01e+00

Pos logit contributions
atively+0.072
agg+0.069
ya+0.068
eways+0.066
aded+0.066
Neg logit contributions
 Wh-0.029
 Snow-0.027
 Brown-0.024
 still-0.024
 Teddy-0.024
Token she
Token ID673
Feature activation-1.54e+00

Pos logit contributions
atively+0.154
agg+0.146
ya+0.143
aded+0.142
overed+0.141
Neg logit contributions
 Wh-0.058
 Snow-0.053
 still-0.051
 Teddy-0.048
 Brown-0.048
Token huge
Token ID3236
Feature activation+3.10e-01

Pos logit contributions
atively+0.076
agg+0.072
ya+0.071
eways+0.069
overed+0.068
Neg logit contributions
 Wh-0.046
 Snow-0.044
 still-0.040
 Brown-0.040
 Teddy-0.040
Token garden
Token ID11376
Feature activation+1.29e-01

Pos logit contributions
atively+0.020
agg+0.019
eways+0.018
ya+0.018
aded+0.018
Neg logit contributions
 Wh-0.013
 Snow-0.012
 still-0.011
 Brown-0.011
 Teddy-0.011
Token filled
Token ID5901
Feature activation+3.59e-01

Pos logit contributions
atively+0.010
agg+0.010
ya+0.009
aded+0.009
eways+0.009
Neg logit contributions
 Wh-0.003
 Snow-0.003
 still-0.003
 Brown-0.003
."-0.003
Token with
Token ID351
Feature activation+3.21e+00

Pos logit contributions
atively+0.032
agg+0.031
aded+0.030
ya+0.030
overed+0.029
Neg logit contributions
 still-0.005
 Wh-0.005
."-0.005
 Snow-0.004
 all-0.004
Token wild
Token ID4295
Feature activation+7.27e-01

Pos logit contributions
atively+0.214
agg+0.199
ya+0.196
overed+0.195
aded+0.192
Neg logit contributions
 Wh-0.121
 Snow-0.119
 still-0.111
 Brown-0.109
 Teddy-0.107
Tokenfl
Token ID2704
Feature activation+5.94e+00

Pos logit contributions
atively+0.050
agg+0.046
overed+0.045
Kevin+0.045
aded+0.045
Neg logit contributions
 Snow-0.027
."-0.026
 Wh-0.025
 Brown-0.025
 all-0.022
Tokenowers
Token ID3618
Feature activation+1.00e+00

Pos logit contributions
atively+0.195
ya+0.182
agg+0.169
eways+0.156
overed+0.150
Neg logit contributions
 Wh-0.415
 Snow-0.408
 Brown-0.396
 still-0.390
."-0.389
Token and
Token ID290
Feature activation+1.26e+00

Pos logit contributions
atively+0.080
agg+0.077
ya+0.076
eways+0.074
overed+0.073
Neg logit contributions
 Wh-0.025
 Snow-0.022
 Teddy-0.019
 Brown-0.019
 still-0.018
Token trees
Token ID7150
Feature activation-8.69e-01

Pos logit contributions
atively+0.080
agg+0.075
ya+0.074
eways+0.072
overed+0.072
Neg logit contributions
 Wh-0.052
 Snow-0.050
 still-0.046
 Brown-0.046
 Teddy-0.045
Token!
Token ID0
Feature activation+1.16e+00

Pos logit contributions
 Wh+0.022
 Snow+0.020
 Teddy+0.018
 Brown+0.017
 Mitt+0.016
Neg logit contributions
atively-0.068
agg-0.064
ya-0.063
eways-0.063
overed-0.063
Token
Token ID198
Feature activation-1.78e-01

Pos logit contributions
atively+0.081
agg+0.077
ya+0.075
overed+0.073
eways+0.073
Neg logit contributions
 Wh-0.038
 Snow-0.035
 still-0.034
 ruined-0.033
 hurt-0.032
Token the
Token ID262
Feature activation+3.10e-01

Pos logit contributions
 Wh+0.003
 Snow+0.003
 still+0.002
 Brown+0.002
 Teddy+0.002
Neg logit contributions
atively-0.010
agg-0.010
ya-0.010
eways-0.010
overed-0.010
Token floor
Token ID4314
Feature activation-9.89e-01

Pos logit contributions
atively+0.018
agg+0.018
overed+0.017
aded+0.017
eways+0.017
Neg logit contributions
 Wh-0.014
 Snow-0.014
 still-0.013
 Brown-0.013
."-0.013
Token.
Token ID13
Feature activation+2.15e-01

Pos logit contributions
 Wh+0.015
 Snow+0.013
 still+0.011
 Brown+0.010
."+0.010
Neg logit contributions
atively-0.087
agg-0.084
ya-0.083
eways-0.081
aded-0.081
Token She
Token ID1375
Feature activation-7.90e-01

Pos logit contributions
atively+0.018
ya+0.017
eways+0.017
agg+0.017
aded+0.017
Neg logit contributions
 Wh-0.004
 Snow-0.004
 still-0.003
 Teddy-0.003
."-0.003
Token looked
Token ID3114
Feature activation+3.12e+00

Pos logit contributions
 Wh+0.027
 Snow+0.026
 still+0.025
 Teddy+0.024
 Brown+0.024
Neg logit contributions
atively-0.055
agg-0.052
eways-0.052
ya-0.051
overed-0.050
Token closer
Token ID5699
Feature activation+5.91e+00

Pos logit contributions
atively+0.243
agg+0.236
eways+0.226
aded+0.222
overed+0.219
Neg logit contributions
 still-0.087
 Wh-0.087
 Snow-0.083
 Teddy-0.080
 Brown-0.075
Token and
Token ID290
Feature activation+1.68e-01

Pos logit contributions
atively+0.520
agg+0.512
aded+0.507
eways+0.497
ya+0.489
Neg logit contributions
 still-0.085
 Snow-0.076
 Wh-0.070
."-0.069
 too-0.061
Token saw
Token ID2497
Feature activation+1.36e+00

Pos logit contributions
atively+0.012
eways+0.012
aded+0.012
agg+0.012
eway+0.012
Neg logit contributions
 still-0.005
 Snow-0.005
 Wh-0.005
 Teddy-0.005
 Lily-0.005
Token that
Token ID326
Feature activation-1.27e+00

Pos logit contributions
atively+0.108
agg+0.103
ya+0.101
aded+0.100
eways+0.100
Neg logit contributions
 Wh-0.035
 Snow-0.034
 Brown-0.030
 Teddy-0.029
 still-0.028
Token it
Token ID340
Feature activation+7.38e-01

Pos logit contributions
 Wh+0.033
 Snow+0.032
 still+0.029
 Brown+0.028
 Teddy+0.028
Neg logit contributions
atively-0.100
agg-0.095
ya-0.093
aded-0.092
eways-0.092
Token was
Token ID373
Feature activation+1.05e-01

Pos logit contributions
atively+0.056
agg+0.054
ya+0.053
eways+0.052
aded+0.051
Neg logit contributions
 Wh-0.022
 Snow-0.020
 still-0.019
 Brown-0.018
 Teddy-0.018
Token
Token ID198
Feature activation-2.58e-01

Pos logit contributions
 Wh+0.004
 Snow+0.003
 still+0.003
 Brown+0.003
 Teddy+0.003
Neg logit contributions
atively-0.015
agg-0.014
ya-0.014
eways-0.013
overed-0.013
TokenThe
Token ID464
Feature activation-8.19e-01

Pos logit contributions
 Wh+0.009
 Snow+0.008
 still+0.008
."+0.007
 Brown+0.007
Neg logit contributions
atively-0.019
agg-0.017
overed-0.017
aded-0.017
ya-0.017
Token little
Token ID1310
Feature activation+6.07e-01

Pos logit contributions
 Snow+0.024
 Wh+0.024
 Brown+0.022
 still+0.022
 Teddy+0.022
Neg logit contributions
atively-0.061
agg-0.059
overed-0.058
eways-0.058
ya-0.057
Token girl
Token ID2576
Feature activation+9.76e-01

Pos logit contributions
atively+0.041
agg+0.039
eways+0.039
aded+0.039
overed+0.038
Neg logit contributions
 Wh-0.023
 Snow-0.023
 Lily-0.021
 Teddy-0.021
 Brown-0.021
Token looked
Token ID3114
Feature activation+2.44e+00

Pos logit contributions
atively+0.065
eways+0.064
agg+0.061
ya+0.060
eway+0.060
Neg logit contributions
 still-0.037
 Wh-0.036
 Snow-0.035
 Brown-0.032
 Teddy-0.032
Token closer
Token ID5699
Feature activation+5.90e+00

Pos logit contributions
atively+0.160
agg+0.153
ya+0.146
eways+0.146
aded+0.145
Neg logit contributions
 Wh-0.094
 Snow-0.092
 still-0.090
 Teddy-0.085
 Brown-0.084
Token and
Token ID290
Feature activation+3.35e-01

Pos logit contributions
atively+0.530
agg+0.524
aded+0.520
eways+0.511
ya+0.504
Neg logit contributions
 still-0.079
 Snow-0.064
 too-0.063
."-0.056
 because-0.054
Token saw
Token ID2497
Feature activation+1.20e+00

Pos logit contributions
atively+0.024
eways+0.023
 flavours+0.023
agg+0.023
aded+0.023
Neg logit contributions
 still-0.011
 Snow-0.011
 Wh-0.011
 Teddy-0.010
 Lily-0.010
Token an
Token ID281
Feature activation+2.44e+00

Pos logit contributions
atively+0.094
agg+0.090
ya+0.089
eways+0.087
overed+0.086
Neg logit contributions
 Wh-0.032
 Snow-0.030
 still-0.026
 Brown-0.026
 Teddy-0.026
Token old
Token ID1468
Feature activation-6.58e-01

Pos logit contributions
atively+0.157
agg+0.148
ya+0.145
eways+0.141
overed+0.140
Neg logit contributions
 Wh-0.097
 Snow-0.093
 still-0.085
 Brown-0.085
 Teddy-0.084
Token fox
Token ID21831
Feature activation+1.75e-01

Pos logit contributions
 Wh+0.026
 Snow+0.025
 still+0.023
 Brown+0.023
 Teddy+0.023
Neg logit contributions
atively-0.042
agg-0.040
ya-0.039
eways-0.038
aded-0.038
Token the
Token ID262
Feature activation+1.25e+00

Pos logit contributions
atively+0.258
agg+0.247
ya+0.244
eways+0.238
aded+0.236
Neg logit contributions
 Wh-0.081
 Snow-0.076
 still-0.066
 Brown-0.065
 Teddy-0.063
Token cave
Token ID11527
Feature activation-4.46e-01

Pos logit contributions
atively+0.072
agg+0.064
ya+0.063
eways+0.063
aded+0.060
Neg logit contributions
 Wh-0.062
 Snow-0.057
 Teddy-0.054
 Mitt-0.053
 Brown-0.052
Token.
Token ID13
Feature activation+3.73e-01

Pos logit contributions
 Wh+0.008
 Snow+0.008
 Brown+0.006
 Teddy+0.006
 still+0.006
Neg logit contributions
atively-0.038
agg-0.036
ya-0.036
eways-0.035
overed-0.035
Token She
Token ID1375
Feature activation-7.42e-01

Pos logit contributions
atively+0.028
agg+0.027
ya+0.026
aded+0.026
eways+0.026
Neg logit contributions
 Wh-0.011
 Snow-0.011
 Brown-0.010
 Teddy-0.009
 still-0.009
Token looked
Token ID3114
Feature activation+2.84e+00

Pos logit contributions
 Wh+0.027
 Snow+0.026
 still+0.026
 Brown+0.024
 Teddy+0.023
Neg logit contributions
atively-0.051
agg-0.048
eways-0.047
ya-0.047
overed-0.046
Token closer
Token ID5699
Feature activation+5.90e+00

Pos logit contributions
atively+0.202
agg+0.196
ya+0.187
aded+0.186
eways+0.186
Neg logit contributions
 Wh-0.094
 Snow-0.090
 still-0.089
 Brown-0.082
 Teddy-0.082
Token and
Token ID290
Feature activation+2.71e-01

Pos logit contributions
atively+0.499
agg+0.485
aded+0.474
ya+0.471
eways+0.468
Neg logit contributions
 Wh-0.104
 Snow-0.102
 still-0.098
."-0.087
 Brown-0.084
Token saw
Token ID2497
Feature activation+1.50e+00

Pos logit contributions
atively+0.020
agg+0.019
aded+0.019
eways+0.019
 flavours+0.019
Neg logit contributions
 still-0.008
 Snow-0.008
 Wh-0.008
 Teddy-0.007
 Lily-0.007
Token a
Token ID257
Feature activation+1.34e+00

Pos logit contributions
atively+0.111
agg+0.106
ya+0.104
eways+0.102
overed+0.102
Neg logit contributions
 Wh-0.044
 Snow-0.040
 still-0.036
 Teddy-0.035
."-0.035
Token pink
Token ID11398
Feature activation-2.53e-01

Pos logit contributions
atively+0.089
agg+0.084
ya+0.084
eways+0.081
overed+0.080
Neg logit contributions
 Wh-0.050
 Snow-0.046
 still-0.042
 Teddy-0.042
 Brown-0.042
Token flower
Token ID15061
Feature activation-6.61e-02

Pos logit contributions
 Wh+0.010
 Snow+0.009
 still+0.008
 Teddy+0.008
 Brown+0.008
Neg logit contributions
atively-0.017
agg-0.016
ya-0.015
overed-0.015
eways-0.015
Token the
Token ID262
Feature activation+2.75e-01

Pos logit contributions
atively+0.160
agg+0.154
ya+0.153
eways+0.150
aded+0.145
Neg logit contributions
 Wh-0.056
 Snow-0.049
 still-0.044
 Brown-0.043
 Teddy-0.042
Token water
Token ID1660
Feature activation-1.75e+00

Pos logit contributions
atively+0.017
agg+0.016
ya+0.016
eways+0.016
overed+0.016
Neg logit contributions
 Wh-0.011
 Snow-0.011
 still-0.010
 Brown-0.010
 Teddy-0.010
Token.
Token ID13
Feature activation+1.24e-01

Pos logit contributions
 Wh+0.039
 Snow+0.034
 Brown+0.029
 Teddy+0.028
 still+0.028
Neg logit contributions
atively-0.145
agg-0.136
ya-0.135
eways-0.134
overed-0.133
Token He
Token ID679
Feature activation+7.33e-01

Pos logit contributions
atively+0.010
agg+0.009
ya+0.009
eways+0.009
aded+0.009
Neg logit contributions
 Wh-0.004
 Snow-0.003
 Brown-0.003
 Teddy-0.003
 still-0.003
Token looked
Token ID3114
Feature activation+2.90e+00

Pos logit contributions
atively+0.050
agg+0.046
eways+0.046
ya+0.046
overed+0.045
Neg logit contributions
 Wh-0.027
 Snow-0.027
 still-0.026
 Teddy-0.024
 Brown-0.023
Token closer
Token ID5699
Feature activation+5.89e+00

Pos logit contributions
atively+0.179
agg+0.171
ya+0.164
eways+0.162
aded+0.161
Neg logit contributions
 Wh-0.123
 Snow-0.120
 still-0.116
 Teddy-0.111
 Brown-0.110
Token and
Token ID290
Feature activation+1.42e-01

Pos logit contributions
atively+0.517
agg+0.507
aded+0.500
eways+0.492
ya+0.488
Neg logit contributions
 still-0.085
 Snow-0.078
 Wh-0.073
."-0.068
 too-0.060
Token it
Token ID340
Feature activation+1.42e+00

Pos logit contributions
atively+0.010
eways+0.010
agg+0.010
aded+0.010
 flavours+0.010
Neg logit contributions
 still-0.005
 Snow-0.005
 Wh-0.004
 Teddy-0.004
 Lily-0.004
Token was
Token ID373
Feature activation+3.44e-01

Pos logit contributions
atively+0.101
agg+0.097
ya+0.096
eways+0.094
overed+0.092
Neg logit contributions
 Wh-0.047
 Snow-0.045
 still-0.043
 Teddy-0.040
 Brown-0.040
Token a
Token ID257
Feature activation+1.99e+00

Pos logit contributions
atively+0.023
agg+0.022
eways+0.021
aded+0.021
overed+0.021
Neg logit contributions
 Wh-0.012
 Snow-0.011
."-0.010
 Brown-0.010
 Teddy-0.010
Token diamond
Token ID15291
Feature activation-5.44e-01

Pos logit contributions
atively+0.131
agg+0.124
ya+0.123
eways+0.118
aded+0.117
Neg logit contributions
 Wh-0.076
 Snow-0.072
 still-0.065
 Brown-0.065
 Teddy-0.065
Tokenol
Token ID349
Feature activation-7.74e-01

Pos logit contributions
atively+0.113
ya+0.107
eways+0.107
Kevin+0.101
eway+0.101
Neg logit contributions
 Wh-0.109
 Snow-0.105
 still-0.100
my-0.098
 Brown-0.097
Tokenanda
Token ID5282
Feature activation-1.46e+00

Pos logit contributions
 Wh+0.036
 Snow+0.035
 still+0.032
 Brown+0.032
 Teddy+0.032
Neg logit contributions
atively-0.045
agg-0.041
eways-0.040
ya-0.040
overed-0.039
Token took
Token ID1718
Feature activation+9.57e-01

Pos logit contributions
 Wh+0.048
 Snow+0.046
 still+0.041
 Brown+0.041
 Teddy+0.040
Neg logit contributions
atively-0.104
agg-0.099
ya-0.097
eways-0.095
overed-0.094
Token the
Token ID262
Feature activation+1.02e+00

Pos logit contributions
atively+0.074
ya+0.069
agg+0.069
overed+0.068
eways+0.068
Neg logit contributions
 Wh-0.027
 Snow-0.026
 Brown-0.024
 still-0.022
 Teddy-0.022
Token sun
Token ID4252
Feature activation+3.93e-01

Pos logit contributions
atively+0.068
overed+0.063
agg+0.063
eways+0.062
aded+0.061
Neg logit contributions
 Wh-0.039
 Snow-0.038
 still-0.036
."-0.035
 Brown-0.035
Tokenfl
Token ID2704
Feature activation+5.88e+00

Pos logit contributions
atively+0.023
agg+0.021
ya+0.020
eways+0.020
overed+0.020
Neg logit contributions
 Wh-0.018
 Snow-0.017
 Teddy-0.016
 still-0.016
 Brown-0.016
Tokenowers
Token ID3618
Feature activation+8.89e-01

Pos logit contributions
atively+0.190
ya+0.168
agg+0.166
eways+0.156
overed+0.148
Neg logit contributions
 Wh-0.425
 Snow-0.414
 Brown-0.398
 still-0.395
 Teddy-0.390
Token and
Token ID290
Feature activation+5.42e-01

Pos logit contributions
atively+0.066
agg+0.063
ya+0.063
eways+0.061
overed+0.060
Neg logit contributions
 Wh-0.026
 Snow-0.024
 Brown-0.021
 Teddy-0.021
 still-0.021
Token went
Token ID1816
Feature activation-1.14e+00

Pos logit contributions
atively+0.037
agg+0.034
ya+0.034
eways+0.034
overed+0.033
Neg logit contributions
 Wh-0.020
 Snow-0.020
 still-0.018
 Brown-0.018
 Teddy-0.018
Token back
Token ID736
Feature activation-1.54e+00

Pos logit contributions
 Wh+0.039
 Snow+0.036
 Brown+0.032
 still+0.032
 Teddy+0.032
Neg logit contributions
atively-0.079
agg-0.075
ya-0.074
eways-0.072
aded-0.072
Token out
Token ID503
Feature activation+4.17e-01

Pos logit contributions
 Wh+0.053
 Snow+0.048
 still+0.044
 Teddy+0.043
 Brown+0.042
Neg logit contributions
atively-0.106
agg-0.102
ya-0.101
eways-0.098
aded-0.097
Token something
Token ID1223
Feature activation+3.07e+00

Pos logit contributions
atively+0.019
agg+0.018
ya+0.018
eways+0.017
overed+0.017
Neg logit contributions
 Wh-0.008
 Snow-0.007
 still-0.007
 Brown-0.007
 Teddy-0.007
Token funny
Token ID8258
Feature activation+1.94e+00

Pos logit contributions
atively+0.230
agg+0.224
ya+0.217
aded+0.209
eways+0.208
Neg logit contributions
 Wh-0.093
 still-0.093
 Snow-0.089
 hurt-0.086
 Teddy-0.081
Token.
Token ID13
Feature activation-3.05e-01

Pos logit contributions
agg+0.178
atively+0.177
ya+0.173
Kevin+0.167
aded+0.165
Neg logit contributions
 Snow-0.022
 Wh-0.021
 because-0.019
 too-0.018
 still-0.016
Token She
Token ID1375
Feature activation-8.85e-01

Pos logit contributions
 Wh+0.007
 Snow+0.007
 Teddy+0.006
 Brown+0.006
 Mitt+0.006
Neg logit contributions
atively-0.025
agg-0.024
ya-0.024
aded-0.023
eways-0.023
Token looked
Token ID3114
Feature activation+3.14e+00

Pos logit contributions
 Wh+0.032
 Snow+0.031
 still+0.030
 Teddy+0.028
 Brown+0.028
Neg logit contributions
atively-0.061
agg-0.056
eways-0.056
overed-0.055
ya-0.055
Token closely
Token ID7173
Feature activation+5.87e+00

Pos logit contributions
atively+0.229
agg+0.220
ya+0.212
eways+0.210
aded+0.208
Neg logit contributions
 Wh-0.100
 Snow-0.096
 still-0.092
 Teddy-0.087
 Brown-0.085
Token and
Token ID290
Feature activation+1.68e+00

Pos logit contributions
atively+0.531
agg+0.523
aded+0.514
eways+0.507
eway+0.504
Neg logit contributions
 still-0.073
 Snow-0.069
."-0.056
 Wh-0.056
 because-0.052
Token saw
Token ID2497
Feature activation+1.51e+00

Pos logit contributions
atively+0.113
agg+0.107
eways+0.104
aded+0.103
ya+0.103
Neg logit contributions
 Wh-0.064
 Snow-0.062
 still-0.060
 Teddy-0.058
 Brown-0.056
Token that
Token ID326
Feature activation-1.14e+00

Pos logit contributions
atively+0.114
agg+0.109
ya+0.107
eways+0.105
overed+0.104
Neg logit contributions
 Wh-0.044
 Snow-0.041
 still-0.036
 Brown-0.036
 Teddy-0.035
Token it
Token ID340
Feature activation+9.21e-01

Pos logit contributions
 Wh+0.040
 Snow+0.037
 still+0.034
 Brown+0.033
 Teddy+0.033
Neg logit contributions
atively-0.078
agg-0.074
ya-0.074
eways-0.072
overed-0.071
Token was
Token ID373
Feature activation+2.06e-01

Pos logit contributions
atively+0.067
agg+0.064
ya+0.063
eways+0.061
overed+0.061
Neg logit contributions
 Wh-0.029
 Snow-0.028
 still-0.025
 Brown-0.025
 Teddy-0.024
Tokenks
Token ID591
Feature activation+4.89e-01

Pos logit contributions
agg+0.130
atively+0.130
ya+0.128
aded+0.124
eways+0.123
Neg logit contributions
 Wh-0.017
 Snow-0.014
 still-0.012
."-0.010
 Brown-0.009
Token.
Token ID13
Feature activation-9.09e-03

Pos logit contributions
atively+0.044
agg+0.043
ya+0.043
 flavours+0.041
aded+0.041
Neg logit contributions
 Snow-0.006
 Wh-0.006
."-0.005
 still-0.005
 Teddy-0.004
Token It
Token ID632
Feature activation+5.69e-01

Pos logit contributions
 Wh+0.000
 Snow+0.000
 Brown+0.000
 Teddy+0.000
 still+0.000
Neg logit contributions
atively-0.001
agg-0.001
ya-0.001
aded-0.001
eways-0.001
Token was
Token ID373
Feature activation+6.00e-01

Pos logit contributions
atively+0.039
agg+0.037
ya+0.036
eways+0.035
overed+0.035
Neg logit contributions
 Wh-0.020
 Snow-0.019
 Teddy-0.017
 Brown-0.017
 still-0.017
Token a
Token ID257
Feature activation+2.05e+00

Pos logit contributions
atively+0.043
agg+0.042
ya+0.041
eways+0.040
aded+0.039
Neg logit contributions
 Wh-0.017
 Snow-0.016
."-0.015
 still-0.015
 Brown-0.014
Token gru
Token ID22848
Feature activation+5.87e+00

Pos logit contributions
atively+0.133
agg+0.126
ya+0.124
eways+0.121
overed+0.120
Neg logit contributions
 Wh-0.081
 Snow-0.077
 still-0.070
 Brown-0.070
 Teddy-0.069
Tokenff
Token ID487
Feature activation+1.64e+00

Pos logit contributions
atively+0.259
agg+0.220
overed+0.217
ya+0.215
eways+0.208
Neg logit contributions
 Wh-0.363
 Snow-0.352
 Brown-0.336
."-0.329
 still-0.328
Token voice
Token ID3809
Feature activation+2.24e+00

Pos logit contributions
atively+0.096
agg+0.093
eways+0.091
aded+0.089
overed+0.089
Neg logit contributions
 Snow-0.073
 Wh-0.071
 Brown-0.068
."-0.065
 hurt-0.065
Token and
Token ID290
Feature activation+7.88e-01

Pos logit contributions
atively+0.174
agg+0.170
eways+0.161
aded+0.161
ya+0.161
Neg logit contributions
 Wh-0.063
 Snow-0.060
 still-0.055
 Brown-0.054
."-0.052
Token it
Token ID340
Feature activation+1.28e+00

Pos logit contributions
atively+0.054
agg+0.051
ya+0.050
eways+0.049
overed+0.049
Neg logit contributions
 Wh-0.028
 Snow-0.027
 still-0.024
 Brown-0.024
 Teddy-0.024
Token said
Token ID531
Feature activation+5.73e-01

Pos logit contributions
atively+0.084
agg+0.079
ya+0.078
eways+0.075
overed+0.075
Neg logit contributions
 Wh-0.049
 Snow-0.046
 Brown-0.042
 Teddy-0.042
 still-0.041
Token the
Token ID262
Feature activation+4.02e-01

Pos logit contributions
 Wh+0.016
 Snow+0.015
 still+0.014
 Brown+0.013
 Teddy+0.013
Neg logit contributions
atively-0.035
agg-0.034
ya-0.033
eways-0.032
aded-0.032
Token biggest
Token ID4094
Feature activation+1.58e+00

Pos logit contributions
atively+0.025
agg+0.024
ya+0.024
eways+0.023
aded+0.022
Neg logit contributions
 Wh-0.017
 Snow-0.016
 Brown-0.015
 Teddy-0.015
 still-0.015
Token and
Token ID290
Feature activation+1.64e+00

Pos logit contributions
atively+0.106
agg+0.100
ya+0.098
eways+0.096
overed+0.095
Neg logit contributions
 Wh-0.059
 Snow-0.056
 still-0.052
 Brown-0.051
 Teddy-0.050
Token brightest
Token ID33871
Feature activation+1.27e+00

Pos logit contributions
atively+0.103
agg+0.095
overed+0.092
eways+0.092
aded+0.091
Neg logit contributions
 Wh-0.071
 Snow-0.069
 still-0.065
 Brown-0.064
 Teddy-0.064
Token sun
Token ID4252
Feature activation+2.84e-01

Pos logit contributions
atively+0.079
agg+0.075
ya+0.073
eways+0.071
overed+0.070
Neg logit contributions
 Wh-0.054
 Snow-0.051
 still-0.047
 Brown-0.047
 Teddy-0.047
Tokenfl
Token ID2704
Feature activation+5.86e+00

Pos logit contributions
atively+0.015
agg+0.014
ya+0.014
eways+0.013
overed+0.013
Neg logit contributions
 Wh-0.014
 Snow-0.014
 still-0.013
 Teddy-0.013
 Brown-0.013
Tokenowers
Token ID3618
Feature activation+6.78e-01

Pos logit contributions
atively+0.194
ya+0.173
agg+0.169
eways+0.158
overed+0.150
Neg logit contributions
 Wh-0.416
 Snow-0.406
 Brown-0.391
 still-0.389
."-0.385
Token she
Token ID673
Feature activation+3.16e-01

Pos logit contributions
atively+0.053
agg+0.051
ya+0.050
eways+0.049
overed+0.049
Neg logit contributions
 Wh-0.017
 Snow-0.016
 Brown-0.014
 Teddy-0.014
 still-0.014
Token could
Token ID714
Feature activation-2.33e+00

Pos logit contributions
atively+0.024
agg+0.023
ya+0.023
eways+0.022
overed+0.022
Neg logit contributions
 Wh-0.009
 Snow-0.009
 Brown-0.008
 Teddy-0.007
 still-0.007
Token find
Token ID1064
Feature activation+2.43e-01

Pos logit contributions
 Wh+0.093
 Snow+0.088
 Teddy+0.080
 Brown+0.080
 Mitt+0.075
Neg logit contributions
atively-0.154
agg-0.146
ya-0.139
aded-0.137
overed-0.137
Token.
Token ID13
Feature activation+2.18e-01

Pos logit contributions
atively+0.021
agg+0.020
ya+0.020
aded+0.020
overed+0.020
Neg logit contributions
 Wh-0.004
 Snow-0.004
 still-0.003
."-0.003
 Brown-0.003
Token the
Token ID262
Feature activation-5.31e-01

Pos logit contributions
 Wh+0.062
 Snow+0.058
 still+0.054
."+0.053
 Brown+0.051
Neg logit contributions
atively-0.162
ya-0.154
agg-0.152
overed-0.149
eways-0.148
Token bushes
Token ID37413
Feature activation-7.67e-01

Pos logit contributions
 Snow+0.025
 Wh+0.025
 Teddy+0.023
 Brown+0.023
."+0.022
Neg logit contributions
atively-0.027
ya-0.025
 traders-0.024
 flavours-0.024
agg-0.023
Token.
Token ID13
Feature activation+3.26e-01

Pos logit contributions
 Wh+0.019
 Snow+0.017
 Brown+0.015
 Teddy+0.015
 still+0.013
Neg logit contributions
atively-0.061
eways-0.056
agg-0.056
ya-0.056
overed-0.056
Token She
Token ID1375
Feature activation-8.28e-01

Pos logit contributions
atively+0.027
agg+0.026
ya+0.026
aded+0.026
eways+0.025
Neg logit contributions
 Wh-0.008
 Snow-0.007
 Brown-0.006
 Teddy-0.006
 Lily-0.006
Token looked
Token ID3114
Feature activation+2.86e+00

Pos logit contributions
 Snow+0.031
 Wh+0.031
 still+0.030
 Brown+0.028
 Teddy+0.028
Neg logit contributions
atively-0.055
agg-0.051
eways-0.051
overed-0.050
ya-0.050
Token closer
Token ID5699
Feature activation+5.86e+00

Pos logit contributions
atively+0.198
agg+0.191
ya+0.182
aded+0.181
eways+0.181
Neg logit contributions
 Wh-0.100
 Snow-0.097
 still-0.093
 Teddy-0.089
 Brown-0.088
Token and
Token ID290
Feature activation+1.31e-01

Pos logit contributions
atively+0.511
agg+0.500
aded+0.494
eways+0.483
ya+0.482
Neg logit contributions
 still-0.086
 Snow-0.083
 Wh-0.080
."-0.070
 Brown-0.065
Token saw
Token ID2497
Feature activation+1.29e+00

Pos logit contributions
atively+0.009
agg+0.009
aded+0.009
 flavours+0.009
eways+0.009
Neg logit contributions
 still-0.004
 Snow-0.004
 Wh-0.004
 Teddy-0.004
 Lily-0.004
Token that
Token ID326
Feature activation-1.51e+00

Pos logit contributions
atively+0.095
agg+0.091
ya+0.089
eways+0.088
overed+0.087
Neg logit contributions
 Wh-0.038
 Snow-0.035
 still-0.033
 Brown-0.031
."-0.031
Token her
Token ID607
Feature activation-1.57e+00

Pos logit contributions
 Wh+0.044
 Snow+0.041
 still+0.036
 Brown+0.036
 Teddy+0.035
Neg logit contributions
atively-0.112
agg-0.107
ya-0.106
eways-0.103
overed-0.102
Token bag
Token ID6131
Feature activation-2.77e+00

Pos logit contributions
 Wh+0.069
 Snow+0.064
 Brown+0.061
."+0.060
 Teddy+0.059
Neg logit contributions
atively-0.093
agg-0.087
ya-0.086
overed-0.083
aded-0.082
Token tall
Token ID7331
Feature activation-2.16e-01

Pos logit contributions
 Wh+0.007
 Snow+0.006
 still+0.006
 Brown+0.006
 Teddy+0.006
Neg logit contributions
atively-0.010
agg-0.009
ya-0.009
eways-0.009
overed-0.009
Token grass
Token ID8701
Feature activation-8.73e-01

Pos logit contributions
 Wh+0.008
 Snow+0.008
 still+0.007
."+0.007
 Brown+0.007
Neg logit contributions
atively-0.014
agg-0.013
ya-0.013
eways-0.013
overed-0.013
Token.
Token ID13
Feature activation+4.32e-01

Pos logit contributions
 Wh+0.014
 Snow+0.013
 still+0.011
 Brown+0.010
 Teddy+0.010
Neg logit contributions
atively-0.076
agg-0.074
ya-0.073
aded-0.071
eways-0.071
Token She
Token ID1375
Feature activation-7.11e-01

Pos logit contributions
atively+0.033
ya+0.031
agg+0.031
aded+0.031
eways+0.030
Neg logit contributions
 Wh-0.013
 Snow-0.012
 Brown-0.011
 Teddy-0.011
 still-0.010
Token looked
Token ID3114
Feature activation+2.82e+00

Pos logit contributions
 still+0.027
 Snow+0.025
 Wh+0.024
 never+0.022
 hurt+0.022
Neg logit contributions
atively-0.047
eways-0.045
agg-0.043
overed-0.043
ya-0.043
Token closer
Token ID5699
Feature activation+5.85e+00

Pos logit contributions
atively+0.190
agg+0.187
aded+0.178
eways+0.176
 flavours+0.173
Neg logit contributions
 still-0.105
 Snow-0.093
 Wh-0.092
 all-0.092
 too-0.089
Token and
Token ID290
Feature activation+2.74e-01

Pos logit contributions
atively+0.525
agg+0.516
aded+0.516
 arom+0.500
 traders+0.499
Neg logit contributions
 still-0.078
 Snow-0.056
 too-0.055
."-0.053
 because-0.050
Token discovered
Token ID5071
Feature activation+7.34e-01

Pos logit contributions
atively+0.019
aded+0.018
 flavours+0.018
eways+0.018
agg+0.018
Neg logit contributions
 still-0.010
 Snow-0.009
 Wh-0.008
 Teddy-0.008
 Lily-0.008
Token it
Token ID340
Feature activation+7.04e-01

Pos logit contributions
atively+0.058
agg+0.055
ya+0.055
aded+0.053
eways+0.053
Neg logit contributions
 Wh-0.019
 Snow-0.018
 still-0.016
 Brown-0.016
 Teddy-0.015
Token was
Token ID373
Feature activation+6.78e-02

Pos logit contributions
atively+0.055
agg+0.054
ya+0.053
aded+0.051
eways+0.051
Neg logit contributions
 Wh-0.017
 still-0.017
 Snow-0.017
 Brown-0.014
."-0.014
Token a
Token ID257
Feature activation+1.89e+00

Pos logit contributions
atively+0.005
agg+0.005
ya+0.005
eways+0.005
overed+0.005
Neg logit contributions
 Wh-0.002
 Snow-0.002
 still-0.002
 Brown-0.002
 Teddy-0.002
Token red
Token ID2266
Feature activation-3.70e-01

Pos logit contributions
 Wh+0.009
 Snow+0.008
 still+0.008
 Brown+0.008
 Teddy+0.008
Neg logit contributions
atively-0.016
agg-0.015
ya-0.015
eways-0.015
overed-0.015
Token button
Token ID4936
Feature activation+2.36e+00

Pos logit contributions
 Wh+0.014
 Snow+0.013
 Brown+0.012
 still+0.012
 Teddy+0.012
Neg logit contributions
atively-0.025
agg-0.024
ya-0.023
eways-0.023
aded-0.023
Token.
Token ID13
Feature activation+1.57e-01

Pos logit contributions
atively+0.196
agg+0.191
ya+0.188
eways+0.183
aded+0.182
Neg logit contributions
 Wh-0.049
 Snow-0.045
 still-0.038
 Brown-0.037
 Teddy-0.036
Token He
Token ID679
Feature activation+6.67e-01

Pos logit contributions
atively+0.011
agg+0.010
ya+0.010
eways+0.010
overed+0.010
Neg logit contributions
 Wh-0.006
 Snow-0.005
 still-0.005
 Brown-0.005
 Teddy-0.005
Token looked
Token ID3114
Feature activation+2.63e+00

Pos logit contributions
atively+0.044
agg+0.042
ya+0.041
eways+0.041
overed+0.040
Neg logit contributions
 Wh-0.025
 Snow-0.024
 still-0.022
 Brown-0.022
 Teddy-0.022
Token closer
Token ID5699
Feature activation+5.85e+00

Pos logit contributions
atively+0.190
agg+0.187
eways+0.178
aded+0.177
ya+0.175
Neg logit contributions
 still-0.084
 Wh-0.077
 Snow-0.076
 Teddy-0.073
 all-0.070
Token and
Token ID290
Feature activation+3.02e-01

Pos logit contributions
atively+0.513
agg+0.506
aded+0.499
eways+0.490
ya+0.489
Neg logit contributions
 still-0.084
 Snow-0.073
."-0.066
 Wh-0.064
 too-0.060
Token found
Token ID1043
Feature activation+3.62e-01

Pos logit contributions
atively+0.021
agg+0.020
eways+0.020
aded+0.020
 flavours+0.019
Neg logit contributions
 still-0.011
 Snow-0.010
 Wh-0.010
 Teddy-0.010
 Lily-0.009
Token a
Token ID257
Feature activation+1.46e+00

Pos logit contributions
atively+0.026
agg+0.025
ya+0.024
eways+0.024
overed+0.024
Neg logit contributions
 Wh-0.012
 Snow-0.011
 still-0.010
 Brown-0.010
 Teddy-0.010
Token label
Token ID6167
Feature activation+1.68e+00

Pos logit contributions
atively+0.096
agg+0.091
ya+0.090
eways+0.087
overed+0.086
Neg logit contributions
 Wh-0.056
 Snow-0.053
 still-0.048
 Brown-0.048
 Teddy-0.048
Token that
Token ID326
Feature activation-4.36e-01

Pos logit contributions
atively+0.140
agg+0.137
ya+0.134
eways+0.131
aded+0.130
Neg logit contributions
 Wh-0.034
 Snow-0.032
 still-0.030
 Brown-0.028
."-0.027
Token
Token ID220
Feature activation+9.15e-01

Pos logit contributions
atively+0.032
agg+0.031
eways+0.031
ya+0.030
aded+0.030
Neg logit contributions
 Wh-0.017
 Snow-0.017
 Teddy-0.015
 still-0.015
 Brown-0.015
Token
Token ID198
Feature activation-1.69e-01

Pos logit contributions
atively+0.068
agg+0.065
eways+0.064
overed+0.063
aded+0.061
Neg logit contributions
 Wh-0.025
 Snow-0.022
 Teddy-0.019
 Brown-0.019
 still-0.019
Token
Token ID198
Feature activation-4.19e-01

Pos logit contributions
 Wh+0.002
 Snow+0.002
 still+0.002
."+0.002
 Teddy+0.002
Neg logit contributions
atively-0.015
agg-0.014
ya-0.014
eways-0.014
overed-0.014
TokenJimmy
Token ID40335
Feature activation+2.82e+00

Pos logit contributions
 still+0.018
 Wh+0.017
 Snow+0.017
."+0.017
 Teddy+0.016
Neg logit contributions
atively-0.026
agg-0.024
eways-0.024
overed-0.024
ya-0.023
Token looked
Token ID3114
Feature activation+2.92e+00

Pos logit contributions
atively+0.204
agg+0.194
eways+0.192
ya+0.188
overed+0.186
Neg logit contributions
 Wh-0.090
 Snow-0.088
 still-0.085
 Brown-0.079
 Teddy-0.078
Token closer
Token ID5699
Feature activation+5.85e+00

Pos logit contributions
atively+0.193
agg+0.185
eways+0.177
ya+0.175
aded+0.173
Neg logit contributions
 Wh-0.115
 Snow-0.111
 still-0.110
 Teddy-0.104
 Brown-0.102
Token and
Token ID290
Feature activation+6.78e-02

Pos logit contributions
atively+0.525
agg+0.522
aded+0.517
eways+0.508
ya+0.501
Neg logit contributions
 still-0.077
 Snow-0.062
 too-0.059
."-0.055
 Wh-0.053
Token asked
Token ID1965
Feature activation-4.66e-01

Pos logit contributions
atively+0.005
eways+0.005
agg+0.005
aded+0.005
 flavours+0.005
Neg logit contributions
 still-0.002
 Snow-0.002
 Wh-0.002
 Teddy-0.002
 Lily-0.002
Token,
Token ID11
Feature activation-7.46e-01

Pos logit contributions
 Wh+0.009
 Snow+0.009
 Brown+0.007
 Teddy+0.007
 still+0.007
Neg logit contributions
atively-0.040
agg-0.038
overed-0.038
aded-0.038
eways-0.037
Token "
Token ID366
Feature activation+1.52e+00

Pos logit contributions
 Wh+0.025
 Snow+0.024
 still+0.023
 Brown+0.022
 Teddy+0.021
Neg logit contributions
atively-0.053
agg-0.051
ya-0.050
eways-0.050
aded-0.049
TokenWhat
Token ID2061
Feature activation+2.82e+00

Pos logit contributions
atively+0.090
agg+0.085
overed+0.084
eways+0.083
aded+0.083
Neg logit contributions
 Wh-0.071
 Snow-0.071
 still-0.066
 Teddy-0.065
 Brown-0.065
Token friendship
Token ID14738
Feature activation-1.71e+00

Pos logit contributions
 Wh+0.040
 Snow+0.033
 Teddy+0.033
 Mitt+0.032
 H+0.031
Neg logit contributions
atively-0.055
ya-0.051
agg-0.050
 arom-0.050
 phrase-0.049
Token.
Token ID13
Feature activation-1.56e+00

Pos logit contributions
 Wh+0.064
 Mitt+0.053
 Snow+0.052
 Rat+0.047
 Teddy+0.047
Neg logit contributions
atively-0.118
ya-0.108
agg-0.105
eways-0.104
overed-0.102
Token When
Token ID1649
Feature activation-1.26e+00

Pos logit contributions
 Wh+0.067
 hurt+0.065
 ruined+0.064
 still+0.063
 Snow+0.061
Neg logit contributions
atively-0.082
agg-0.079
overed-0.076
ya-0.074
Run-0.073
Token my
Token ID616
Feature activation-2.39e+00

Pos logit contributions
 Wh+0.042
 Snow+0.039
 Brown+0.035
 still+0.035
 Teddy+0.035
Neg logit contributions
atively-0.087
agg-0.084
ya-0.082
aded-0.080
eways-0.079
Token wing
Token ID8539
Feature activation-7.64e+00

Pos logit contributions
 Wh+0.085
 Snow+0.074
 Teddy+0.071
 Brown+0.068
 still+0.067
Neg logit contributions
atively-0.161
agg-0.155
ya-0.152
aded-0.145
overed-0.145
Token heals
Token ID38673
Feature activation-7.73e+00

Pos logit contributions
 Wh+0.273
 Snow+0.263
 Teddy+0.249
 Brown+0.243
 Mitt+0.231
Neg logit contributions
atively-0.496
agg-0.442
overed-0.438
aded-0.427
ya-0.425
Token,
Token ID11
Feature activation-1.57e+00

Pos logit contributions
 Wh+0.280
 Snow+0.253
 Teddy+0.241
 Brown+0.228
 still+0.226
Neg logit contributions
atively-0.485
ya-0.455
agg-0.442
overed-0.436
ued-0.428
Token I
Token ID314
Feature activation-1.20e+00

Pos logit contributions
 Wh+0.054
 Snow+0.050
 Brown+0.046
 Teddy+0.045
 still+0.043
Neg logit contributions
atively-0.106
agg-0.102
ya-0.101
aded-0.096
overed-0.096
Token will
Token ID481
Feature activation-1.38e+00

Pos logit contributions
 Wh+0.050
 Teddy+0.045
 Mitt+0.044
 Brown+0.043
 Snow+0.043
Neg logit contributions
atively-0.065
agg-0.063
ager-0.061
aded-0.059
ued-0.059
Token take
Token ID1011
Feature activation+5.63e-01

Pos logit contributions
 Wh+0.065
 Teddy+0.058
 Mitt+0.056
 Snow+0.056
 Rat+0.054
Neg logit contributions
atively-0.065
agg-0.061
ured-0.058
ya-0.058
 explanation-0.057
Token you
Token ID345
Feature activation+1.86e+00

Pos logit contributions
atively+0.038
agg+0.036
ya+0.036
aded+0.034
overed+0.034
Neg logit contributions
 Wh-0.020
 Snow-0.018
 still-0.016
 Brown-0.016
 Teddy-0.016
Token your
Token ID534
Feature activation-9.51e-01

Pos logit contributions
ya+0.033
atively+0.033
agg+0.033
aded+0.031
 arom+0.031
Neg logit contributions
 Wh-0.022
 Snow-0.019
 Brown-0.018
 still-0.018
 Teddy-0.017
Token friendship
Token ID14738
Feature activation-1.71e+00

Pos logit contributions
 Wh+0.040
 Snow+0.033
 Teddy+0.033
 Mitt+0.032
 H+0.031
Neg logit contributions
atively-0.055
ya-0.051
agg-0.050
 arom-0.050
 phrase-0.049
Token.
Token ID13
Feature activation-1.56e+00

Pos logit contributions
 Wh+0.064
 Mitt+0.053
 Snow+0.052
 Rat+0.047
 Teddy+0.047
Neg logit contributions
atively-0.118
ya-0.108
agg-0.105
eways-0.104
overed-0.102
Token When
Token ID1649
Feature activation-1.26e+00

Pos logit contributions
 Wh+0.067
 hurt+0.065
 ruined+0.064
 still+0.063
 Snow+0.061
Neg logit contributions
atively-0.082
agg-0.079
overed-0.076
ya-0.074
Run-0.073
Token my
Token ID616
Feature activation-2.39e+00

Pos logit contributions
 Wh+0.042
 Snow+0.039
 Brown+0.035
 still+0.035
 Teddy+0.035
Neg logit contributions
atively-0.087
agg-0.084
ya-0.082
aded-0.080
eways-0.079
Token wing
Token ID8539
Feature activation-7.64e+00

Pos logit contributions
 Wh+0.085
 Snow+0.074
 Teddy+0.071
 Brown+0.068
 still+0.067
Neg logit contributions
atively-0.161
agg-0.155
ya-0.152
aded-0.145
overed-0.145
Token heals
Token ID38673
Feature activation-7.73e+00

Pos logit contributions
 Wh+0.273
 Snow+0.263
 Teddy+0.249
 Brown+0.243
 Mitt+0.231
Neg logit contributions
atively-0.496
agg-0.442
overed-0.438
aded-0.427
ya-0.425
Token,
Token ID11
Feature activation-1.57e+00

Pos logit contributions
 Wh+0.280
 Snow+0.253
 Teddy+0.241
 Brown+0.228
 still+0.226
Neg logit contributions
atively-0.485
ya-0.455
agg-0.442
overed-0.436
ued-0.428
Token I
Token ID314
Feature activation-1.20e+00

Pos logit contributions
 Wh+0.054
 Snow+0.050
 Brown+0.046
 Teddy+0.045
 still+0.043
Neg logit contributions
atively-0.106
agg-0.102
ya-0.101
aded-0.096
overed-0.096
Token will
Token ID481
Feature activation-1.38e+00

Pos logit contributions
 Wh+0.050
 Teddy+0.045
 Mitt+0.044
 Brown+0.043
 Snow+0.043
Neg logit contributions
atively-0.065
agg-0.063
ager-0.061
aded-0.059
ued-0.059
Token take
Token ID1011
Feature activation+5.63e-01

Pos logit contributions
 Wh+0.065
 Teddy+0.058
 Mitt+0.056
 Snow+0.056
 Rat+0.054
Neg logit contributions
atively-0.065
agg-0.061
ured-0.058
ya-0.058
 explanation-0.057
Token Max
Token ID5436
Feature activation-2.36e-01

Pos logit contributions
atively+0.005
ya+0.005
agg+0.005
eways+0.005
overed+0.005
Neg logit contributions
 Wh-0.001
 Snow-0.001
."-0.001
 still-0.001
 Brown-0.001
Token felt
Token ID2936
Feature activation-7.27e-01

Pos logit contributions
 Wh+0.010
 Snow+0.009
 Brown+0.009
 Teddy+0.008
."+0.008
Neg logit contributions
atively-0.014
ya-0.014
agg-0.013
aded-0.013
eways-0.013
Token helpless
Token ID21144
Feature activation+3.21e-02

Pos logit contributions
 Wh+0.025
 Brown+0.024
 Snow+0.023
 Teddy+0.021
."+0.020
Neg logit contributions
atively-0.045
agg-0.044
aded-0.044
overed-0.044
ya-0.043
Token when
Token ID618
Feature activation+1.77e-01

Pos logit contributions
atively+0.002
ya+0.002
eways+0.002
overed+0.002
agg+0.002
Neg logit contributions
 Wh-0.001
 Snow-0.001
 Brown-0.001
 Teddy-0.001
 Mitt-0.001
Token his
Token ID465
Feature activation-2.08e+00

Pos logit contributions
atively+0.011
agg+0.011
ya+0.011
eways+0.010
overed+0.010
Neg logit contributions
 Wh-0.007
 Snow-0.006
."-0.006
 still-0.006
 Brown-0.006
Token wing
Token ID8539
Feature activation-7.59e+00

Pos logit contributions
 Wh+0.071
 Snow+0.063
 Teddy+0.059
 Brown+0.057
 Mitt+0.056
Neg logit contributions
atively-0.147
agg-0.142
ya-0.136
aded-0.134
overed-0.134
Token was
Token ID373
Feature activation-1.82e+00

Pos logit contributions
 Wh+0.310
 Snow+0.299
 Brown+0.296
 Teddy+0.296
 my+0.262
Neg logit contributions
atively-0.466
aded-0.407
overed-0.404
agg-0.382
 edged-0.381
Token injured
Token ID6686
Feature activation-4.23e+00

Pos logit contributions
 Wh+0.075
 Snow+0.067
 Teddy+0.062
 Rat+0.062
 Brown+0.061
Neg logit contributions
atively-0.114
aded-0.106
overed-0.106
agg-0.104
ued-0.103
Token.
Token ID13
Feature activation-4.06e-02

Pos logit contributions
 Wh+0.149
 Snow+0.134
 Teddy+0.119
 Brown+0.118
 Mitt+0.118
Neg logit contributions
atively-0.261
eways-0.236
ya-0.234
 curiously-0.229
Run-0.227
Token He
Token ID679
Feature activation+5.88e-01

Pos logit contributions
 Wh+0.001
 Snow+0.001
 still+0.001
."+0.001
 ruined+0.001
Neg logit contributions
atively-0.003
eways-0.002
agg-0.002
overed-0.002
ya-0.002
Token couldn
Token ID3521
Feature activation-2.74e+00

Pos logit contributions
atively+0.033
ya+0.031
agg+0.030
aded+0.030
ued+0.029
Neg logit contributions
 Wh-0.027
 Snow-0.025
 Brown-0.023
 Mitt-0.023
 Teddy-0.023
Token in
Token ID287
Feature activation+5.93e-01

Pos logit contributions
atively+0.038
agg+0.036
ya+0.036
aded+0.036
overed+0.034
Neg logit contributions
 Wh-0.022
 Snow-0.019
 Brown-0.018
 Teddy-0.017
."-0.017
Token his
Token ID465
Feature activation-4.70e-01

Pos logit contributions
atively+0.038
ya+0.036
agg+0.035
eway+0.034
eways+0.034
Neg logit contributions
 Wh-0.019
 Snow-0.017
 still-0.016
."-0.015
my-0.015
Token nest
Token ID16343
Feature activation-4.18e+00

Pos logit contributions
 Wh+0.020
 Snow+0.017
."+0.017
my+0.017
un+0.017
Neg logit contributions
atively-0.024
ya-0.023
agg-0.022
ement-0.021
 site-0.021
Token until
Token ID1566
Feature activation-8.91e-01

Pos logit contributions
 Wh+0.156
 Snow+0.145
 Teddy+0.132
 Brown+0.127
 Mitt+0.119
Neg logit contributions
atively-0.292
agg-0.260
ya-0.259
eways-0.252
overed-0.244
Token his
Token ID465
Feature activation-2.20e+00

Pos logit contributions
 Wh+0.032
 Snow+0.029
 Brown+0.028
."+0.027
 still+0.026
Neg logit contributions
atively-0.060
agg-0.056
ya-0.055
overed-0.054
aded-0.053
Token wing
Token ID8539
Feature activation-7.29e+00

Pos logit contributions
 Wh+0.073
 Snow+0.059
 Teddy+0.058
 Mitt+0.055
 Brown+0.055
Neg logit contributions
atively-0.153
agg-0.152
aded-0.143
ya-0.142
overed-0.138
Token got
Token ID1392
Feature activation-2.15e+00

Pos logit contributions
 Wh+0.299
 Snow+0.276
 Teddy+0.275
 Brown+0.268
 Mitt+0.253
Neg logit contributions
atively-0.467
overed-0.396
agg-0.394
aded-0.392
eways-0.375
Token better
Token ID1365
Feature activation-1.77e+00

Pos logit contributions
 Wh+0.076
 Snow+0.070
 Rat+0.064
 Brown+0.062
 Teddy+0.060
Neg logit contributions
atively-0.135
aded-0.125
agg-0.125
 nearer-0.122
overed-0.119
Token.
Token ID13
Feature activation-2.19e-01

Pos logit contributions
 Wh+0.063
 Snow+0.051
 Mitt+0.049
 Teddy+0.047
 Brown+0.046
Neg logit contributions
atively-0.125
ya-0.117
agg-0.116
overed-0.112
 flavours-0.111
Token
Token ID220
Feature activation+2.86e-01

Pos logit contributions
 ruined+0.009
 bleeding+0.008
 hurt+0.008
 Wh+0.007
 bruised+0.007
Neg logit contributions
agg-0.013
atively-0.013
overed-0.012
aded-0.012
ya-0.012
Token
Token ID198
Feature activation-5.24e-01

Pos logit contributions
atively+0.019
agg+0.018
eways+0.018
overed+0.018
aded+0.017
Neg logit contributions
 Wh-0.009
 Snow-0.008
 ruined-0.008
 hurt-0.008
 bruised-0.008
Token couldn
Token ID3521
Feature activation-3.17e+00

Pos logit contributions
atively+0.021
ya+0.020
agg+0.019
aded+0.019
 edged+0.018
Neg logit contributions
 Wh-0.015
 Snow-0.013
 Brown-0.013
."-0.013
 Teddy-0.012
Token't
Token ID470
Feature activation-2.95e+00

Pos logit contributions
 Snow+0.115
 Wh+0.115
 bruised+0.104
 Teddy+0.102
 Brown+0.099
Neg logit contributions
atively-0.194
agg-0.180
overed-0.177
ued-0.176
aded-0.172
Token fly
Token ID6129
Feature activation-2.79e+00

Pos logit contributions
 Wh+0.143
 Snow+0.132
 Mitt+0.129
 Teddy+0.129
 Brown+0.122
Neg logit contributions
atively-0.157
agg-0.141
ya-0.137
ued-0.131
aded-0.130
Token until
Token ID1566
Feature activation-8.41e-01

Pos logit contributions
 Snow+0.094
 Wh+0.093
 Teddy+0.084
 Brown+0.080
 Mitt+0.080
Neg logit contributions
atively-0.181
eways-0.164
overed-0.157
eway-0.154
 inspection-0.154
Token his
Token ID465
Feature activation-2.04e+00

Pos logit contributions
 Wh+0.032
 Snow+0.030
 Brown+0.027
 Teddy+0.026
."+0.025
Neg logit contributions
atively-0.056
agg-0.051
overed-0.050
ya-0.050
aded-0.049
Token wing
Token ID8539
Feature activation-7.25e+00

Pos logit contributions
 Wh+0.076
 Snow+0.065
 Teddy+0.063
 Brown+0.061
 Mitt+0.058
Neg logit contributions
atively-0.136
agg-0.130
ya-0.128
aded-0.124
overed-0.121
Token was
Token ID373
Feature activation-1.97e+00

Pos logit contributions
 Wh+0.286
 Snow+0.272
 Teddy+0.263
 Brown+0.259
 my+0.255
Neg logit contributions
atively-0.456
overed-0.382
aded-0.377
agg-0.368
eways-0.362
Token healed
Token ID28557
Feature activation-5.55e+00

Pos logit contributions
 Wh+0.076
 Snow+0.067
 Rat+0.065
 Teddy+0.060
 Mitt+0.059
Neg logit contributions
atively-0.121
aded-0.111
agg-0.107
 nearer-0.106
overed-0.105
Token.
Token ID13
Feature activation+2.10e-02

Pos logit contributions
 Wh+0.163
 Snow+0.146
 Brown+0.122
 Teddy+0.119
 Mitt+0.116
Neg logit contributions
atively-0.416
agg-0.377
eways-0.372
ya-0.372
aded-0.367
Token He
Token ID679
Feature activation+3.50e-01

Pos logit contributions
atively+0.001
agg+0.001
ya+0.001
overed+0.001
eways+0.001
Neg logit contributions
 Wh-0.001
 Snow-0.001
 Brown-0.001
 still-0.001
 Teddy-0.001
Token had
Token ID550
Feature activation-1.46e+00

Pos logit contributions
atively+0.020
ya+0.019
agg+0.018
aded+0.017
 edged+0.017
Neg logit contributions
 Wh-0.016
 Snow-0.014
."-0.013
 Brown-0.013
 Teddy-0.013
Token it
Token ID340
Feature activation+7.15e-01

Pos logit contributions
 Wh+0.126
 Snow+0.117
 still+0.108
 Brown+0.105
 Teddy+0.104
Neg logit contributions
atively-0.221
ya-0.209
agg-0.205
eways-0.198
overed-0.196
Token for
Token ID329
Feature activation+1.80e-01

Pos logit contributions
atively+0.045
ya+0.041
overed+0.040
ued+0.039
eways+0.039
Neg logit contributions
 Wh-0.028
 Snow-0.026
 Mitt-0.025
 Teddy-0.023
 Brown-0.023
Token us
Token ID514
Feature activation+5.73e-01

Pos logit contributions
atively+0.012
agg+0.012
ya+0.012
aded+0.011
eways+0.011
Neg logit contributions
 Wh-0.006
 Snow-0.006
 still-0.005
 Brown-0.005
 Teddy-0.005
Token when
Token ID618
Feature activation-1.38e+00

Pos logit contributions
atively+0.037
ya+0.035
agg+0.034
eways+0.033
ued+0.032
Neg logit contributions
 Wh-0.022
 Snow-0.019
 Mitt-0.018
 Teddy-0.018
 Brown-0.017
Token she
Token ID673
Feature activation-4.00e+00

Pos logit contributions
 Wh+0.047
 Snow+0.044
 still+0.040
 Brown+0.040
 Teddy+0.039
Neg logit contributions
atively-0.095
agg-0.091
ya-0.089
eways-0.087
overed-0.086
Token died
Token ID3724
Feature activation-7.07e+00

Pos logit contributions
 Wh+0.162
 Snow+0.149
 Mitt+0.139
 Teddy+0.137
 Brown+0.137
Neg logit contributions
atively-0.250
agg-0.233
ya-0.229
aded-0.222
overed-0.221
Token.
Token ID13
Feature activation-1.16e+00

Pos logit contributions
 Wh+0.243
 Snow+0.216
 Mitt+0.199
 Teddy+0.194
 still+0.194
Neg logit contributions
atively-0.485
ya-0.449
agg-0.440
eways-0.426
overed-0.421
Token It
Token ID632
Feature activation-8.19e-02

Pos logit contributions
 hurt+0.049
 ruined+0.048
 Wh+0.047
 still+0.047
 bleeding+0.045
Neg logit contributions
atively-0.062
agg-0.060
ya-0.056
eways-0.056
Run-0.053
Token had
Token ID550
Feature activation-1.68e+00

Pos logit contributions
 Wh+0.003
 Snow+0.003
 Mitt+0.003
 Teddy+0.003
 Brown+0.003
Neg logit contributions
atively-0.005
 arom-0.004
ya-0.004
agg-0.004
ued-0.004
Token her
Token ID607
Feature activation-4.81e-01

Pos logit contributions
 Wh+0.059
 Snow+0.053
 Mitt+0.052
 Teddy+0.051
 still+0.050
Neg logit contributions
atively-0.107
agg-0.099
ya-0.098
 arom-0.094
 flavours-0.094
Token most
Token ID749
Feature activation+1.82e+00

Pos logit contributions
 Wh+0.021
 Mitt+0.018
 Snow+0.018
 Teddy+0.017
 bleeding+0.016
Neg logit contributions
atively-0.027
ya-0.026
agg-0.025
 flavours-0.024
 arom-0.024
Token care
Token ID1337
Feature activation-5.44e-01

Pos logit contributions
atively+0.043
agg+0.041
ya+0.041
eways+0.040
overed+0.039
Neg logit contributions
 Wh-0.018
 Snow-0.017
 Brown-0.015
 Teddy-0.015
 still-0.015
Token of
Token ID286
Feature activation-2.26e+00

Pos logit contributions
 Wh+0.022
 Snow+0.020
 Brown+0.018
 Teddy+0.018
 Mitt+0.017
Neg logit contributions
atively-0.036
agg-0.034
eways-0.033
overed-0.032
ya-0.032
Token it
Token ID340
Feature activation+8.63e-01

Pos logit contributions
 Wh+0.078
 Snow+0.070
 still+0.064
 Teddy+0.063
 Brown+0.063
Neg logit contributions
atively-0.150
agg-0.142
ya-0.141
eways-0.140
aded-0.135
Token until
Token ID1566
Feature activation-6.74e-01

Pos logit contributions
atively+0.070
agg+0.067
ya+0.066
eways+0.065
overed+0.064
Neg logit contributions
 Wh-0.020
 Snow-0.018
 Brown-0.015
 Teddy-0.015
 still-0.015
Token its
Token ID663
Feature activation-3.63e+00

Pos logit contributions
 Wh+0.022
 Snow+0.020
 Brown+0.018
 still+0.018
 Teddy+0.018
Neg logit contributions
atively-0.049
agg-0.047
ya-0.046
overed-0.045
eways-0.045
Token wing
Token ID8539
Feature activation-6.94e+00

Pos logit contributions
 Wh+0.143
 Snow+0.131
 Teddy+0.124
 Brown+0.120
 still+0.116
Neg logit contributions
atively-0.237
agg-0.225
ya-0.217
aded-0.213
eways-0.210
Token was
Token ID373
Feature activation-1.83e+00

Pos logit contributions
 Wh+0.275
 Snow+0.256
 Teddy+0.250
 Brown+0.245
 Mitt+0.225
Neg logit contributions
atively-0.447
agg-0.401
aded-0.396
overed-0.396
eways-0.383
Token better
Token ID1365
Feature activation-2.17e+00

Pos logit contributions
 Wh+0.072
 Snow+0.061
 Rat+0.060
 Teddy+0.057
 Brown+0.055
Neg logit contributions
atively-0.118
aded-0.114
agg-0.114
overed-0.107
 arom-0.102
Token.
Token ID13
Feature activation+3.83e-02

Pos logit contributions
 Wh+0.071
 Snow+0.061
 Teddy+0.056
 Brown+0.055
 Mitt+0.053
Neg logit contributions
atively-0.158
agg-0.149
ya-0.148
overed-0.147
eways-0.143
Token The
Token ID383
Feature activation-7.29e-01

Pos logit contributions
atively+0.002
agg+0.002
overed+0.002
ya+0.002
eways+0.002
Neg logit contributions
 Wh-0.001
 ruined-0.001
 Snow-0.001
 hurt-0.001
 still-0.001
Token little
Token ID1310
Feature activation+3.62e-03

Pos logit contributions
 Wh+0.026
 Snow+0.025
 Brown+0.022
 Teddy+0.022
 still+0.022
Neg logit contributions
atively-0.050
agg-0.048
ya-0.047
eways-0.045
overed-0.045
Token care
Token ID1337
Feature activation-2.23e-01

Pos logit contributions
atively+0.076
agg+0.071
ya+0.071
eways+0.069
overed+0.068
Neg logit contributions
 Wh-0.033
 Snow-0.032
 Brown-0.028
 Teddy-0.028
 still-0.027
Token of
Token ID286
Feature activation-2.04e+00

Pos logit contributions
 Wh+0.010
 Snow+0.009
 Brown+0.009
 Teddy+0.009
 Mitt+0.008
Neg logit contributions
atively-0.013
eways-0.012
agg-0.012
overed-0.012
aded-0.012
Token it
Token ID340
Feature activation+9.27e-01

Pos logit contributions
 Wh+0.063
 Snow+0.056
 Teddy+0.052
 still+0.051
 Brown+0.051
Neg logit contributions
atively-0.142
ya-0.135
agg-0.135
eways-0.132
overed-0.130
Token until
Token ID1566
Feature activation-6.31e-01

Pos logit contributions
atively+0.070
agg+0.065
ya+0.065
eways+0.064
overed+0.063
Neg logit contributions
 Wh-0.027
 Snow-0.025
 Teddy-0.021
 Brown-0.021
 Mitt-0.020
Token its
Token ID663
Feature activation-3.68e+00

Pos logit contributions
 Wh+0.021
 Snow+0.020
 Brown+0.018
 Teddy+0.017
 still+0.017
Neg logit contributions
atively-0.045
agg-0.042
ya-0.042
overed-0.041
eways-0.040
Token wing
Token ID8539
Feature activation-6.89e+00

Pos logit contributions
 Wh+0.132
 Teddy+0.114
 Snow+0.112
 Mitt+0.104
 Brown+0.102
Neg logit contributions
atively-0.247
agg-0.232
aded-0.222
ya-0.220
 arom-0.215
Token healed
Token ID28557
Feature activation-6.41e+00

Pos logit contributions
 Wh+0.283
 Teddy+0.270
 Snow+0.262
 Brown+0.258
 my+0.244
Neg logit contributions
atively-0.429
overed-0.376
aded-0.370
agg-0.363
eways-0.354
Token.
Token ID13
Feature activation-1.21e-01

Pos logit contributions
 Wh+0.179
 Snow+0.153
 Teddy+0.141
 Brown+0.136
 still+0.128
Neg logit contributions
atively-0.470
ya-0.444
agg-0.438
 arom-0.431
eways-0.429
Token
Token ID198
Feature activation-6.63e-01

Pos logit contributions
 Wh+0.004
 hurt+0.004
 Snow+0.004
 bleeding+0.003
 ac+0.003
Neg logit contributions
atively-0.008
overed-0.008
agg-0.008
ya-0.007
eways-0.007
Token
Token ID198
Feature activation-8.09e-01

Pos logit contributions
 Wh+0.018
 Snow+0.017
 bruised+0.015
 Brown+0.015
 still+0.014
Neg logit contributions
atively-0.049
agg-0.048
eways-0.047
ya-0.046
overed-0.045
TokenA
Token ID32
Feature activation-5.31e-02

Pos logit contributions
 Wh+0.038
 Snow+0.036
 still+0.035
 Teddy+0.033
."+0.033
Neg logit contributions
atively-0.047
agg-0.044
ya-0.043
eways-0.042
overed-0.041
Token could
Token ID714
Feature activation-3.09e+00

Pos logit contributions
 Wh+0.082
 Snow+0.079
 Teddy+0.073
 Brown+0.071
."+0.071
Neg logit contributions
atively-0.146
agg-0.138
ya-0.135
overed-0.131
aded-0.130
Token not
Token ID407
Feature activation-3.28e+00

Pos logit contributions
 Wh+0.098
 Snow+0.092
 Teddy+0.083
 Mitt+0.076
 Brown+0.076
Neg logit contributions
atively-0.226
agg-0.203
overed-0.191
ued-0.190
aded-0.190
Token recover
Token ID8551
Feature activation-3.91e+00

Pos logit contributions
 Wh+0.133
 Snow+0.128
 Teddy+0.116
 Mitt+0.113
 Brown+0.111
Neg logit contributions
atively-0.211
agg-0.190
ya-0.184
aded-0.182
overed-0.178
Token and
Token ID290
Feature activation-7.79e-01

Pos logit contributions
 Wh+0.116
 Snow+0.106
 Teddy+0.091
 Brown+0.091
 still+0.089
Neg logit contributions
atively-0.290
agg-0.270
ya-0.268
eways-0.266
overed-0.260
Token eventually
Token ID4191
Feature activation-1.91e+00

Pos logit contributions
 Wh+0.026
 Snow+0.025
 Teddy+0.022
 Brown+0.022
."+0.021
Neg logit contributions
atively-0.054
agg-0.050
ya-0.049
aded-0.048
overed-0.048
Token died
Token ID3724
Feature activation-6.86e+00

Pos logit contributions
 Wh+0.072
 Snow+0.064
 Brown+0.058
 Teddy+0.057
 Mitt+0.056
Neg logit contributions
atively-0.130
agg-0.122
ya-0.116
aded-0.116
overed-0.115
Token due
Token ID2233
Feature activation-9.59e-01

Pos logit contributions
 Wh+0.194
 Snow+0.170
 Teddy+0.154
 Mitt+0.146
 still+0.142
Neg logit contributions
atively-0.523
agg-0.467
overed-0.467
eways-0.462
aded-0.453
Token to
Token ID284
Feature activation+1.49e-01

Pos logit contributions
 Wh+0.028
 Snow+0.026
 Brown+0.023
 still+0.023
 Teddy+0.023
Neg logit contributions
atively-0.072
agg-0.069
ya-0.067
eways-0.066
overed-0.066
Token the
Token ID262
Feature activation-1.19e+00

Pos logit contributions
atively+0.010
agg+0.010
ya+0.009
aded+0.009
eways+0.009
Neg logit contributions
 Wh-0.005
 Snow-0.005
 Teddy-0.004
 Brown-0.004
 still-0.004
Token damage
Token ID2465
Feature activation-1.90e+00

Pos logit contributions
 Wh+0.051
 Snow+0.049
 Teddy+0.046
 Brown+0.045
."+0.044
Neg logit contributions
atively-0.071
agg-0.068
ya-0.067
aded-0.063
eways-0.063
Token caused
Token ID4073
Feature activation-2.20e+00

Pos logit contributions
 Wh+0.045
 Snow+0.040
 Brown+0.034
 still+0.033
 Teddy+0.033
Neg logit contributions
atively-0.153
agg-0.145
ya-0.145
eways-0.141
overed-0.140
Token share
Token ID2648
Feature activation-1.29e+00

Pos logit contributions
agg+0.063
aded+0.060
atively+0.059
ya+0.057
 traders+0.056
Neg logit contributions
 Teddy-0.046
 Wh-0.044
 Snow-0.044
 bleeding-0.044
 Brown-0.043
Token.
Token ID13
Feature activation-1.50e+00

Pos logit contributions
 Wh+0.041
 Snow+0.036
 Teddy+0.033
 Brown+0.033
 still+0.033
Neg logit contributions
atively-0.086
ya-0.086
agg-0.084
eways-0.081
 arom-0.081
Token We
Token ID775
Feature activation+2.30e+00

Pos logit contributions
 Wh+0.070
 Snow+0.065
 still+0.064
 hurt+0.063
 Brown+0.063
Neg logit contributions
atively-0.078
agg-0.075
ya-0.072
eways-0.070
overed-0.070
Token hope
Token ID2911
Feature activation-2.02e+00

Pos logit contributions
atively+0.133
agg+0.131
ya+0.128
aded+0.125
ager+0.124
Neg logit contributions
 Wh-0.084
 Brown-0.078
 bleeding-0.077
 Teddy-0.077
 Snow-0.076
Token your
Token ID534
Feature activation-1.78e+00

Pos logit contributions
 Wh+0.078
 Snow+0.070
 Brown+0.065
 still+0.065
 Teddy+0.064
Neg logit contributions
atively-0.123
agg-0.122
ya-0.121
eways-0.112
 arom-0.111
Token wing
Token ID8539
Feature activation-6.85e+00

Pos logit contributions
 Wh+0.069
 Teddy+0.063
 Snow+0.063
 Brown+0.061
 still+0.058
Neg logit contributions
atively-0.105
agg-0.104
ya-0.103
 flavours-0.098
aded-0.097
Token will
Token ID481
Feature activation-1.69e+00

Pos logit contributions
 Wh+0.255
 Teddy+0.228
 Snow+0.226
 Brown+0.221
 Mitt+0.207
Neg logit contributions
atively-0.464
agg-0.424
ya-0.407
overed-0.406
eways-0.405
Token heal
Token ID12035
Feature activation-5.05e+00

Pos logit contributions
 Wh+0.071
 Teddy+0.065
 Snow+0.062
 Brown+0.061
 Rat+0.061
Neg logit contributions
atively-0.096
agg-0.089
ured-0.082
 nearer-0.081
ya-0.081
Token soon
Token ID2582
Feature activation-3.29e+00

Pos logit contributions
 Wh+0.179
 Snow+0.156
 Teddy+0.145
 Brown+0.144
 Mitt+0.140
Neg logit contributions
atively-0.336
ya-0.322
agg-0.319
 arom-0.301
eways-0.299
Token,"
Token ID553
Feature activation-7.75e-01

Pos logit contributions
 Wh+0.109
 Snow+0.096
 Teddy+0.087
 Brown+0.086
 Mitt+0.085
Neg logit contributions
atively-0.232
ya-0.222
agg-0.219
overed-0.209
 arom-0.207
Token Sara
Token ID24799
Feature activation-7.88e-01

Pos logit contributions
 Wh+0.022
 Snow+0.020
 still+0.018
 Brown+0.018
 Teddy+0.017
Neg logit contributions
atively-0.058
agg-0.056
ya-0.055
overed-0.053
eways-0.052
Token and
Token ID290
Feature activation-3.00e-01

Pos logit contributions
atively+0.020
ya+0.019
agg+0.019
eways+0.019
overed+0.018
Neg logit contributions
 Wh-0.007
 Snow-0.006
 Brown-0.006
 Teddy-0.005
 Mitt-0.005
Token find
Token ID1064
Feature activation-2.99e-01

Pos logit contributions
 Wh+0.012
 Snow+0.011
 Teddy+0.010
 Brown+0.010
 Mitt+0.009
Neg logit contributions
atively-0.019
ya-0.018
agg-0.018
overed-0.017
aded-0.017
Token out
Token ID503
Feature activation+5.45e-02

Pos logit contributions
 Wh+0.011
 Snow+0.010
 still+0.009
 Brown+0.009
 Teddy+0.009
Neg logit contributions
atively-0.021
agg-0.020
ya-0.019
eways-0.019
overed-0.019
Token why
Token ID1521
Feature activation+3.35e-02

Pos logit contributions
atively+0.004
ya+0.004
agg+0.003
eways+0.003
aded+0.003
Neg logit contributions
 Wh-0.002
 Snow-0.002
 Brown-0.002
 Teddy-0.002
 Mitt-0.002
Token it
Token ID340
Feature activation-1.79e+00

Pos logit contributions
atively+0.002
ya+0.002
agg+0.002
eways+0.002
overed+0.002
Neg logit contributions
 Wh-0.001
 Snow-0.001
 Teddy-0.001
 Brown-0.001
 still-0.001
Token died
Token ID3724
Feature activation-6.81e+00

Pos logit contributions
 Wh+0.071
 Snow+0.067
 Teddy+0.062
 Brown+0.061
 Mitt+0.059
Neg logit contributions
atively-0.113
agg-0.106
ya-0.105
aded-0.102
overed-0.101
Token."
Token ID526
Feature activation+2.21e-01

Pos logit contributions
 Wh+0.169
 Snow+0.133
 Mitt+0.126
 Teddy+0.123
 Rat+0.116
Neg logit contributions
atively-0.526
eways-0.484
ya-0.482
agg-0.472
 arom-0.460
Token
Token ID198
Feature activation-1.95e-01

Pos logit contributions
atively+0.021
aded+0.021
ya+0.020
agg+0.020
eways+0.020
Neg logit contributions
-0.001
."-0.001
 still-0.001
 Wh-0.000
 Snow-0.000
Token
Token ID198
Feature activation-3.26e-01

Pos logit contributions
 Wh+0.002
 Snow+0.002
 still+0.002
."+0.001
 Brown+0.001
Neg logit contributions
atively-0.018
ya-0.017
agg-0.017
aded-0.017
 arom-0.017
TokenThe
Token ID464
Feature activation-9.02e-01

Pos logit contributions
 still+0.016
 never+0.016
+0.014
 now+0.014
."+0.014
Neg logit contributions
 arom-0.017
atively-0.017
overed-0.016
aded-0.016
acies-0.015
Token teacher
Token ID4701
Feature activation+9.83e-01

Pos logit contributions
 Wh+0.030
 Snow+0.029
 still+0.028
 Brown+0.026
 hurt+0.025
Neg logit contributions
atively-0.065
agg-0.061
ya-0.061
eways-0.060
overed-0.059
Token a
Token ID257
Feature activation+7.99e-01

Pos logit contributions
atively+0.023
agg+0.021
ya+0.021
aded+0.020
 flavours+0.020
Neg logit contributions
 Wh-0.013
 Snow-0.012
 Teddy-0.011
 Brown-0.011
 still-0.011
Token nail
Token ID17864
Feature activation-1.37e+00

Pos logit contributions
atively+0.050
agg+0.047
ya+0.046
aded+0.044
 arom+0.044
Neg logit contributions
 Wh-0.032
 Snow-0.029
 Brown-0.027
 Teddy-0.027
 still-0.027
Token to
Token ID284
Feature activation+1.42e+00

Pos logit contributions
 Wh+0.041
 Snow+0.037
 Brown+0.032
 Teddy+0.032
 Mitt+0.032
Neg logit contributions
atively-0.099
ya-0.090
agg-0.089
aded-0.088
overed-0.086
Token help
Token ID1037
Feature activation-6.09e-01

Pos logit contributions
atively+0.080
agg+0.077
ya+0.075
aded+0.073
ured+0.070
Neg logit contributions
 Wh-0.055
 Snow-0.052
 Brown-0.049
 Teddy-0.048
 still-0.046
Token his
Token ID465
Feature activation-1.95e+00

Pos logit contributions
 Wh+0.024
 Snow+0.023
 still+0.021
 Brown+0.020
 Teddy+0.020
Neg logit contributions
atively-0.036
ya-0.035
agg-0.034
eways-0.033
aded-0.033
Token wing
Token ID8539
Feature activation-6.80e+00

Pos logit contributions
 Wh+0.060
 Snow+0.054
 Teddy+0.050
 Brown+0.046
 still+0.046
Neg logit contributions
atively-0.134
agg-0.129
ya-0.129
aded-0.123
 flavours-0.122
Token heal
Token ID12035
Feature activation-4.66e+00

Pos logit contributions
 Wh+0.215
 Snow+0.195
 Teddy+0.187
 Brown+0.183
 Rat+0.158
Neg logit contributions
atively-0.474
agg-0.432
eways-0.426
eway-0.417
aded-0.415
Token."
Token ID526
Feature activation-2.18e-02

Pos logit contributions
 Wh+0.124
 Snow+0.101
 Brown+0.088
 Teddy+0.086
 still+0.083
Neg logit contributions
atively-0.342
ya-0.329
agg-0.316
 arom-0.311
eways-0.311
Token
Token ID220
Feature activation+1.91e-01

Pos logit contributions
 Wh+0.001
 Snow+0.001
 still+0.001
 ruined+0.001
 hurt+0.001
Neg logit contributions
atively-0.001
agg-0.001
ya-0.001
overed-0.001
eways-0.001
Token
Token ID198
Feature activation-2.78e-01

Pos logit contributions
atively+0.014
agg+0.014
overed+0.013
eways+0.013
aded+0.013
Neg logit contributions
 Wh-0.005
 Snow-0.005
 ruined-0.004
 Teddy-0.004
 bleeding-0.004
Token
Token ID198
Feature activation-4.40e-01

Pos logit contributions
 Wh+0.007
 Snow+0.006
 still+0.006
 Brown+0.005
 Teddy+0.005
Neg logit contributions
atively-0.021
agg-0.021
ya-0.020
eways-0.020
Kevin-0.019
Token and
Token ID290
Feature activation+7.36e-02

Pos logit contributions
 Wh+0.034
 Snow+0.031
 Teddy+0.028
 Mitt+0.026
 Brown+0.026
Neg logit contributions
atively-0.092
ya-0.088
eways-0.086
agg-0.085
overed-0.082
Token find
Token ID1064
Feature activation+6.73e-02

Pos logit contributions
atively+0.005
ya+0.005
agg+0.004
eways+0.004
overed+0.004
Neg logit contributions
 Wh-0.003
 Snow-0.002
 Teddy-0.002
 Brown-0.002
 Mitt-0.002
Token out
Token ID503
Feature activation+3.77e-01

Pos logit contributions
atively+0.005
agg+0.005
ya+0.004
eways+0.004
overed+0.004
Neg logit contributions
 Wh-0.002
 Snow-0.002
 Brown-0.002
 still-0.002
 Teddy-0.002
Token why
Token ID1521
Feature activation+1.03e-01

Pos logit contributions
atively+0.027
ya+0.026
agg+0.026
eways+0.026
aded+0.025
Neg logit contributions
 Wh-0.012
 Snow-0.011
 Teddy-0.009
 Brown-0.009
 still-0.009
Token it
Token ID340
Feature activation-1.77e+00

Pos logit contributions
atively+0.007
ya+0.006
agg+0.006
eways+0.006
overed+0.006
Neg logit contributions
 Wh-0.004
 Snow-0.003
 Teddy-0.003
 Brown-0.003
 still-0.003
Token died
Token ID3724
Feature activation-6.73e+00

Pos logit contributions
 Wh+0.072
 Snow+0.067
 Teddy+0.062
 Brown+0.062
 Mitt+0.060
Neg logit contributions
atively-0.111
agg-0.104
ya-0.103
aded-0.100
overed-0.099
Token."
Token ID526
Feature activation+4.48e-02

Pos logit contributions
 Wh+0.166
 Snow+0.129
 Mitt+0.128
 Teddy+0.119
 Rat+0.114
Neg logit contributions
atively-0.518
ya-0.478
eways-0.474
agg-0.466
 arom-0.452
Token
Token ID198
Feature activation-3.19e-01

Pos logit contributions
atively+0.004
ya+0.004
agg+0.004
aded+0.004
eways+0.004
Neg logit contributions
."-0.000
 Wh-0.000
 still-0.000
-0.000
 Snow-0.000
Token
Token ID198
Feature activation-4.24e-01

Pos logit contributions
 Wh+0.004
 Snow+0.003
 still+0.003
."+0.002
 Brown+0.002
Neg logit contributions
atively-0.029
ya-0.028
agg-0.028
overed-0.027
aded-0.027
TokenSo
Token ID2396
Feature activation+1.26e+00

Pos logit contributions
 still+0.016
 never+0.015
."+0.014
+0.014
 now+0.014
Neg logit contributions
 arom-0.026
atively-0.026
overed-0.026
aded-0.025
agg-0.024
Token Jim
Token ID5395
Feature activation+3.43e+00

Pos logit contributions
atively+0.070
aded+0.069
agg+0.069
eways+0.068
overed+0.068
Neg logit contributions
 still-0.056
."-0.054
 all-0.053
 no-0.052
 both-0.051
Token it
Token ID340
Feature activation+1.07e+00

Pos logit contributions
 Wh+0.056
 Snow+0.052
 still+0.047
 Brown+0.047
 Teddy+0.046
Neg logit contributions
atively-0.124
agg-0.118
ya-0.117
eways-0.113
aded-0.112
Token to
Token ID284
Feature activation+1.35e+00

Pos logit contributions
atively+0.074
ya+0.069
agg+0.068
eways+0.066
aded+0.064
Neg logit contributions
 Wh-0.034
 Snow-0.031
 still-0.028
 Teddy-0.028
 Brown-0.028
Token me
Token ID502
Feature activation+1.96e-01

Pos logit contributions
atively+0.082
ya+0.080
agg+0.078
aded+0.073
 arom+0.072
Neg logit contributions
 Wh-0.050
 Snow-0.048
 still-0.045
 Brown-0.044
 Teddy-0.043
Token before
Token ID878
Feature activation-1.34e+00

Pos logit contributions
atively+0.015
ya+0.015
agg+0.014
eways+0.014
overed+0.014
Neg logit contributions
 Wh-0.005
 Snow-0.004
 Brown-0.004
 Teddy-0.004
 Mitt-0.003
Token he
Token ID339
Feature activation-2.24e+00

Pos logit contributions
 Wh+0.046
 Snow+0.042
 still+0.039
 Brown+0.038
 Teddy+0.037
Neg logit contributions
atively-0.088
ya-0.083
agg-0.083
aded-0.080
eways-0.080
Token died
Token ID3724
Feature activation-6.71e+00

Pos logit contributions
 Wh+0.090
 Snow+0.085
 Brown+0.079
 Teddy+0.078
 Mitt+0.076
Neg logit contributions
atively-0.141
agg-0.132
ya-0.130
aded-0.127
overed-0.126
Token.
Token ID13
Feature activation-8.03e-01

Pos logit contributions
 Wh+0.158
 Snow+0.133
 Mitt+0.119
 Teddy+0.118
 still+0.114
Neg logit contributions
atively-0.528
ya-0.486
eways-0.478
agg-0.473
overed-0.468
Token He
Token ID679
Feature activation+2.32e-01

Pos logit contributions
 Wh+0.033
 ruined+0.033
 still+0.032
 hurt+0.032
 Snow+0.030
Neg logit contributions
atively-0.042
agg-0.039
Run-0.038
ya-0.037
 gru-0.037
Token said
Token ID531
Feature activation+4.82e-01

Pos logit contributions
atively+0.015
ya+0.014
agg+0.013
aded+0.013
ued+0.013
Neg logit contributions
 Wh-0.009
 Snow-0.008
 Mitt-0.008
 Brown-0.007
 Teddy-0.007
Token it
Token ID340
Feature activation+3.57e-01

Pos logit contributions
atively+0.034
agg+0.033
ya+0.032
overed+0.031
eways+0.031
Neg logit contributions
 Wh-0.015
 Snow-0.014
 still-0.013
 Brown-0.012
 Teddy-0.012
Token was
Token ID373
Feature activation-3.89e-01

Pos logit contributions
atively+0.023
agg+0.021
ya+0.021
eways+0.020
overed+0.020
Neg logit contributions
 Wh-0.013
 Snow-0.012
 Mitt-0.011
 Teddy-0.011
 Brown-0.011
Token what
Token ID644
Feature activation+7.71e-01

Pos logit contributions
 Wh+0.091
 Snow+0.083
 still+0.077
 bleeding+0.076
 hurt+0.075
Neg logit contributions
atively-0.135
ya-0.127
agg-0.127
eways-0.124
overed-0.119
Token would
Token ID561
Feature activation-1.04e+00

Pos logit contributions
atively+0.049
agg+0.048
ya+0.048
eways+0.046
 flavours+0.045
Neg logit contributions
 Wh-0.025
 Snow-0.023
 still-0.022
 Brown-0.021
."-0.020
Token happen
Token ID1645
Feature activation-6.15e-01

Pos logit contributions
 Wh+0.048
 Snow+0.046
 still+0.043
 Brown+0.043
 Teddy+0.043
Neg logit contributions
atively-0.060
agg-0.057
ya-0.056
eways-0.054
overed-0.053
Token when
Token ID618
Feature activation-1.44e+00

Pos logit contributions
 Wh+0.017
 Snow+0.016
 still+0.014
 Brown+0.014
 Teddy+0.014
Neg logit contributions
atively-0.047
agg-0.045
ya-0.044
eways-0.043
overed-0.043
Token her
Token ID607
Feature activation-4.43e+00

Pos logit contributions
 Wh+0.046
 Snow+0.043
 still+0.039
 Brown+0.038
 Teddy+0.038
Neg logit contributions
atively-0.105
agg-0.099
ya-0.098
eways-0.096
overed-0.095
Token tooth
Token ID16162
Feature activation-6.70e+00

Pos logit contributions
 Wh+0.164
 Snow+0.144
."+0.129
 still+0.128
 Brown+0.127
Neg logit contributions
atively-0.286
agg-0.273
ya-0.264
 arom-0.256
aded-0.252
Token finally
Token ID3443
Feature activation-2.76e+00

Pos logit contributions
 Wh+0.258
 Snow+0.227
 Mitt+0.217
 Brown+0.211
 Teddy+0.210
Neg logit contributions
atively-0.443
agg-0.385
overed-0.381
aded-0.370
 arom-0.363
Token fell
Token ID3214
Feature activation-5.32e+00

Pos logit contributions
 Wh+0.121
 Snow+0.108
 Brown+0.101
 Mitt+0.099
 Teddy+0.096
Neg logit contributions
atively-0.169
agg-0.153
ya-0.152
 arom-0.147
overed-0.147
Token out
Token ID503
Feature activation+8.37e-01

Pos logit contributions
 Wh+0.201
 Snow+0.178
 Mitt+0.171
 still+0.171
 never+0.161
Neg logit contributions
atively-0.317
eways-0.262
 curiously-0.258
overed-0.257
ly-0.257
Token.
Token ID13
Feature activation-3.47e-01

Pos logit contributions
atively+0.059
eways+0.055
agg+0.054
ya+0.053
eway+0.052
Neg logit contributions
 Wh-0.029
 Snow-0.027
 Mitt-0.023
 Brown-0.022
 Teddy-0.022
Token "
Token ID366
Feature activation+2.58e+00

Pos logit contributions
 Wh+0.011
 Snow+0.010
 still+0.009
 Brown+0.009
 Teddy+0.009
Neg logit contributions
atively-0.025
agg-0.024
ya-0.023
eways-0.023
overed-0.023
Token few
Token ID1178
Feature activation-1.12e+00

Pos logit contributions
atively+0.218
agg+0.206
ya+0.198
overed+0.198
eways+0.197
Neg logit contributions
 Wh-0.113
 Snow-0.106
."-0.098
 still-0.098
 Brown-0.097
Token days
Token ID1528
Feature activation-9.57e-01

Pos logit contributions
 Wh+0.059
 Snow+0.057
 still+0.055
."+0.054
 Brown+0.053
Neg logit contributions
atively-0.058
agg-0.053
ya-0.052
overed-0.050
eways-0.050
Token until
Token ID1566
Feature activation-9.09e-01

Pos logit contributions
 Wh+0.025
 Snow+0.022
 Brown+0.018
 Teddy+0.018
 Mitt+0.018
Neg logit contributions
atively-0.074
agg-0.070
ya-0.070
overed-0.069
eways-0.068
Token his
Token ID465
Feature activation-2.37e+00

Pos logit contributions
 Wh+0.032
 Snow+0.030
 Brown+0.027
 still+0.027
 Teddy+0.026
Neg logit contributions
atively-0.062
agg-0.059
ya-0.058
aded-0.056
overed-0.056
Token ankle
Token ID19847
Feature activation-4.93e+00

Pos logit contributions
 Wh+0.094
 Snow+0.088
 Brown+0.081
 Teddy+0.080
 still+0.079
Neg logit contributions
atively-0.154
agg-0.147
ya-0.144
eways-0.139
aded-0.139
Token healed
Token ID28557
Feature activation-6.69e+00

Pos logit contributions
 Wh+0.195
 Brown+0.177
 Snow+0.176
 Teddy+0.172
 Mitt+0.162
Neg logit contributions
atively-0.313
overed-0.276
aded-0.268
agg-0.257
ued-0.257
Token.
Token ID13
Feature activation-1.55e-01

Pos logit contributions
 Wh+0.195
 Snow+0.169
 Teddy+0.146
 Brown+0.145
 Mitt+0.142
Neg logit contributions
atively-0.491
ya-0.456
agg-0.446
eways-0.442
 arom-0.436
Token He
Token ID679
Feature activation+2.65e-01

Pos logit contributions
 Wh+0.006
 Snow+0.006
 Brown+0.005
 still+0.005
 Teddy+0.005
Neg logit contributions
atively-0.010
agg-0.010
ya-0.010
eways-0.009
aded-0.009
Token felt
Token ID2936
Feature activation-2.31e-01

Pos logit contributions
atively+0.015
ya+0.014
agg+0.014
aded+0.013
overed+0.013
Neg logit contributions
 Wh-0.013
 Snow-0.011
 Brown-0.010
 Mitt-0.010
 Teddy-0.010
Token sad
Token ID6507
Feature activation-1.32e+00

Pos logit contributions
 Wh+0.010
 Brown+0.008
 Snow+0.008
ety+0.007
 Rat+0.007
Neg logit contributions
atively-0.013
agg-0.013
aded-0.013
ued-0.013
overed-0.012
Token not
Token ID407
Feature activation-1.66e+00

Pos logit contributions
 Wh+0.056
 Snow+0.048
 Brown+0.043
 Mitt+0.043
 Fl+0.040
Neg logit contributions
atively-0.081
overed-0.073
ya-0.070
 inspection-0.069
agg-0.069
Token became
Token ID2627
Feature activation-1.73e+00

Pos logit contributions
 Wh+0.005
 Snow+0.005
 Brown+0.005
 Teddy+0.004
."+0.004
Neg logit contributions
atively-0.008
agg-0.008
ya-0.008
aded-0.007
overed-0.007
Token very
Token ID845
Feature activation-3.12e-01

Pos logit contributions
 Wh+0.052
 Snow+0.050
 Brown+0.043
 Teddy+0.041
."+0.037
Neg logit contributions
atively-0.123
agg-0.119
ya-0.118
aded-0.117
 arom-0.113
Token weak
Token ID4939
Feature activation-2.47e+00

Pos logit contributions
 Wh+0.010
 Snow+0.009
 Brown+0.009
 Teddy+0.008
 Mitt+0.007
Neg logit contributions
atively-0.023
agg-0.022
ya-0.021
aded-0.021
overed-0.020
Token and
Token ID290
Feature activation+2.40e-01

Pos logit contributions
 Wh+0.070
 Snow+0.064
 Teddy+0.054
 Brown+0.053
 Mitt+0.051
Neg logit contributions
atively-0.189
ya-0.176
agg-0.175
overed-0.172
eways-0.171
Token eventually
Token ID4191
Feature activation-1.58e+00

Pos logit contributions
atively+0.015
ya+0.014
agg+0.014
aded+0.014
ued+0.013
Neg logit contributions
 Wh-0.009
 Snow-0.009
 Brown-0.008
 Teddy-0.008
un-0.007
Token died
Token ID3724
Feature activation-6.67e+00

Pos logit contributions
 Wh+0.065
 Snow+0.058
 Brown+0.054
 Teddy+0.052
 Mitt+0.048
Neg logit contributions
atively-0.103
agg-0.097
ya-0.094
aded-0.092
 arom-0.090
Token.
Token ID13
Feature activation-1.40e-01

Pos logit contributions
 Wh+0.186
 Snow+0.163
 Teddy+0.147
 Mitt+0.135
 Brown+0.133
Neg logit contributions
atively-0.517
agg-0.462
overed-0.459
eways-0.456
ya-0.453
Token
Token ID198
Feature activation-5.44e-01

Pos logit contributions
 Wh+0.005
 ruined+0.005
 ac+0.005
 Snow+0.005
 lose+0.005
Neg logit contributions
atively-0.008
agg-0.008
Kevin-0.007
ya-0.007
mber-0.007
Token
Token ID198
Feature activation-6.57e-01

Pos logit contributions
 Wh+0.018
 Snow+0.017
 Brown+0.015
 Teddy+0.015
 bruised+0.015
Neg logit contributions
agg-0.036
atively-0.036
eways-0.034
aded-0.034
Kevin-0.033
TokenThe
Token ID464
Feature activation-8.66e-01

Pos logit contributions
 Wh+0.033
 Snow+0.032
 Brown+0.031
 Teddy+0.030
."+0.029
Neg logit contributions
atively-0.035
agg-0.033
ya-0.032
aded-0.031
eways-0.031
Token sad
Token ID6507
Feature activation-2.47e+00

Pos logit contributions
 Wh+0.033
 Snow+0.032
 Teddy+0.029
."+0.029
 Brown+0.028
Neg logit contributions
atively-0.054
ya-0.051
agg-0.051
aded-0.048
 arom-0.047
Token is
Token ID318
Feature activation+3.89e-01

Pos logit contributions
 Wh+0.056
 Snow+0.052
 Brown+0.047
 Teddy+0.047
 Mitt+0.045
Neg logit contributions
atively-0.116
agg-0.109
ya-0.109
overed-0.105
aded-0.104
Token not
Token ID407
Feature activation-2.41e+00

Pos logit contributions
ya+0.023
atively+0.023
agg+0.022
aded+0.022
Kevin+0.021
Neg logit contributions
 Wh-0.014
 Snow-0.012
 Brown-0.012
 Teddy-0.011
un-0.011
Token happy
Token ID3772
Feature activation-1.53e+00

Pos logit contributions
 Wh+0.086
 Snow+0.083
 Brown+0.072
 Teddy+0.072
 Rat+0.070
Neg logit contributions
ya-0.150
atively-0.144
agg-0.139
aded-0.134
 arom-0.134
Token when
Token ID618
Feature activation-1.24e+00

Pos logit contributions
 Wh+0.043
 Snow+0.040
 Brown+0.034
 Teddy+0.034
 still+0.033
Neg logit contributions
atively-0.115
ya-0.109
agg-0.109
eways-0.106
overed-0.106
Token you
Token ID345
Feature activation-7.73e-01

Pos logit contributions
 Wh+0.039
 Snow+0.036
 still+0.032
 Brown+0.032
 Teddy+0.032
Neg logit contributions
atively-0.090
agg-0.086
ya-0.084
eways-0.082
overed-0.082
Token hurt
Token ID5938
Feature activation-6.62e+00

Pos logit contributions
 Wh+0.029
 Snow+0.027
 Brown+0.026
 Teddy+0.025
 Mitt+0.024
Neg logit contributions
atively-0.050
agg-0.046
ya-0.046
aded-0.045
overed-0.044
Token it
Token ID340
Feature activation-1.30e+00

Pos logit contributions
 Wh+0.238
 Snow+0.222
 Brown+0.201
 Teddy+0.195
 still+0.195
Neg logit contributions
atively-0.420
ya-0.419
agg-0.398
eways-0.397
aded-0.376
Token.
Token ID13
Feature activation-1.13e+00

Pos logit contributions
 Wh+0.039
 Snow+0.035
 Mitt+0.030
 Brown+0.030
 Teddy+0.029
Neg logit contributions
atively-0.093
ya-0.085
agg-0.084
ued-0.083
aded-0.082
Token How
Token ID1374
Feature activation+2.18e+00

Pos logit contributions
 ruined+0.048
 hurt+0.047
 Wh+0.047
 still+0.046
 bleeding+0.044
Neg logit contributions
agg-0.056
atively-0.055
ya-0.051
eways-0.051
Run-0.051
Token about
Token ID546
Feature activation-2.22e+00

Pos logit contributions
atively+0.143
agg+0.139
ya+0.134
eways+0.133
aded+0.128
Neg logit contributions
 Wh-0.084
 Snow-0.079
 Brown-0.073
 Teddy-0.070
 Mitt-0.068
Token we
Token ID356
Feature activation-6.17e-01

Pos logit contributions
 Wh+0.067
 Snow+0.063
 still+0.056
 Brown+0.055
 Teddy+0.055
Neg logit contributions
atively-0.166
agg-0.158
ya-0.156
eways-0.152
overed-0.151
Token it
Token ID340
Feature activation+1.54e+00

Pos logit contributions
 Wh+0.054
 Snow+0.051
 still+0.047
 Brown+0.046
 Teddy+0.046
Neg logit contributions
atively-0.100
agg-0.095
ya-0.094
eways-0.091
overed-0.089
Token to
Token ID284
Feature activation+1.55e+00

Pos logit contributions
atively+0.119
agg+0.114
ya+0.112
overed+0.109
eways+0.109
Neg logit contributions
 Wh-0.043
 Snow-0.040
 Brown-0.035
 Teddy-0.035
 still-0.035
Token me
Token ID502
Feature activation+5.12e-01

Pos logit contributions
atively+0.106
ya+0.102
agg+0.099
eways+0.093
 arom+0.091
Neg logit contributions
 Wh-0.052
 Snow-0.048
 still-0.046
 bleeding-0.043
 Brown-0.042
Token before
Token ID878
Feature activation-1.12e+00

Pos logit contributions
atively+0.039
agg+0.037
ya+0.036
eways+0.035
overed+0.035
Neg logit contributions
 Wh-0.015
 Snow-0.014
 Brown-0.012
 still-0.012
 Teddy-0.012
Token he
Token ID339
Feature activation-2.04e+00

Pos logit contributions
 Wh+0.043
 Snow+0.040
 still+0.038
 Brown+0.036
 Teddy+0.036
Neg logit contributions
atively-0.072
agg-0.068
ya-0.068
overed-0.065
eways-0.065
Token died
Token ID3724
Feature activation-6.61e+00

Pos logit contributions
 Wh+0.077
 Snow+0.072
 Brown+0.066
 Teddy+0.065
 still+0.064
Neg logit contributions
atively-0.136
agg-0.127
ya-0.125
aded-0.121
overed-0.120
Token.
Token ID13
Feature activation-2.93e-01

Pos logit contributions
 Wh+0.178
 Snow+0.152
 Mitt+0.139
 still+0.136
 Teddy+0.134
Neg logit contributions
atively-0.519
ya-0.466
agg-0.464
eways-0.459
overed-0.458
Token I
Token ID314
Feature activation+6.90e-01

Pos logit contributions
 hurt+0.009
 ruined+0.009
 Wh+0.009
 still+0.009
 bleeding+0.009
Neg logit contributions
atively-0.019
agg-0.018
ya-0.018
mber-0.017
overed-0.017
Token value
Token ID1988
Feature activation-1.40e+00

Pos logit contributions
atively+0.042
agg+0.040
ued+0.037
aded+0.037
ya+0.037
Neg logit contributions
 Wh-0.028
 Snow-0.025
 Mitt-0.024
 Brown-0.024
 Teddy-0.024
Token it
Token ID340
Feature activation+8.12e-01

Pos logit contributions
 Wh+0.044
 Snow+0.038
 still+0.035
 Brown+0.033
 Mitt+0.032
Neg logit contributions
atively-0.099
ya-0.098
agg-0.094
eways-0.092
overed-0.089
Token very
Token ID845
Feature activation-4.97e-01

Pos logit contributions
atively+0.057
ya+0.053
agg+0.050
eways+0.050
ued+0.048
Neg logit contributions
 Wh-0.028
 Snow-0.025
 Mitt-0.022
 Brown-0.021
 Teddy-0.021
Token bug
Token ID5434
Feature activation-1.50e+00

Pos logit contributions
 Wh+0.025
 still+0.023
 Snow+0.023
 hurt+0.021
 Teddy+0.021
Neg logit contributions
atively-0.057
ya-0.054
agg-0.054
eways-0.052
overed-0.051
Token couldn
Token ID3521
Feature activation-3.82e+00

Pos logit contributions
 Wh+0.056
 Snow+0.054
 Brown+0.049
 Teddy+0.049
."+0.046
Neg logit contributions
atively-0.101
agg-0.093
ya-0.092
aded-0.091
overed-0.090
Token't
Token ID470
Feature activation-3.38e+00

Pos logit contributions
 Snow+0.138
 Wh+0.137
 Teddy+0.123
 bruised+0.123
 Brown+0.119
Neg logit contributions
atively-0.239
overed-0.223
agg-0.220
aded-0.213
ued-0.212
Token survive
Token ID7866
Feature activation-1.61e+00

Pos logit contributions
 Wh+0.152
 Snow+0.144
 Teddy+0.134
 Brown+0.132
 Mitt+0.130
Neg logit contributions
atively-0.204
agg-0.189
ya-0.180
aded-0.180
overed-0.175
Token and
Token ID290
Feature activation-1.15e+00

Pos logit contributions
 Wh+0.044
 Snow+0.040
 Brown+0.034
 still+0.033
 Teddy+0.033
Neg logit contributions
atively-0.125
agg-0.118
ya-0.117
eways-0.115
overed-0.114
Token died
Token ID3724
Feature activation-6.59e+00

Pos logit contributions
 Wh+0.040
 Snow+0.039
."+0.037
 Teddy+0.034
un+0.034
Neg logit contributions
atively-0.072
overed-0.064
aded-0.064
agg-0.063
 inspection-0.062
Token.
Token ID13
Feature activation-3.37e-01

Pos logit contributions
 Wh+0.197
 Snow+0.171
 Teddy+0.156
 have+0.153
 Mitt+0.153
Neg logit contributions
atively-0.488
overed-0.428
eways-0.423
agg-0.417
aded-0.408
Token Tim
Token ID5045
Feature activation+8.31e-01

Pos logit contributions
 Snow+0.010
 still+0.009
 Wh+0.009
."+0.009
 hurt+0.008
Neg logit contributions
atively-0.023
agg-0.021
eways-0.021
overed-0.021
ya-0.021
Tokenmy
Token ID1820
Feature activation-1.74e-01

Pos logit contributions
ya+0.053
atively+0.046
ering+0.045
agg+0.045
mber+0.045
Neg logit contributions
 Wh-0.031
 Snow-0.029
 Brown-0.025
."-0.024
 Fl-0.024
Token felt
Token ID2936
Feature activation-6.15e-01

Pos logit contributions
 Wh+0.008
 Snow+0.007
 Brown+0.007
 Teddy+0.007
."+0.007
Neg logit contributions
atively-0.009
ya-0.009
agg-0.009
aded-0.009
ued-0.008
Token very
Token ID845
Feature activation+1.39e+00

Pos logit contributions
 Wh+0.024
 Snow+0.022
 Brown+0.022
."+0.019
 Teddy+0.019
Neg logit contributions
atively-0.037
ued-0.035
aded-0.035
agg-0.035
ya-0.033
Token where
Token ID810
Feature activation+6.24e-01

Pos logit contributions
atively+0.003
agg+0.003
ya+0.003
eways+0.003
overed+0.003
Neg logit contributions
 Wh-0.002
 Snow-0.001
 still-0.001
 Brown-0.001
 Teddy-0.001
Token she
Token ID673
Feature activation-8.10e-01

Pos logit contributions
atively+0.045
agg+0.042
ya+0.042
eways+0.041
aded+0.040
Neg logit contributions
 Wh-0.020
 Snow-0.018
 still-0.016
 Brown-0.016
 Teddy-0.016
Token was
Token ID373
Feature activation-7.03e-01

Pos logit contributions
 Wh+0.024
 Snow+0.022
 still+0.019
 Brown+0.019
 Teddy+0.019
Neg logit contributions
atively-0.061
agg-0.058
ya-0.057
eways-0.056
overed-0.055
Token.
Token ID13
Feature activation+1.56e-01

Pos logit contributions
 Wh+0.019
 Snow+0.018
 Teddy+0.015
 Brown+0.015
 still+0.015
Neg logit contributions
atively-0.054
agg-0.051
ya-0.051
eways-0.050
overed-0.049
Token He
Token ID679
Feature activation+8.86e-01

Pos logit contributions
atively+0.012
agg+0.011
ya+0.011
eways+0.011
overed+0.011
Neg logit contributions
 Wh-0.004
 Snow-0.004
 still-0.004
 Brown-0.004
."-0.004
Token waited
Token ID13488
Feature activation+3.24e+00

Pos logit contributions
atively+0.056
eways+0.053
agg+0.053
ya+0.052
overed+0.051
Neg logit contributions
 Wh-0.035
 Snow-0.035
 still-0.035
 Brown-0.031
 Teddy-0.031
Token and
Token ID290
Feature activation-1.50e-01

Pos logit contributions
atively+0.247
agg+0.243
ya+0.241
aded+0.235
eways+0.232
Neg logit contributions
 Snow-0.078
 Wh-0.077
 still-0.076
."-0.071
 Teddy-0.068
Token waited
Token ID13488
Feature activation+2.46e+00

Pos logit contributions
 still+0.006
 Snow+0.006
 Wh+0.006
 Teddy+0.006
 Brown+0.005
Neg logit contributions
atively-0.009
eways-0.009
agg-0.009
ya-0.009
 flavours-0.008
Token.
Token ID13
Feature activation-2.38e-01

Pos logit contributions
atively+0.189
agg+0.185
ya+0.184
aded+0.179
eways+0.177
Neg logit contributions
 Snow-0.058
 Wh-0.058
 still-0.055
."-0.054
 Teddy-0.051
Token
Token ID198
Feature activation-3.12e-01

Pos logit contributions
 Wh+0.008
 Snow+0.008
 still+0.007
 Brown+0.007
."+0.007
Neg logit contributions
atively-0.017
agg-0.016
ya-0.015
eways-0.015
overed-0.015
Token
Token ID198
Feature activation-5.13e-01

Pos logit contributions
 Wh+0.007
 Snow+0.006
 Brown+0.005
 still+0.005
 Teddy+0.005
Neg logit contributions
atively-0.026
agg-0.025
ya-0.024
eways-0.024
aded-0.024
Token
Token ID198
Feature activation-2.95e-01

Pos logit contributions
atively+0.044
agg+0.041
ya+0.041
eways+0.040
overed+0.040
Neg logit contributions
 Wh-0.016
 Snow-0.015
 still-0.014
 Teddy-0.013
 Brown-0.013
Token
Token ID198
Feature activation-4.10e-01

Pos logit contributions
 Wh+0.007
 Snow+0.006
 still+0.006
 Teddy+0.006
 Brown+0.006
Neg logit contributions
atively-0.023
agg-0.022
ya-0.022
eways-0.021
aded-0.021
TokenThe
Token ID464
Feature activation-8.72e-01

Pos logit contributions
 Wh+0.016
 Snow+0.015
 still+0.014
 Brown+0.014
 Teddy+0.014
Neg logit contributions
atively-0.027
agg-0.026
ya-0.025
overed-0.024
eways-0.024
Token dog
Token ID3290
Feature activation-3.46e-01

Pos logit contributions
 Wh+0.029
 Snow+0.027
 Brown+0.025
 still+0.024
 Teddy+0.024
Neg logit contributions
atively-0.062
agg-0.059
ya-0.058
eways-0.057
overed-0.056
Token looked
Token ID3114
Feature activation+2.80e+00

Pos logit contributions
 Wh+0.013
 still+0.012
 Snow+0.012
 Brown+0.011
 Fl+0.010
Neg logit contributions
atively-0.023
eways-0.023
agg-0.023
ya-0.022
aded-0.022
Token at
Token ID379
Feature activation+4.09e+00

Pos logit contributions
atively+0.195
agg+0.187
ya+0.182
eways+0.180
overed+0.177
Neg logit contributions
 Wh-0.096
 Snow-0.092
 still-0.087
 Teddy-0.083
 Brown-0.083
Token him
Token ID683
Feature activation+2.51e+00

Pos logit contributions
atively+0.293
ya+0.276
agg+0.268
eways+0.261
 inspection+0.256
Neg logit contributions
 Wh-0.112
 still-0.106
 Snow-0.103
."-0.097
 bleeding-0.096
Token for
Token ID329
Feature activation+1.00e+00

Pos logit contributions
atively+0.203
agg+0.196
ya+0.192
eways+0.188
aded+0.187
Neg logit contributions
 Wh-0.059
 Snow-0.055
 still-0.050
 Brown-0.047
 Teddy-0.046
Token a
Token ID257
Feature activation+5.78e-01

Pos logit contributions
atively+0.076
agg+0.073
ya+0.072
eways+0.071
overed+0.070
Neg logit contributions
 Wh-0.031
 Snow-0.029
 Brown-0.025
 still-0.025
 Teddy-0.024
Token few
Token ID1178
Feature activation+3.48e-01

Pos logit contributions
atively+0.035
agg+0.034
overed+0.033
eways+0.032
aded+0.032
Neg logit contributions
 Wh-0.025
 Snow-0.025
 still-0.023
 Brown-0.023
."-0.022
Token seconds
Token ID4201
Feature activation+2.38e+00

Pos logit contributions
atively+0.018
overed+0.017
agg+0.016
ya+0.016
eways+0.015
Neg logit contributions
."-0.018
 hurt-0.018
 Wh-0.018
 still-0.017
 too-0.017
Token amazing
Token ID4998
Feature activation+1.44e+00

Pos logit contributions
 Wh+0.024
 Snow+0.021
 Teddy+0.020
 bleeding+0.019
 Mitt+0.019
Neg logit contributions
atively-0.052
ya-0.051
agg-0.050
eways-0.050
overed-0.048
Token.
Token ID13
Feature activation-1.22e+00

Pos logit contributions
atively+0.109
ya+0.106
agg+0.104
eways+0.103
overed+0.101
Neg logit contributions
 Wh-0.038
 Snow-0.034
 still-0.030
 Teddy-0.029
 Brown-0.029
Token Let
Token ID3914
Feature activation+2.44e+00

Pos logit contributions
 Wh+0.056
 Snow+0.054
 hurt+0.054
 ruined+0.053
 still+0.053
Neg logit contributions
atively-0.062
agg-0.058
ya-0.057
eways-0.057
overed-0.057
Token's
Token ID338
Feature activation-2.35e+00

Pos logit contributions
atively+0.168
agg+0.161
ya+0.160
aded+0.153
eways+0.153
Neg logit contributions
 Wh-0.084
 Snow-0.079
 Brown-0.072
 still-0.072
 Teddy-0.070
Token go
Token ID467
Feature activation-2.72e-01

Pos logit contributions
 Wh+0.100
 Snow+0.095
 bleeding+0.090
 Teddy+0.088
 Brown+0.085
Neg logit contributions
atively-0.134
agg-0.132
ya-0.129
aded-0.124
 traders-0.118
Token closer
Token ID5699
Feature activation+3.57e+00

Pos logit contributions
 Wh+0.009
 Snow+0.009
 Teddy+0.008
 bleeding+0.008
 Brown+0.008
Neg logit contributions
atively-0.018
ya-0.017
agg-0.017
aded-0.016
eways-0.016
Token and
Token ID290
Feature activation-1.55e+00

Pos logit contributions
atively+0.266
ya+0.258
agg+0.256
eways+0.248
overed+0.245
Neg logit contributions
 Wh-0.104
 Snow-0.093
 Teddy-0.084
 Brown-0.081
 still-0.080
Token take
Token ID1011
Feature activation+6.39e-01

Pos logit contributions
 Wh+0.059
 Snow+0.055
 Teddy+0.050
 Brown+0.050
 still+0.049
Neg logit contributions
atively-0.100
ya-0.095
agg-0.095
overed-0.091
eways-0.090
Token a
Token ID257
Feature activation+4.89e-01

Pos logit contributions
atively+0.042
agg+0.039
ya+0.038
eways+0.037
overed+0.037
Neg logit contributions
 Wh-0.026
 Snow-0.025
 Brown-0.023
 Teddy-0.023
."-0.023
Token better
Token ID1365
Feature activation-1.14e+00

Pos logit contributions
atively+0.032
agg+0.030
overed+0.029
eways+0.029
aded+0.029
Neg logit contributions
 Wh-0.019
 Snow-0.019
 Brown-0.017
 Teddy-0.017
 still-0.017
Token look
Token ID804
Feature activation+1.34e+00

Pos logit contributions
 Wh+0.052
 Snow+0.049
 still+0.046
 Teddy+0.046
 Brown+0.045
Neg logit contributions
atively-0.068
agg-0.064
ya-0.063
eways-0.061
overed-0.060
Token€
Token ID26391
Feature activation+2.90e+00

Pos logit contributions
atively+0.072
agg+0.069
ya+0.066
eways+0.064
overed+0.060
Neg logit contributions
 Wh-0.091
 Snow-0.086
 still-0.084
."-0.082
 Brown-0.080
Token�
Token ID129
Feature activation-6.42e-01

Pos logit contributions
atively+0.142
agg+0.132
overed+0.131
eways+0.130
ya+0.128
Neg logit contributions
 Wh-0.138
 Snow-0.133
 Teddy-0.128
 Brown-0.124
 still-0.124
Token�
Token ID241
Feature activation+2.86e+00

Pos logit contributions
 Wh+0.040
 Snow+0.039
 still+0.037
 Brown+0.036
 Teddy+0.036
Neg logit contributions
atively-0.028
agg-0.025
ya-0.024
eways-0.024
overed-0.023
TokenIt
Token ID1026
Feature activation+1.08e+00

Pos logit contributions
atively+0.168
agg+0.156
ya+0.152
eways+0.149
aded+0.147
Neg logit contributions
 Wh-0.135
 Snow-0.130
 still-0.122
."-0.119
 Teddy-0.118
Tokenâ
Token ID22940
Feature activation+2.96e+00

Pos logit contributions
atively+0.077
agg+0.073
ya+0.072
eways+0.070
overed+0.070
Neg logit contributions
 Wh-0.036
 Snow-0.034
 still-0.031
 Brown-0.030
 Teddy-0.030
Token€
Token ID26391
Feature activation+3.24e+00

Pos logit contributions
atively+0.158
agg+0.147
eways+0.144
ya+0.142
overed+0.134
Neg logit contributions
 Wh-0.158
 Snow-0.151
 still-0.144
."-0.143
 Teddy-0.139
Tokenâ„¢
Token ID8151
Feature activation-1.36e+00

Pos logit contributions
atively+0.163
agg+0.159
ya+0.153
eways+0.153
overed+0.152
Neg logit contributions
 Wh-0.150
 Snow-0.144
 still-0.139
 Brown-0.137
 Teddy-0.136
Tokens
Token ID82
Feature activation-1.29e+00

Pos logit contributions
 Snow+0.064
 Wh+0.063
 Brown+0.058
 Teddy+0.056
 still+0.054
Neg logit contributions
atively-0.077
agg-0.072
ya-0.069
eways-0.068
overed-0.067
Token okay
Token ID8788
Feature activation+2.34e-01

Pos logit contributions
 Wh+0.036
 Snow+0.034
 Teddy+0.032
 Brown+0.031
 Mitt+0.027
Neg logit contributions
atively-0.088
aded-0.085
agg-0.084
eways-0.082
overed-0.081
Token,
Token ID11
Feature activation-7.79e-01

Pos logit contributions
atively+0.018
agg+0.017
ya+0.017
eways+0.016
aded+0.016
Neg logit contributions
 Wh-0.006
 Snow-0.006
 still-0.005
 Brown-0.005
 Teddy-0.005
Token it
Token ID340
Feature activation-2.23e-01

Pos logit contributions
 Wh+0.026
 Snow+0.024
 Brown+0.022
 still+0.021
 Teddy+0.021
Neg logit contributions
atively-0.054
agg-0.052
ya-0.052
overed-0.049
aded-0.049
Token to
Token ID284
Feature activation+4.69e-01

Pos logit contributions
atively+0.002
ya+0.002
agg+0.002
eways+0.002
overed+0.002
Neg logit contributions
 Wh-0.001
 Snow-0.001
 Brown-0.001
 Teddy-0.001
 still-0.001
Token grow
Token ID1663
Feature activation-1.91e+00

Pos logit contributions
ya+0.026
agg+0.026
atively+0.026
 arom+0.024
ured+0.024
Neg logit contributions
 Wh-0.020
 Snow-0.018
 Teddy-0.017
 Brown-0.017
 Rat-0.017
Token.
Token ID13
Feature activation-2.32e-01

Pos logit contributions
 Wh+0.068
 Snow+0.061
 Brown+0.056
 Teddy+0.055
 Mitt+0.052
Neg logit contributions
atively-0.133
agg-0.127
ya-0.124
eways-0.123
overed-0.119
Token This
Token ID770
Feature activation+1.39e+00

Pos logit contributions
 Wh+0.007
 Snow+0.007
 still+0.006
 Teddy+0.006
."+0.006
Neg logit contributions
atively-0.017
agg-0.017
ya-0.016
eways-0.016
aded-0.016
Token made
Token ID925
Feature activation-2.02e-01

Pos logit contributions
atively+0.093
agg+0.091
ya+0.091
aded+0.085
eways+0.084
Neg logit contributions
 Wh-0.050
 Snow-0.045
 Brown-0.043
 Teddy-0.042
."-0.041
Token Jack
Token ID3619
Feature activation+3.57e+00

Pos logit contributions
 Wh+0.008
 Snow+0.008
 still+0.008
 Teddy+0.008
 Brown+0.007
Neg logit contributions
atively-0.013
agg-0.012
ya-0.012
overed-0.012
eways-0.012
Token very
Token ID845
Feature activation+3.12e-01

Pos logit contributions
atively+0.254
ya+0.239
agg+0.237
aded+0.228
eways+0.227
Neg logit contributions
 Wh-0.119
 Snow-0.106
 Brown-0.095
 Teddy-0.091
 Mitt-0.086
Token frustrated
Token ID14718
Feature activation+7.86e-02

Pos logit contributions
atively+0.024
agg+0.023
ya+0.022
aded+0.022
eways+0.021
Neg logit contributions
 Wh-0.009
 Snow-0.009
 Brown-0.008
 Teddy-0.007
 Mitt-0.007
Token!
Token ID0
Feature activation+8.49e-01

Pos logit contributions
atively+0.006
ya+0.006
agg+0.006
eways+0.006
overed+0.005
Neg logit contributions
 Wh-0.002
 Snow-0.002
 Brown-0.002
 still-0.002
 Teddy-0.002
Token He
Token ID679
Feature activation+5.62e-01

Pos logit contributions
atively+0.063
agg+0.060
ya+0.059
eways+0.058
overed+0.058
Neg logit contributions
 Wh-0.025
 Snow-0.024
 still-0.021
 Brown-0.021
 Teddy-0.021
Token asked
Token ID1965
Feature activation+4.02e-02

Pos logit contributions
atively+0.037
agg+0.035
ya+0.034
aded+0.033
overed+0.033
Neg logit contributions
 Wh-0.022
 Snow-0.021
 Brown-0.019
 Teddy-0.019
."-0.018
Token proud
Token ID6613
Feature activation+1.47e+00

Pos logit contributions
 Wh+0.020
 Snow+0.017
un+0.017
 Rat+0.016
 Mitt+0.016
Neg logit contributions
agg-0.031
atively-0.030
ya-0.030
aded-0.029
 arom-0.028
Token of
Token ID286
Feature activation-1.85e+00

Pos logit contributions
atively+0.094
agg+0.091
ya+0.090
overed+0.086
eways+0.086
Neg logit contributions
 Wh-0.056
 Snow-0.051
 Brown-0.046
 Mitt-0.044
 Teddy-0.044
Token her
Token ID607
Feature activation-1.15e+00

Pos logit contributions
 Wh+0.077
 Snow+0.073
 Brown+0.067
 Teddy+0.067
 still+0.066
Neg logit contributions
atively-0.112
agg-0.108
ya-0.106
eways-0.101
overed-0.101
Token for
Token ID329
Feature activation+3.98e-01

Pos logit contributions
 Wh+0.030
 Snow+0.027
 Teddy+0.023
 Brown+0.022
 Mitt+0.022
Neg logit contributions
atively-0.089
ya-0.084
agg-0.083
overed-0.081
eways-0.081
Token being
Token ID852
Feature activation-4.38e-03

Pos logit contributions
atively+0.026
agg+0.024
ya+0.024
eways+0.023
aded+0.023
Neg logit contributions
 Wh-0.015
 Snow-0.015
 Brown-0.013
 Teddy-0.013
 still-0.013
Token brave
Token ID14802
Feature activation-3.20e-02

Pos logit contributions
 Wh+0.000
 Snow+0.000
 Brown+0.000
 Teddy+0.000
 still+0.000
Neg logit contributions
atively-0.000
agg-0.000
ya-0.000
aded-0.000
eways-0.000
Token and
Token ID290
Feature activation-7.81e-01

Pos logit contributions
 Wh+0.001
 Snow+0.001
 Brown+0.001
 still+0.001
 Teddy+0.001
Neg logit contributions
atively-0.002
ya-0.002
agg-0.002
eways-0.002
overed-0.002
Token honest
Token ID5508
Feature activation-1.18e+00

Pos logit contributions
 Wh+0.034
 Snow+0.032
 Brown+0.030
 Teddy+0.030
 still+0.029
Neg logit contributions
atively-0.047
agg-0.044
ya-0.043
overed-0.042
aded-0.042
Token.
Token ID13
Feature activation-1.89e-01

Pos logit contributions
 Wh+0.031
 Snow+0.027
 Teddy+0.023
 Mitt+0.023
 Brown+0.023
Neg logit contributions
atively-0.092
ya-0.086
agg-0.085
eways-0.084
overed-0.084
Token They
Token ID1119
Feature activation+6.50e-01

Pos logit contributions
 Wh+0.007
 bleeding+0.006
 hurt+0.006
 ruined+0.006
 still+0.006
Neg logit contributions
atively-0.011
agg-0.011
ya-0.011
overed-0.010
eways-0.010
Token said
Token ID531
Feature activation+7.42e-01

Pos logit contributions
atively+0.033
agg+0.031
ya+0.030
aded+0.026
 arom+0.025
Neg logit contributions
 Wh-0.034
 Snow-0.031
 Brown-0.030
 my-0.029
 Mitt-0.029
Token started
Token ID2067
Feature activation-8.84e-01

Pos logit contributions
atively+0.025
agg+0.024
ya+0.023
eways+0.023
overed+0.022
Neg logit contributions
 Wh-0.016
 Snow-0.015
 still-0.014
 Brown-0.014
 Teddy-0.014
Token running
Token ID2491
Feature activation+1.68e+00

Pos logit contributions
 Wh+0.024
 Snow+0.021
 still+0.020
 Brown+0.019
."+0.018
Neg logit contributions
atively-0.071
agg-0.069
ya-0.067
eways-0.065
aded-0.064
Token as
Token ID355
Feature activation+6.41e-01

Pos logit contributions
atively+0.129
agg+0.126
ya+0.122
aded+0.120
eways+0.119
Neg logit contributions
 Wh-0.046
 Snow-0.042
 still-0.039
 Brown-0.037
."-0.037
Token fast
Token ID3049
Feature activation-1.60e+00

Pos logit contributions
atively+0.051
agg+0.049
ya+0.048
aded+0.047
eways+0.047
Neg logit contributions
 Wh-0.017
 Snow-0.016
 still-0.014
 Brown-0.013
 Teddy-0.013
Token as
Token ID355
Feature activation+4.39e-01

Pos logit contributions
 Wh+0.057
 Snow+0.054
 still+0.048
 Brown+0.048
 Teddy+0.048
Neg logit contributions
atively-0.112
agg-0.108
ya-0.105
eways-0.103
aded-0.101
Token they
Token ID484
Feature activation+8.81e-03

Pos logit contributions
atively+0.027
agg+0.025
ya+0.025
eways+0.024
overed+0.024
Neg logit contributions
 Wh-0.019
 Snow-0.018
 still-0.017
 Brown-0.017
 Teddy-0.017
Token could
Token ID714
Feature activation-2.82e+00

Pos logit contributions
atively+0.001
agg+0.001
overed+0.001
ya+0.001
eways+0.001
Neg logit contributions
 Wh-0.000
 Snow-0.000
 Brown-0.000
 Mitt-0.000
 Teddy-0.000
Token.
Token ID13
Feature activation-1.70e-02

Pos logit contributions
 Wh+0.070
 Snow+0.065
 Brown+0.055
 Teddy+0.055
 still+0.053
Neg logit contributions
atively-0.226
agg-0.214
ya-0.210
eways-0.207
overed-0.207
Token
Token ID198
Feature activation-4.60e-01

Pos logit contributions
 Wh+0.000
 Snow+0.000
 still+0.000
 Brown+0.000
 Teddy+0.000
Neg logit contributions
atively-0.001
agg-0.001
ya-0.001
eways-0.001
overed-0.001
Token
Token ID198
Feature activation-6.09e-01

Pos logit contributions
 Wh+0.011
 Snow+0.010
 Teddy+0.008
 Brown+0.008
 still+0.008
Neg logit contributions
atively-0.037
agg-0.035
eways-0.034
ya-0.034
overed-0.034
TokenAs
Token ID1722
Feature activation-5.20e-01

Pos logit contributions
 Wh+0.031
 Snow+0.029
 still+0.028
."+0.027
 Brown+0.026
Neg logit contributions
atively-0.034
agg-0.032
ya-0.032
eways-0.030
overed-0.029
Token boy
Token ID2933
Feature activation+1.35e+00

Pos logit contributions
 Wh+0.006
 Snow+0.006
 still+0.005
 Brown+0.005
 Teddy+0.005
Neg logit contributions
atively-0.008
agg-0.007
ya-0.007
eways-0.007
aded-0.007
Token named
Token ID3706
Feature activation-3.63e+00

Pos logit contributions
ya+0.081
agg+0.078
atively+0.077
aded+0.076
eways+0.074
Neg logit contributions
 Wh-0.043
 Snow-0.043
 still-0.040
 Teddy-0.038
 Brown-0.038
Token Tim
Token ID5045
Feature activation-1.34e-01

Pos logit contributions
 heals+0.118
 Wh+0.114
 Snow+0.113
 bleeding+0.112
 wing+0.112
Neg logit contributions
atively-0.213
agg-0.192
ya-0.188
eways-0.188
 Kevin-0.183
Tokenmy
Token ID1820
Feature activation-7.72e-01

Pos logit contributions
 Wh+0.005
 Snow+0.005
 Mitt+0.005
 Ho+0.004
 Fl+0.004
Neg logit contributions
ya-0.007
atively-0.007
eways-0.007
urious-0.006
Kevin-0.006
Token.
Token ID13
Feature activation-1.80e+00

Pos logit contributions
 Wh+0.028
 Snow+0.024
 Teddy+0.024
 Velvet+0.024
 my+0.023
Neg logit contributions
ya-0.041
ager-0.040
atively-0.039
eways-0.036
agg-0.036
Token Tim
Token ID5045
Feature activation+7.00e-01

Pos logit contributions
 Snow+0.050
 Wh+0.048
 still+0.045
 hurt+0.043
."+0.043
Neg logit contributions
atively-0.125
eways-0.118
agg-0.117
aded-0.112
 flavours-0.112
Tokenmy
Token ID1820
Feature activation+7.36e-03

Pos logit contributions
ya+0.041
agg+0.039
anne+0.038
ager+0.038
atively+0.038
Neg logit contributions
 Wh-0.025
 Snow-0.022
 Mitt-0.021
 Ho-0.021
 Fl-0.019
Token had
Token ID550
Feature activation-1.29e+00

Pos logit contributions
ya+0.000
atively+0.000
agg+0.000
ager+0.000
anne+0.000
Neg logit contributions
 Wh-0.000
 Snow-0.000
 Mitt-0.000
 bruised-0.000
 Brown-0.000
Token a
Token ID257
Feature activation+1.73e+00

Pos logit contributions
 Wh+0.050
."+0.049
 Snow+0.045
 heals+0.044
 bruised+0.043
Neg logit contributions
atively-0.065
agg-0.064
aded-0.063
Kevin-0.060
ya-0.060
Token tutor
Token ID48680
Feature activation+1.66e+00

Pos logit contributions
atively+0.119
agg+0.113
ya+0.113
aded+0.107
 arom+0.105
Neg logit contributions
 Wh-0.058
 Snow-0.055
."-0.050
 Brown-0.049
 still-0.048
Token named
Token ID3706
Feature activation-2.87e+00

Pos logit contributions
ya+0.101
atively+0.100
agg+0.094
 traders+0.089
den+0.089
Neg logit contributions
 Wh-0.058
 Snow-0.055
 still-0.048
 Mitt-0.048
 bleeding-0.047
Token are
Token ID389
Feature activation+4.99e-01

Pos logit contributions
atively+0.063
ya+0.057
Whoever+0.056
 traders+0.055
agg+0.055
Neg logit contributions
 Wh-0.043
 Snow-0.041
 Brown-0.039
 bleeding-0.038
 Teddy-0.037
Token happy
Token ID3772
Feature activation+2.36e-01

Pos logit contributions
atively+0.025
agg+0.023
aded+0.022
overed+0.022
 intrigued+0.021
Neg logit contributions
 Wh-0.022
 Snow-0.022
 Rat-0.021
 Brown-0.020
 Teddy-0.020
Token and
Token ID290
Feature activation+4.27e-01

Pos logit contributions
atively+0.017
overed+0.016
agg+0.015
ya+0.015
eways+0.015
Neg logit contributions
 Wh-0.007
 Snow-0.006
 Mitt-0.006
 Teddy-0.006
 Brown-0.006
Token quiet
Token ID5897
Feature activation+1.00e-01

Pos logit contributions
atively+0.026
overed+0.024
ya+0.024
agg+0.024
eways+0.023
Neg logit contributions
 Wh-0.017
 Snow-0.016
 Brown-0.015
 Teddy-0.014
 Mitt-0.014
Token.
Token ID13
Feature activation+9.29e-02

Pos logit contributions
atively+0.007
overed+0.007
eways+0.007
ya+0.006
agg+0.006
Neg logit contributions
 Wh-0.003
 Snow-0.003
 Mitt-0.003
 Teddy-0.003
 Brown-0.002
Token
Token ID198
Feature activation-2.40e-02

Pos logit contributions
atively+0.006
agg+0.006
eways+0.006
ya+0.006
overed+0.006
Neg logit contributions
 Wh-0.003
 Snow-0.003
 ac-0.003
 bleeding-0.003
 Brown-0.003
Token
Token ID198
Feature activation-2.88e-01

Pos logit contributions
 Wh+0.001
 bruised+0.001
 Snow+0.001
 Brown+0.001
 Teddy+0.001
Neg logit contributions
agg-0.001
atively-0.001
eways-0.001
ya-0.001
overed-0.001
TokenThe
Token ID464
Feature activation-1.16e+00

Pos logit contributions
 Wh+0.011
 Snow+0.011
 still+0.010
."+0.009
 Teddy+0.009
Neg logit contributions
atively-0.019
agg-0.018
ya-0.018
overed-0.018
eways-0.018
Token old
Token ID1468
Feature activation-1.62e+00

Pos logit contributions
 Wh+0.047
 Snow+0.045
 still+0.042
 Brown+0.041
 Teddy+0.040
Neg logit contributions
atively-0.075
agg-0.071
ya-0.070
eways-0.069
aded-0.068
Token lady
Token ID10846
Feature activation+4.22e-01

Pos logit contributions
 Wh+0.069
 Snow+0.066
 still+0.062
."+0.060
 Brown+0.060
Neg logit contributions
atively-0.101
agg-0.097
eways-0.095
aded-0.094
ya-0.093
Token is
Token ID318
Feature activation+4.06e-01

Pos logit contributions
atively+0.026
agg+0.024
ya+0.024
eways+0.023
overed+0.023
Neg logit contributions
 Wh-0.018
 Snow-0.018
 still-0.016
 Brown-0.016
 Teddy-0.016
Token.
Token ID13
Feature activation-2.91e-01

Pos logit contributions
 Wh+0.010
 Snow+0.009
 Mitt+0.008
 Teddy+0.008
 still+0.007
Neg logit contributions
atively-0.023
overed-0.022
agg-0.021
ya-0.021
eways-0.021
Token She
Token ID1375
Feature activation-1.35e+00

Pos logit contributions
 hurt+0.013
 bruised+0.013
 ac+0.012
 ruined+0.012
 bleeding+0.012
Neg logit contributions
atively-0.014
eways-0.014
 Sure-0.014
overed-0.014
agg-0.013
Token couldn
Token ID3521
Feature activation-3.43e+00

Pos logit contributions
 Wh+0.067
 bruised+0.059
 Brown+0.056
 bleeding+0.056
arl+0.053
Neg logit contributions
ya-0.070
agg-0.065
atively-0.064
mber-0.061
overed-0.056
Token't
Token ID470
Feature activation-3.09e+00

Pos logit contributions
 Wh+0.129
 Snow+0.124
 bruised+0.120
 Brown+0.114
 Teddy+0.113
Neg logit contributions
atively-0.211
overed-0.199
agg-0.199
ued-0.191
aded-0.188
Token wait
Token ID4043
Feature activation+2.17e+00

Pos logit contributions
 Wh+0.203
 Snow+0.192
 Brown+0.183
 Mitt+0.182
 Teddy+0.180
Neg logit contributions
atively-0.121
agg-0.109
ya-0.109
overed-0.092
ued-0.091
Token to
Token ID284
Feature activation+2.45e-01

Pos logit contributions
atively+0.172
agg+0.164
ya+0.161
eways+0.158
overed+0.157
Neg logit contributions
 Wh-0.054
 Snow-0.052
 still-0.046
 Teddy-0.044
 Brown-0.043
Token sing
Token ID1702
Feature activation-2.21e+00

Pos logit contributions
ya+0.010
agg+0.010
 sermon+0.009
Kevin+0.009
aded+0.009
Neg logit contributions
 Wh-0.013
 bruised-0.011
 bleeding-0.011
 Snow-0.011
 Mitt-0.011
Token with
Token ID351
Feature activation+8.02e-01

Pos logit contributions
 Wh+0.070
 Snow+0.065
 Brown+0.058
 still+0.058
 Teddy+0.057
Neg logit contributions
atively-0.160
agg-0.152
ya-0.150
eways-0.146
overed-0.145
Token Max
Token ID5436
Feature activation+1.73e-01

Pos logit contributions
atively+0.043
ya+0.042
agg+0.041
 arom+0.039
 avail+0.038
Neg logit contributions
 Wh-0.031
 Snow-0.028
."-0.028
 bruised-0.028
 Brown-0.027
Token again
Token ID757
Feature activation-8.74e-01

Pos logit contributions
atively+0.011
ya+0.011
agg+0.010
overed+0.010
eways+0.010
Neg logit contributions
 Wh-0.006
 Snow-0.005
 bleeding-0.005
 hurt-0.005
 ruined-0.005
Token tomorrow
Token ID9439
Feature activation-1.16e+00

Pos logit contributions
 Wh+0.031
 Snow+0.027
 Brown+0.025
 Teddy+0.024
 bleeding+0.023
Neg logit contributions
ya-0.059
atively-0.058
agg-0.056
overed-0.052
eways-0.052
Token in
Token ID287
Feature activation+1.86e+00

Pos logit contributions
atively+0.163
agg+0.156
ya+0.154
eways+0.150
overed+0.149
Neg logit contributions
 Wh-0.059
 Snow-0.056
 still-0.051
 Brown-0.049
 Teddy-0.049
Token the
Token ID262
Feature activation+7.79e-01

Pos logit contributions
atively+0.131
agg+0.124
ya+0.121
eways+0.118
 arom+0.117
Neg logit contributions
 Wh-0.059
 Snow-0.053
 Teddy-0.047
 still-0.046
 Brown-0.046
Token oven
Token ID14361
Feature activation+1.66e-01

Pos logit contributions
atively+0.041
agg+0.039
ya+0.038
eways+0.038
overed+0.037
Neg logit contributions
 Wh-0.040
 Snow-0.039
 still-0.037
."-0.036
 Brown-0.036
Token.
Token ID13
Feature activation+2.01e-01

Pos logit contributions
atively+0.013
agg+0.012
ya+0.012
eways+0.012
overed+0.012
Neg logit contributions
 Wh-0.004
 Snow-0.004
 still-0.003
 Brown-0.003
 Teddy-0.003
Token When
Token ID1649
Feature activation-8.61e-02

Pos logit contributions
atively+0.013
agg+0.013
overed+0.012
eways+0.012
ya+0.012
Neg logit contributions
 Wh-0.007
 Snow-0.006
 still-0.006
 ruined-0.006
 hurt-0.006
Token it
Token ID340
Feature activation-1.05e+00

Pos logit contributions
 Wh+0.003
 Snow+0.002
 still+0.002
 Brown+0.002
 Teddy+0.002
Neg logit contributions
atively-0.006
agg-0.006
ya-0.006
overed-0.006
aded-0.006
Token was
Token ID373
Feature activation-2.01e+00

Pos logit contributions
 Wh+0.036
 Snow+0.034
 still+0.031
 Brown+0.031
 Teddy+0.030
Neg logit contributions
atively-0.074
agg-0.070
ya-0.069
eways-0.067
overed-0.067
Token done
Token ID1760
Feature activation-6.16e-01

Pos logit contributions
 Wh+0.076
 Snow+0.071
 Brown+0.064
 Teddy+0.064
 still+0.061
Neg logit contributions
atively-0.136
agg-0.130
ya-0.125
aded-0.123
overed-0.122
Token,
Token ID11
Feature activation-3.14e-01

Pos logit contributions
 Wh+0.011
 Snow+0.010
 Brown+0.009
 Teddy+0.008
 still+0.008
Neg logit contributions
atively-0.054
ya-0.053
agg-0.052
eways-0.052
aded-0.050
Token it
Token ID340
Feature activation+2.60e-01

Pos logit contributions
 Wh+0.010
 Snow+0.009
 Teddy+0.008
."+0.008
 Brown+0.008
Neg logit contributions
atively-0.022
agg-0.020
ya-0.020
overed-0.020
 arom-0.019
Token took
Token ID1718
Feature activation+8.05e-01

Pos logit contributions
atively+0.017
agg+0.016
ya+0.015
aded+0.015
overed+0.015
Neg logit contributions
 Wh-0.011
 Snow-0.010
 Brown-0.009
 Teddy-0.009
."-0.009
Token!"
Token ID2474
Feature activation+4.77e-01

Pos logit contributions
 Wh+0.057
 Snow+0.050
 still+0.050
 bleeding+0.047
 Teddy+0.047
Neg logit contributions
ya-0.091
atively-0.087
agg-0.083
eways-0.079
anne-0.077
Token said
Token ID531
Feature activation+1.03e-01

Pos logit contributions
atively+0.036
agg+0.035
eways+0.034
ya+0.033
aded+0.033
Neg logit contributions
 Wh-0.015
 Snow-0.014
 Teddy-0.013
 Brown-0.013
 still-0.012
Token her
Token ID607
Feature activation-1.39e+00

Pos logit contributions
atively+0.008
agg+0.008
ya+0.008
eways+0.008
aded+0.008
Neg logit contributions
 Wh-0.002
 Snow-0.002
 Brown-0.002
 Teddy-0.002
 still-0.002
Token cat
Token ID3797
Feature activation-2.35e+00

Pos logit contributions
 Wh+0.030
 Snow+0.026
 still+0.022
 Teddy+0.021
 Brown+0.021
Neg logit contributions
atively-0.116
agg-0.111
ya-0.109
eways-0.106
overed-0.106
Token,
Token ID11
Feature activation+2.30e-01

Pos logit contributions
 Wh+0.051
 Snow+0.047
 still+0.040
 Teddy+0.039
 Brown+0.038
Neg logit contributions
atively-0.191
agg-0.181
ya-0.180
eways-0.176
overed-0.175
Token Mitt
Token ID16627
Feature activation-2.49e+00

Pos logit contributions
atively+0.013
ya+0.012
agg+0.012
overed+0.012
aded+0.011
Neg logit contributions
 Wh-0.011
 Snow-0.010
 Teddy-0.009
 Brown-0.009
 still-0.009
Tokenens
Token ID641
Feature activation-1.84e+00

Pos logit contributions
 Wh+0.086
 Snow+0.081
 still+0.078
 Brown+0.075
 Teddy+0.073
Neg logit contributions
atively-0.168
ya-0.158
agg-0.158
eways-0.150
overed-0.149
Token.
Token ID13
Feature activation-6.11e-01

Pos logit contributions
 Wh+0.041
 Snow+0.037
 still+0.031
 Teddy+0.031
 Brown+0.031
Neg logit contributions
atively-0.149
agg-0.141
ya-0.140
overed-0.136
eways-0.136
Token
Token ID198
Feature activation-4.12e-01

Pos logit contributions
 ruined+0.025
 lose+0.024
 still+0.024
 Wh+0.024
 least+0.024
Neg logit contributions
atively-0.033
overed-0.028
agg-0.028
ya-0.027
mber-0.026
Token
Token ID198
Feature activation-5.72e-01

Pos logit contributions
 Wh+0.012
 Snow+0.011
 bruised+0.011
 bleeding+0.010
 still+0.010
Neg logit contributions
atively-0.028
agg-0.028
eways-0.027
ya-0.026
aded-0.026
Token"
Token ID1
Feature activation+1.73e+00

Pos logit contributions
 Wh+0.023
 Snow+0.022
 Brown+0.020
 still+0.020
 Teddy+0.020
Neg logit contributions
atively-0.037
agg-0.035
ya-0.034
eways-0.033
aded-0.033
Token.
Token ID13
Feature activation+1.17e-01

Pos logit contributions
 Wh+0.027
 Snow+0.024
 Brown+0.021
 still+0.021
 Teddy+0.021
Neg logit contributions
atively-0.057
ya-0.053
overed-0.053
eways-0.052
agg-0.052
Token
Token ID198
Feature activation-3.82e-01

Pos logit contributions
atively+0.010
agg+0.010
ya+0.009
eways+0.009
aded+0.009
Neg logit contributions
 Wh-0.003
 Snow-0.002
 Brown-0.002
 Teddy-0.002
 still-0.002
Token
Token ID198
Feature activation-5.95e-01

Pos logit contributions
 Wh+0.007
 Snow+0.006
 still+0.005
 Brown+0.005
 Teddy+0.005
Neg logit contributions
atively-0.033
agg-0.031
ya-0.031
eways-0.030
overed-0.030
Tokenâ
Token ID22940
Feature activation+2.11e+00

Pos logit contributions
 Wh+0.024
 Snow+0.022
 still+0.020
 Teddy+0.020
 Brown+0.020
Neg logit contributions
atively-0.041
agg-0.038
ya-0.038
overed-0.037
 arom-0.036
Token€
Token ID26391
Feature activation+2.48e+00

Pos logit contributions
atively+0.105
agg+0.098
eways+0.094
ya+0.093
overed+0.090
Neg logit contributions
 Wh-0.118
 Snow-0.114
 still-0.109
 Teddy-0.106
 Brown-0.105
Token�
Token ID129
Feature activation-1.16e+00

Pos logit contributions
atively+0.141
agg+0.133
ya+0.131
eways+0.130
overed+0.128
Neg logit contributions
 Wh-0.101
 Snow-0.096
 still-0.095
 Teddy-0.092
."-0.091
Token�
Token ID241
Feature activation+2.15e+00

Pos logit contributions
 Wh+0.072
 Snow+0.070
 still+0.066
 Brown+0.066
 Teddy+0.066
Neg logit contributions
atively-0.049
agg-0.045
ya-0.044
eways-0.042
overed-0.041
TokenOh
Token ID5812
Feature activation+1.60e+00

Pos logit contributions
atively+0.122
agg+0.114
ya+0.111
eways+0.108
overed+0.107
Neg logit contributions
 Wh-0.103
 Snow-0.100
 still-0.093
 Brown-0.092
 Teddy-0.091
Token no
Token ID645
Feature activation-3.62e+00

Pos logit contributions
atively+0.097
 inspection+0.092
ya+0.092
agg+0.092
 arom+0.087
Neg logit contributions
 heals-0.048
 still-0.046
 Wh-0.045
 Snow-0.044
my-0.041
Token!
Token ID0
Feature activation-2.41e-01

Pos logit contributions
 Wh+0.124
 Snow+0.119
 still+0.112
 Teddy+0.108
 Brown+0.107
Neg logit contributions
atively-0.236
ya-0.230
agg-0.227
aded-0.219
 arom-0.217
Tokenâ
Token ID22940
Feature activation+2.03e+00

Pos logit contributions
 Wh+0.009
 still+0.008
 Snow+0.008
 ruined+0.008
."+0.008
Neg logit contributions
atively-0.015
agg-0.014
ya-0.014
overed-0.014
aded-0.013
Token to
Token ID284
Feature activation+8.99e-01

Pos logit contributions
 Wh+0.108
 Snow+0.102
 Teddy+0.094
 Brown+0.092
 still+0.085
Neg logit contributions
atively-0.181
agg-0.177
ya-0.174
eways-0.169
overed-0.168
Token find
Token ID1064
Feature activation-3.28e-01

Pos logit contributions
atively+0.049
agg+0.048
aded+0.046
ya+0.043
 traders+0.041
Neg logit contributions
 Wh-0.041
 Snow-0.039
 Teddy-0.038
 Brown-0.037
 bleeding-0.035
Token a
Token ID257
Feature activation+5.13e-01

Pos logit contributions
 Wh+0.010
 Snow+0.010
 still+0.009
 Brown+0.009
 Teddy+0.009
Neg logit contributions
atively-0.024
agg-0.023
ya-0.022
eways-0.022
aded-0.022
Token way
Token ID835
Feature activation+3.11e-02

Pos logit contributions
atively+0.035
agg+0.034
ya+0.033
aded+0.032
eways+0.032
Neg logit contributions
 Wh-0.017
 Snow-0.016
 Teddy-0.015
 Brown-0.014
."-0.014
Token to
Token ID284
Feature activation+6.43e-01

Pos logit contributions
atively+0.002
agg+0.002
eways+0.002
ya+0.002
overed+0.002
Neg logit contributions
 Wh-0.001
 Snow-0.001
 Teddy-0.001
 Brown-0.001
 Mitt-0.001
Token get
Token ID651
Feature activation-1.27e+00

Pos logit contributions
atively+0.039
agg+0.037
aded+0.036
ya+0.035
overed+0.034
Neg logit contributions
 Wh-0.026
 Snow-0.025
 Teddy-0.024
 Brown-0.024
."-0.022
Token home
Token ID1363
Feature activation-1.68e+00

Pos logit contributions
 Wh+0.040
 Snow+0.037
 Brown+0.033
 Teddy+0.033
 still+0.031
Neg logit contributions
atively-0.091
agg-0.087
ya-0.084
aded-0.084
overed-0.083
Token.
Token ID13
Feature activation+1.49e-01

Pos logit contributions
 Wh+0.044
 Snow+0.039
 Teddy+0.032
 Brown+0.032
 Mitt+0.030
Neg logit contributions
atively-0.131
agg-0.125
ya-0.123
eways-0.120
overed-0.119
Token She
Token ID1375
Feature activation-1.16e+00

Pos logit contributions
atively+0.009
agg+0.009
overed+0.008
ya+0.008
eways+0.008
Neg logit contributions
 ruined-0.006
 hurt-0.006
 Wh-0.005
 bleeding-0.005
 still-0.005
Token smiled
Token ID13541
Feature activation+8.71e-01

Pos logit contributions
 Wh+0.047
 Snow+0.041
 Brown+0.040
 Teddy+0.039
."+0.039
Neg logit contributions
atively-0.074
agg-0.072
ya-0.070
aded-0.066
overed-0.065
Token and
Token ID290
Feature activation+8.19e-01

Pos logit contributions
atively+0.064
agg+0.059
ya+0.058
overed+0.057
eways+0.055
Neg logit contributions
 Wh-0.030
 Snow-0.026
 Brown-0.023
 Teddy-0.023
 Mitt-0.022
Token,
Token ID11
Feature activation+4.64e-01

Pos logit contributions
atively+0.032
overed+0.029
eways+0.029
ya+0.029
agg+0.028
Neg logit contributions
 Wh-0.011
 Snow-0.011
 Teddy-0.009
 Brown-0.009
 Mitt-0.008
Token but
Token ID475
Feature activation+1.53e+00

Pos logit contributions
atively+0.029
ya+0.026
agg+0.026
overed+0.026
aded+0.025
Neg logit contributions
 Wh-0.019
 Snow-0.018
 Brown-0.017
 Teddy-0.017
."-0.017
Token the
Token ID262
Feature activation-3.69e-01

Pos logit contributions
atively+0.104
ya+0.095
overed+0.095
agg+0.095
eways+0.092
Neg logit contributions
 Wh-0.051
 Snow-0.049
."-0.046
 Brown-0.045
 Teddy-0.044
Token dog
Token ID3290
Feature activation-1.09e+00

Pos logit contributions
 Wh+0.011
 Snow+0.011
 Brown+0.010
 Teddy+0.009
 still+0.009
Neg logit contributions
atively-0.027
agg-0.025
ya-0.025
eways-0.025
overed-0.025
Token wouldn
Token ID3636
Feature activation-2.10e+00

Pos logit contributions
 Wh+0.037
 Snow+0.036
 Brown+0.033
 Teddy+0.033
."+0.032
Neg logit contributions
atively-0.075
agg-0.069
ya-0.069
aded-0.067
overed-0.067
Token't
Token ID470
Feature activation-3.37e+00

Pos logit contributions
 Wh+0.083
 Snow+0.080
 bruised+0.073
 Teddy+0.072
 Brown+0.072
Neg logit contributions
atively-0.123
ued-0.114
Run-0.112
overed-0.112
agg-0.108
Token leave
Token ID2666
Feature activation-3.27e+00

Pos logit contributions
 Wh+0.141
 Snow+0.136
 Teddy+0.127
 Brown+0.125
 Mitt+0.122
Neg logit contributions
atively-0.206
ya-0.188
agg-0.187
eways-0.180
aded-0.178
Token him
Token ID683
Feature activation+5.44e-01

Pos logit contributions
 Wh+0.111
 Snow+0.104
 Teddy+0.094
 Brown+0.094
 still+0.092
Neg logit contributions
atively-0.221
ya-0.202
agg-0.199
eways-0.198
overed-0.197
Token alone
Token ID3436
Feature activation-3.61e+00

Pos logit contributions
atively+0.038
ya+0.035
ued+0.034
eways+0.034
overed+0.034
Neg logit contributions
 Wh-0.017
 Snow-0.016
 Brown-0.014
 Teddy-0.014
 Mitt-0.013
Token.
Token ID13
Feature activation-1.58e-02

Pos logit contributions
 Wh+0.105
 Snow+0.098
 Teddy+0.082
 Brown+0.082
 Mitt+0.081
Neg logit contributions
atively-0.270
overed-0.248
ya-0.247
eways-0.246
agg-0.243
Token
Token ID198
Feature activation-4.92e-01

Pos logit contributions
 Snow+0.000
 Wh+0.000
 Teddy+0.000
 still+0.000
 Brown+0.000
Neg logit contributions
atively-0.001
agg-0.001
overed-0.001
eways-0.001
ya-0.001
Token"
Token ID1
Feature activation+1.35e+00

Pos logit contributions
 Wh+0.022
 Snow+0.021
 still+0.019
 Brown+0.019
 Teddy+0.019
Neg logit contributions
atively-0.029
agg-0.028
ya-0.027
eways-0.026
overed-0.026
TokenReally
Token ID26392
Feature activation+3.94e+00

Pos logit contributions
atively+0.077
agg+0.073
ya+0.073
eways+0.072
aded+0.069
Neg logit contributions
 Wh-0.066
 Snow-0.063
 still-0.063
 Teddy-0.057
."-0.056
Token?
Token ID30
Feature activation-7.28e-01

Pos logit contributions
atively+0.305
agg+0.295
ya+0.289
eways+0.282
overed+0.282
Neg logit contributions
 Wh-0.104
 Snow-0.095
 Brown-0.083
 Teddy-0.080
 still-0.079
Token Do
Token ID2141
Feature activation+4.42e-01

Pos logit contributions
 Wh+0.031
 Snow+0.030
 still+0.028
 Brown+0.028
 Teddy+0.027
Neg logit contributions
atively-0.043
agg-0.040
ya-0.039
overed-0.039
eways-0.038
Token you
Token ID345
Feature activation-2.80e-01

Pos logit contributions
atively+0.031
agg+0.029
ya+0.029
eways+0.028
overed+0.028
Neg logit contributions
 Wh-0.015
 Snow-0.014
 Brown-0.013
 Teddy-0.012
 still-0.012
Token still
Token ID991
Feature activation-4.84e+00

Pos logit contributions
 Wh+0.013
 Snow+0.013
 Brown+0.012
 Teddy+0.011
 Fl+0.011
Neg logit contributions
atively-0.016
agg-0.015
aded-0.015
ya-0.015
 phrase-0.014
Token want
Token ID765
Feature activation-8.41e-01

Pos logit contributions
 Snow+0.163
 Wh+0.162
 Brown+0.142
 Teddy+0.137
 Mitt+0.136
Neg logit contributions
ya-0.279
atively-0.278
aded-0.277
agg-0.271
 traders-0.266
Token to
Token ID284
Feature activation-2.30e-01

Pos logit contributions
 Wh+0.026
 Snow+0.025
 still+0.022
 Brown+0.022
 Teddy+0.021
Neg logit contributions
atively-0.061
agg-0.058
ya-0.057
eways-0.056
aded-0.055
Token play
Token ID711
Feature activation-1.52e+00

Pos logit contributions
 Wh+0.010
 Snow+0.010
 bruised+0.010
 bleeding+0.010
 Mitt+0.009
Neg logit contributions
ades-0.010
atively-0.010
agg-0.010
 competition-0.009
 pillars-0.009
Token with
Token ID351
Feature activation+3.27e-02

Pos logit contributions
 Wh+0.048
 Snow+0.046
 Brown+0.040
 Teddy+0.039
 still+0.039
Neg logit contributions
atively-0.109
agg-0.102
ya-0.101
overed-0.099
aded-0.099
Token me
Token ID502
Feature activation+3.66e-01

Pos logit contributions
atively+0.002
agg+0.002
ya+0.002
eways+0.002
aded+0.002
Neg logit contributions
 Wh-0.001
 Snow-0.001
 Brown-0.001
 still-0.001
 Teddy-0.001
Token being
Token ID852
Feature activation+6.57e-01

Pos logit contributions
atively+0.042
ya+0.039
agg+0.039
overed+0.038
eways+0.037
Neg logit contributions
 Wh-0.024
 Snow-0.022
 Brown-0.020
 Teddy-0.020
."-0.020
Token extra
Token ID3131
Feature activation-3.16e-01

Pos logit contributions
atively+0.045
agg+0.043
ya+0.042
eways+0.041
aded+0.040
Neg logit contributions
 Wh-0.024
 Snow-0.022
 Brown-0.020
 still-0.020
 Teddy-0.020
Token careful
Token ID8161
Feature activation+7.66e-01

Pos logit contributions
 Wh+0.012
 Snow+0.012
 still+0.011
 Brown+0.010
 Teddy+0.010
Neg logit contributions
atively-0.021
agg-0.020
ya-0.020
eways-0.019
overed-0.019
Token not
Token ID407
Feature activation-3.59e+00

Pos logit contributions
atively+0.059
agg+0.056
ya+0.055
eways+0.054
overed+0.054
Neg logit contributions
 Wh-0.021
 Snow-0.020
 Brown-0.017
 Teddy-0.017
 still-0.016
Token to
Token ID284
Feature activation-7.83e-01

Pos logit contributions
 Wh+0.119
 Snow+0.114
 Teddy+0.104
 Brown+0.102
 still+0.099
Neg logit contributions
atively-0.243
ya-0.229
agg-0.226
eways-0.223
overed-0.221
Token hurt
Token ID5938
Feature activation-6.12e+00

Pos logit contributions
 Snow+0.029
 Wh+0.029
 Teddy+0.027
 Brown+0.027
 still+0.025
Neg logit contributions
atively-0.046
ya-0.045
agg-0.043
aded-0.042
 flavours-0.041
Token it
Token ID340
Feature activation-6.83e-01

Pos logit contributions
 Wh+0.200
 Snow+0.189
 still+0.169
 Brown+0.169
 Teddy+0.166
Neg logit contributions
atively-0.426
ya-0.405
agg-0.403
eways-0.392
overed-0.385
Token.
Token ID13
Feature activation-4.95e-02

Pos logit contributions
 Wh+0.020
 Snow+0.019
 Brown+0.016
 Teddy+0.015
 Mitt+0.014
Neg logit contributions
atively-0.050
ya-0.046
eways-0.045
agg-0.045
overed-0.044
Token Tad
Token ID50077
Feature activation+2.84e-01

Pos logit contributions
 ruined+0.002
 hurt+0.002
 bleeding+0.002
 Wh+0.002
 still+0.002
Neg logit contributions
atively-0.003
agg-0.003
ya-0.003
overed-0.003
eways-0.003
Token found
Token ID1043
Feature activation+3.97e-01

Pos logit contributions
atively+0.019
agg+0.018
ya+0.018
eways+0.017
overed+0.017
Neg logit contributions
 Wh-0.010
 Snow-0.010
 still-0.009
 Brown-0.009
 Teddy-0.009
Token a
Token ID257
Feature activation+1.49e+00

Pos logit contributions
atively+0.030
agg+0.029
ya+0.028
eways+0.027
overed+0.027
Neg logit contributions
 Wh-0.012
 Snow-0.011
 still-0.010
 Brown-0.010
 Teddy-0.010
Token
Token ID198
Feature activation+7.26e-02

Pos logit contributions
atively+0.030
agg+0.029
ya+0.028
eways+0.028
overed+0.027
Neg logit contributions
 Wh-0.008
 Snow-0.007
 still-0.006
 Brown-0.006
 Teddy-0.006
Token
Token ID198
Feature activation-2.43e-01

Pos logit contributions
atively+0.006
agg+0.005
eways+0.005
ya+0.005
aded+0.005
Neg logit contributions
 Wh-0.002
 Snow-0.002
 Brown-0.001
 Teddy-0.001
 still-0.001
Token"
Token ID1
Feature activation+1.64e+00

Pos logit contributions
 Wh+0.008
 still+0.008
 Snow+0.008
."+0.007
 Teddy+0.007
Neg logit contributions
atively-0.018
ya-0.016
overed-0.016
agg-0.016
eways-0.016
TokenCan
Token ID6090
Feature activation+1.25e+00

Pos logit contributions
atively+0.109
ya+0.102
agg+0.100
overed+0.098
eways+0.097
Neg logit contributions
 Wh-0.070
 Snow-0.067
 still-0.063
 Lily-0.059
 Mitt-0.058
Token we
Token ID356
Feature activation-6.91e-01

Pos logit contributions
atively+0.065
agg+0.059
ya+0.058
overed+0.058
Run+0.056
Neg logit contributions
 Wh-0.055
 Snow-0.054
 Brown-0.050
 Teddy-0.049
 still-0.049
Token still
Token ID991
Feature activation-4.16e+00

Pos logit contributions
 Wh+0.034
 bleeding+0.033
 Rat+0.032
 Ho+0.032
 Snow+0.032
Neg logit contributions
agg-0.027
aded-0.026
 plunge-0.026
atively-0.025
 nearer-0.024
Token go
Token ID467
Feature activation-5.46e-01

Pos logit contributions
 Wh+0.153
 Snow+0.145
 Rat+0.136
 Teddy+0.134
 Ho+0.134
Neg logit contributions
agg-0.236
atively-0.234
ya-0.225
aded-0.225
overed-0.211
Token to
Token ID284
Feature activation+8.84e-01

Pos logit contributions
 Wh+0.021
 Snow+0.019
 Mitt+0.018
 Teddy+0.017
 Brown+0.017
Neg logit contributions
atively-0.033
ya-0.032
agg-0.031
overed-0.030
aded-0.030
Token the
Token ID262
Feature activation-1.25e+00

Pos logit contributions
ya+0.046
agg+0.045
 plunge+0.044
atively+0.043
 nearer+0.043
Neg logit contributions
 Wh-0.030
 bruised-0.030
 bleeding-0.030
un-0.029
 sore-0.028
Token park
Token ID3952
Feature activation-7.00e-01

Pos logit contributions
 Wh+0.056
 Teddy+0.054
 Snow+0.054
 Brown+0.052
."+0.051
Neg logit contributions
atively-0.066
agg-0.061
ya-0.061
aded-0.057
overed-0.057
Token?"
Token ID1701
Feature activation+4.54e-02

Pos logit contributions
 Wh+0.018
 Snow+0.017
 Teddy+0.014
 Brown+0.014
 Mitt+0.013
Neg logit contributions
atively-0.054
agg-0.051
ya-0.051
overed-0.049
eways-0.049
Token his
Token ID465
Feature activation-5.75e-01

Pos logit contributions
 Wh+0.004
 Snow+0.004
 Brown+0.003
 still+0.003
."+0.003
Neg logit contributions
atively-0.008
agg-0.008
ya-0.007
eways-0.007
aded-0.007
Token mom
Token ID1995
Feature activation-8.05e-01

Pos logit contributions
 Wh+0.020
 Snow+0.018
 Brown+0.016
."+0.015
 Teddy+0.015
Neg logit contributions
atively-0.039
ya-0.035
 flavours-0.035
overed-0.034
agg-0.034
Token's
Token ID338
Feature activation-1.17e+00

Pos logit contributions
 Wh+0.032
 Snow+0.030
 Teddy+0.027
."+0.027
 Mitt+0.027
Neg logit contributions
atively-0.048
ya-0.045
agg-0.044
aded-0.042
overed-0.042
Token love
Token ID1842
Feature activation-1.63e+00

Pos logit contributions
 Wh+0.047
 Snow+0.045
 still+0.042
 Brown+0.041
 Teddy+0.041
Neg logit contributions
atively-0.075
agg-0.071
ya-0.070
eways-0.068
overed-0.067
Token would
Token ID561
Feature activation+8.23e-02

Pos logit contributions
 Wh+0.055
 Snow+0.050
 Brown+0.044
 Teddy+0.043
."+0.042
Neg logit contributions
atively-0.110
ya-0.102
agg-0.101
 flavours-0.099
overed-0.099
Token never
Token ID1239
Feature activation-4.70e+00

Pos logit contributions
atively+0.005
agg+0.004
 phrase+0.004
ued+0.004
 explanation+0.004
Neg logit contributions
 Wh-0.003
 Snow-0.003
 Teddy-0.003
 Mitt-0.003
 Rat-0.003
Token be
Token ID307
Feature activation-9.26e-01

Pos logit contributions
 Wh+0.163
 Snow+0.160
 Teddy+0.139
 Brown+0.139
 Mitt+0.132
Neg logit contributions
atively-0.315
agg-0.292
ya-0.292
aded-0.287
overed-0.281
Token harsh
Token ID11859
Feature activation-2.03e+00

Pos logit contributions
 Snow+0.035
 Wh+0.035
 Brown+0.030
 Teddy+0.029
 Rat+0.029
Neg logit contributions
atively-0.054
ya-0.054
aded-0.053
agg-0.053
overed-0.051
Token.
Token ID13
Feature activation-5.24e-01

Pos logit contributions
 Wh+0.080
 Snow+0.075
 Brown+0.067
 Teddy+0.066
 still+0.065
Neg logit contributions
atively-0.131
ya-0.121
agg-0.120
overed-0.119
eways-0.117
Token<|endoftext|>
Token ID50256
Feature activation+7.01e-01

Pos logit contributions
 hurt+0.017
 lose+0.016
 Snow+0.016
 bleeding+0.016
 ruined+0.016
Neg logit contributions
atively-0.032
agg-0.031
eways-0.030
overed-0.030
ya-0.029
TokenOnce
Token ID7454
Feature activation-1.90e+00

Pos logit contributions
atively+0.051
agg+0.049
eways+0.048
overed+0.047
ya+0.047
Neg logit contributions
 Wh-0.019
 Snow-0.017
 still-0.016
 bruised-0.015
 bleeding-0.015
Token him
Token ID683
Feature activation+1.65e-01

Pos logit contributions
atively+0.139
agg+0.137
ya+0.132
aded+0.129
eways+0.128
Neg logit contributions
 Wh-0.052
 Snow-0.049
 Brown-0.045
 Teddy-0.044
."-0.042
Token,
Token ID11
Feature activation+1.36e-01

Pos logit contributions
atively+0.012
agg+0.012
ya+0.011
eways+0.011
overed+0.011
Neg logit contributions
 Wh-0.005
 Snow-0.005
 still-0.004
 Brown-0.004
 Teddy-0.004
Token fascinated
Token ID30103
Feature activation+2.24e+00

Pos logit contributions
atively+0.010
agg+0.010
ya+0.009
eways+0.009
aded+0.009
Neg logit contributions
 Wh-0.004
 Snow-0.004
 still-0.004
 Brown-0.003
 Teddy-0.003
Token by
Token ID416
Feature activation+1.36e+00

Pos logit contributions
atively+0.187
agg+0.179
aded+0.173
overed+0.168
eways+0.167
Neg logit contributions
 Wh-0.049
 still-0.046
 Snow-0.045
."-0.044
 because-0.041
Token how
Token ID703
Feature activation+7.14e-02

Pos logit contributions
atively+0.105
agg+0.100
ya+0.100
eways+0.098
overed+0.096
Neg logit contributions
 Wh-0.035
 Snow-0.032
 still-0.029
 Brown-0.028
 Teddy-0.028
Token much
Token ID881
Feature activation-4.14e+00

Pos logit contributions
atively+0.005
agg+0.005
ya+0.005
overed+0.005
eways+0.005
Neg logit contributions
 Wh-0.002
 Snow-0.002
 still-0.002
."-0.002
 Teddy-0.002
Token fun
Token ID1257
Feature activation+8.34e-01

Pos logit contributions
 Wh+0.145
 Snow+0.137
 still+0.124
 Brown+0.123
 Teddy+0.122
Neg logit contributions
atively-0.286
agg-0.271
ya-0.267
eways-0.260
overed-0.258
Token he
Token ID339
Feature activation-1.90e-01

Pos logit contributions
atively+0.061
agg+0.058
ya+0.056
overed+0.055
eways+0.055
Neg logit contributions
 Wh-0.027
 Snow-0.026
 Brown-0.023
 Teddy-0.023
 still-0.023
Token was
Token ID373
Feature activation-5.68e-01

Pos logit contributions
 Wh+0.006
 Snow+0.005
 still+0.005
 Brown+0.005
 Teddy+0.005
Neg logit contributions
atively-0.014
agg-0.014
ya-0.013
eways-0.013
overed-0.013
Token having
Token ID1719
Feature activation+1.45e-01

Pos logit contributions
 Wh+0.015
 Snow+0.014
 Teddy+0.012
 Brown+0.012
 still+0.011
Neg logit contributions
atively-0.044
agg-0.042
ya-0.042
eways-0.041
overed-0.041
Token.
Token ID13
Feature activation+1.38e-01

Pos logit contributions
atively+0.012
agg+0.011
ya+0.011
eways+0.011
overed+0.011
Neg logit contributions
 Wh-0.003
 Snow-0.003
 Brown-0.002
 still-0.002
 Teddy-0.002