TOP ACTIVATIONS
MAX = 0.194

." She crawled into their bed and held their hands .
. He lay in his bed and fell asleep , dreaming
She tucked him in his bed and sang him a lull
. She gets into her bed . Her mom kisses her
ara got out of her bed . She put on her
They tucked her in her bed . They gave her a
wheel . Later that day , Lily was eating
He jumped out of his bed and ran to grandma 's
sn ugg led in her bed with her gray sheet and
she sat up in her bed and looked around the room
sn uggle up in their bed . Mom sits next to
He lay in his bed , hoping something would change
. He gets into his bed and pulls up his sheet
. Later that day , Lily 's dad
. Tom jumped into the bath tub and spl ashed in
together ." Later that day , they went to
!" Later that day , Lily and her
home and lay in his bed . Spot 's mom was
She puts her in her bed and t ucks her in
. She sat on her bed and c uddled her t

MIN ACTIVATIONS
MIN = -0.272

if she could request some av oc ados from the store
store and forgot to buy av oc ados . Lily was
still couldn 't find any av oc ados . Finally ,
girl who didn 't like av oc ados . She always
who liked to collect or nam ents . Everywhere she went
something new ! She thought av oc ados were the most
" I will buy more av oc ados tomorrow . You
tree could see lots of av oc ados that the supplier
away . She learned that av oc ados are good for
said , " I love av oc ados ! They are
something new ! She thought av oc ados were the most
. Did you know that av oc ados are very healthy
Maybe they could grow more av oc ados and share them
on , whenever they wanted av oc ados , they would
happy that it produced more av oc ados than ever before
promise I won 't tell anyone ." The rabbit agreed and
the store to get more av oc ados . Gary looked
went she searched for or nam ents , and the more
every day to supply the av oc ados . And the
worked hard and never told anybody a lie .

INTERVAL 0.078 - 0.194
CONTAINS 4.205%

Maggie breathed a sigh of relief and happily sc ur ried
it . She played a song that she learned from her
away . Lily felt happy that she could help the bird
day , she drew a picture of her dog , Spot
each had a special purple dress on , just for the

INTERVAL -0.039 - 0.078
CONTAINS 79.463%

" Wow , that 's cool !" Lily said .
but all of the seats were too hard . It didn
and fell to the floor . Lily laughed . She pulled
was so ugly that everyone was afraid of him .
, taking turns and having so much fun .

INTERVAL -0.155 - -0.039
CONTAINS 16.282%

door and see what was inside , but it was stuck
and said that the penny could help the ideas get spread
girl saw the mineral and decided she wanted to take it
sky light and pretty . All the animals and plants loved
to see the rock . He said , " Wow ,

INTERVAL -0.272 - -0.155
CONTAINS 0.050%

over and said , " Exc use me , the item
happy to find you , Twe ety ! Let 's go
, modest barn . Two mis chie vous kittens lived in
The animals sc ur ried off , leaving the
his neighbor if he knew anyone who could fix the TV
Token."
Token ID526
Feature activation+3.46e-02

Pos logit contributions
 coffee+0.016
 band+0.015
 puppet+0.014
 bath+0.014
 DVD+0.013
Neg logit contributions
uders-0.027
achable-0.027
ust-0.027
uding-0.026
 heights-0.026
Token She
Token ID1375
Feature activation+2.66e-03

Pos logit contributions
 coffee+0.040
 band+0.040
 puppet+0.037
 bath+0.035
 DVD+0.034
Neg logit contributions
ver-0.064
ust-0.064
achable-0.063
uders-0.062
uding-0.061
Token crawled
Token ID45668
Feature activation-2.72e-02

Pos logit contributions
 band+0.003
 coffee+0.003
 puppet+0.003
 bath+0.003
 DVD+0.003
Neg logit contributions
ust-0.005
ver-0.005
uders-0.005
achable-0.005
uding-0.005
Token into
Token ID656
Feature activation-4.62e-02

Pos logit contributions
ver+0.047
ust+0.045
achable+0.044
uders+0.044
uding+0.044
Neg logit contributions
 coffee-0.036
 band-0.034
 puppet-0.033
 bath-0.032
 DVD-0.031
Token their
Token ID511
Feature activation+1.19e-01

Pos logit contributions
 ten+0.070
 anyone+0.069
 heights+0.068
uders+0.068
achable+0.067
Neg logit contributions
 coffee-0.059
 band-0.058
cakes-0.058
 puppet-0.057
uggle-0.056
Token bed
Token ID3996
Feature activation+1.78e-01

Pos logit contributions
 coffee+0.154
cakes+0.153
ic+0.146
on+0.146
you+0.142
Neg logit contributions
uders-0.174
 heights-0.173
 roots-0.171
 steep-0.170
 habitats-0.165
Token and
Token ID290
Feature activation+5.48e-02

Pos logit contributions
 coffee+0.302
 band+0.286
 bath+0.280
 puppet+0.278
 DVD+0.275
Neg logit contributions
ver-0.227
achable-0.200
ust-0.197
uders-0.194
uding-0.194
Token held
Token ID2714
Feature activation+1.24e-02

Pos logit contributions
 coffee+0.082
 band+0.076
 bath+0.074
 puppet+0.074
eddy+0.073
Neg logit contributions
ver-0.083
achable-0.079
ust-0.079
uders-0.078
uding-0.077
Token their
Token ID511
Feature activation+8.21e-02

Pos logit contributions
 coffee+0.015
 band+0.014
 puppet+0.013
 bath+0.013
 DVD+0.012
Neg logit contributions
ver-0.023
ust-0.023
uders-0.022
achable-0.022
uding-0.022
Token hands
Token ID2832
Feature activation+8.67e-02

Pos logit contributions
 coffee+0.110
 band+0.105
 puppet+0.101
 bath+0.096
 DVD+0.094
Neg logit contributions
ust-0.135
ver-0.133
uders-0.133
achable-0.131
uding-0.130
Token.
Token ID13
Feature activation+2.70e-02

Pos logit contributions
 coffee+0.121
 band+0.117
 puppet+0.111
 bath+0.108
 DVD+0.103
Neg logit contributions
ver-0.143
ust-0.141
achable-0.137
uders-0.133
uding-0.133
Token.
Token ID13
Feature activation+1.61e-02

Pos logit contributions
 coffee+0.042
 band+0.041
 puppet+0.039
 DVD+0.039
 CD+0.038
Neg logit contributions
ver-0.033
 anyone-0.033
 impossible-0.032
ust-0.032
 heights-0.032
Token He
Token ID679
Feature activation-3.35e-02

Pos logit contributions
 coffee+0.017
 band+0.014
 bath+0.014
 puppet+0.014
 DVD+0.013
Neg logit contributions
uders-0.032
ust-0.032
uding-0.032
ver-0.032
achable-0.031
Token lay
Token ID3830
Feature activation+3.82e-02

Pos logit contributions
ver+0.058
ust+0.058
uders+0.057
achable+0.057
uding+0.056
Neg logit contributions
 coffee-0.044
 band-0.043
 puppet-0.040
 bath-0.040
 DVD-0.037
Token in
Token ID287
Feature activation-5.07e-02

Pos logit contributions
 coffee+0.048
 band+0.046
 puppet+0.043
 bath+0.042
 DVD+0.040
Neg logit contributions
ver-0.069
ust-0.067
achable-0.066
uders-0.066
uding-0.065
Token his
Token ID465
Feature activation+3.25e-02

Pos logit contributions
 heights+0.092
achable+0.092
ver+0.091
 steep+0.091
 ten+0.090
Neg logit contributions
 coffee-0.054
 band-0.052
 puppet-0.049
cakes-0.047
eddy-0.045
Token bed
Token ID3996
Feature activation+1.76e-01

Pos logit contributions
 coffee+0.032
 band+0.030
 puppet+0.028
 DVD+0.026
 video+0.025
Neg logit contributions
ust-0.064
uders-0.063
achable-0.063
ver-0.062
 heights-0.062
Token and
Token ID290
Feature activation+4.98e-02

Pos logit contributions
 coffee+0.275
 band+0.260
 puppet+0.252
 bath+0.243
 DVD+0.242
Neg logit contributions
ver-0.265
ust-0.245
achable-0.242
uders-0.233
 steep-0.233
Token fell
Token ID3214
Feature activation+3.52e-02

Pos logit contributions
 coffee+0.073
 band+0.070
 puppet+0.067
 DVD+0.065
 bath+0.064
Neg logit contributions
ver-0.076
ust-0.075
achable-0.074
uders-0.072
uding-0.071
Token asleep
Token ID16039
Feature activation+5.97e-03

Pos logit contributions
 band+0.039
 coffee+0.039
 bath+0.035
 puppet+0.035
 DVD+0.032
Neg logit contributions
ust-0.069
ver-0.068
uders-0.067
achable-0.067
uding-0.066
Token,
Token ID11
Feature activation+3.64e-03

Pos logit contributions
 coffee+0.009
 band+0.008
 puppet+0.008
 bath+0.008
eddy+0.007
Neg logit contributions
ver-0.009
achable-0.009
uding-0.009
ust-0.009
uders-0.009
Token dreaming
Token ID28368
Feature activation+6.27e-02

Pos logit contributions
 coffee+0.004
 band+0.004
 puppet+0.004
 bath+0.004
 DVD+0.004
Neg logit contributions
ver-0.007
ust-0.006
achable-0.006
uding-0.006
uders-0.006
Token She
Token ID1375
Feature activation+3.84e-03

Pos logit contributions
 coffee+0.031
 band+0.026
 bath+0.024
 puppet+0.024
 DVD+0.022
Neg logit contributions
ust-0.073
ver-0.072
uders-0.071
uding-0.070
achable-0.070
Token tucked
Token ID29779
Feature activation+6.47e-02

Pos logit contributions
 coffee+0.004
 band+0.004
 bath+0.003
 puppet+0.003
 DVD+0.003
Neg logit contributions
ver-0.008
ust-0.008
achable-0.007
uders-0.007
uding-0.007
Token him
Token ID683
Feature activation-1.57e-04

Pos logit contributions
 coffee+0.068
 band+0.067
 puppet+0.058
 bath+0.057
 DVD+0.053
Neg logit contributions
ust-0.132
ver-0.130
achable-0.128
uders-0.128
uding-0.125
Token in
Token ID287
Feature activation-6.62e-02

Pos logit contributions
ver+0.000
ust+0.000
uders+0.000
achable+0.000
uding+0.000
Neg logit contributions
 coffee-0.000
 band-0.000
 puppet-0.000
 bath-0.000
 DVD-0.000
Token his
Token ID465
Feature activation+2.34e-02

Pos logit contributions
ver+0.112
ust+0.109
achable+0.108
uding+0.107
uders+0.106
Neg logit contributions
 coffee-0.082
 band-0.079
 puppet-0.075
cakes-0.071
 bath-0.070
Token bed
Token ID3996
Feature activation+1.76e-01

Pos logit contributions
 coffee+0.020
 band+0.018
cakes+0.018
 puppet+0.017
eddy+0.016
Neg logit contributions
uders-0.046
 steep-0.046
 heights-0.045
ust-0.045
ver-0.045
Token and
Token ID290
Feature activation+6.38e-02

Pos logit contributions
 coffee+0.272
 band+0.257
 puppet+0.249
 bath+0.246
 video+0.237
Neg logit contributions
ver-0.263
ust-0.242
achable-0.238
uders-0.231
uding-0.231
Token sang
Token ID25889
Feature activation+4.49e-02

Pos logit contributions
 coffee+0.092
eddy+0.090
 video+0.087
ic+0.086
cakes+0.085
Neg logit contributions
ver-0.087
 anyone-0.082
ust-0.081
achable-0.081
 steep-0.081
Token him
Token ID683
Feature activation-1.06e-03

Pos logit contributions
 coffee+0.064
 band+0.060
 puppet+0.058
 kettle+0.058
 bath+0.057
Neg logit contributions
ver-0.067
ust-0.066
 ten-0.065
 anyone-0.064
achable-0.063
Token a
Token ID257
Feature activation+1.47e-02

Pos logit contributions
ver+0.002
ust+0.002
achable+0.002
 anyone+0.002
 ten+0.002
Neg logit contributions
 coffee-0.002
 band-0.001
 kettle-0.001
 puppet-0.001
 bath-0.001
Token lull
Token ID42858
Feature activation+1.16e-01

Pos logit contributions
 coffee+0.020
cakes+0.019
uck+0.019
eddy+0.018
rolley+0.018
Neg logit contributions
ust-0.022
ver-0.022
 steep-0.021
 impossible-0.020
 rarely-0.020
Token.
Token ID13
Feature activation+2.61e-02

Pos logit contributions
 coffee+0.134
 puppet+0.134
 band+0.129
 DVD+0.128
 video+0.124
Neg logit contributions
ver-0.094
 heights-0.093
uding-0.093
uders-0.092
ust-0.092
Token She
Token ID1375
Feature activation-2.53e-03

Pos logit contributions
 band+0.034
 coffee+0.032
 puppet+0.032
 sound+0.029
 dish+0.028
Neg logit contributions
ver-0.045
ust-0.044
achable-0.044
uders-0.043
uding-0.042
Token gets
Token ID3011
Feature activation+4.75e-02

Pos logit contributions
ust+0.005
ver+0.005
achable+0.005
uders+0.005
uding+0.005
Neg logit contributions
 coffee-0.003
 band-0.003
 puppet-0.003
 bath-0.003
 DVD-0.002
Token into
Token ID656
Feature activation-5.02e-02

Pos logit contributions
 puppet+0.064
 video+0.061
board+0.061
ic+0.058
 coffee+0.058
Neg logit contributions
ver-0.070
ust-0.070
 halfway-0.070
 anyone-0.068
 ten-0.064
Token her
Token ID607
Feature activation+4.25e-02

Pos logit contributions
 heights+0.089
 ten+0.087
 anyone+0.086
achable+0.084
 fail+0.083
Neg logit contributions
cakes-0.056
washer-0.052
board-0.050
ugg-0.048
 puppet-0.048
Token bed
Token ID3996
Feature activation+1.76e-01

Pos logit contributions
 coffee+0.038
 band+0.037
 puppet+0.035
cakes+0.032
 DVD+0.032
Neg logit contributions
ust-0.083
ver-0.082
uders-0.082
achable-0.081
 heights-0.081
Token.
Token ID13
Feature activation+2.99e-02

Pos logit contributions
 coffee+0.298
 band+0.277
 puppet+0.277
 DVD+0.270
 bath+0.266
Neg logit contributions
ver-0.224
ust-0.201
 steep-0.197
achable-0.195
 impossible-0.190
Token Her
Token ID2332
Feature activation-1.84e-02

Pos logit contributions
 band+0.038
 coffee+0.038
 puppet+0.036
 sound+0.033
 dish+0.032
Neg logit contributions
ver-0.051
achable-0.050
ust-0.050
uders-0.049
uding-0.047
Token mom
Token ID1995
Feature activation+4.82e-02

Pos logit contributions
ust+0.025
uders+0.024
achable+0.024
 steep+0.024
 heights+0.024
Neg logit contributions
 coffee-0.027
 band-0.026
 puppet-0.026
 DVD-0.025
cakes-0.025
Token kisses
Token ID36544
Feature activation+9.12e-02

Pos logit contributions
 coffee+0.048
 band+0.043
 bath+0.041
eddy+0.039
 puppet+0.039
Neg logit contributions
ver-0.098
uders-0.093
ust-0.092
 heights-0.092
achable-0.092
Token her
Token ID607
Feature activation+1.35e-02

Pos logit contributions
 puppet+0.148
washer+0.147
 refreshed+0.147
vation+0.146
 coffee+0.145
Neg logit contributions
 anyone-0.113
 or-0.105
 ten-0.097
ver-0.091
 anybody-0.086
Tokenara
Token ID3301
Feature activation+4.21e-02

Pos logit contributions
ust+0.008
ver+0.008
uders+0.007
achable+0.007
OO+0.007
Neg logit contributions
 coffee-0.010
 band-0.010
 puppet-0.009
 bath-0.009
 DVD-0.009
Token got
Token ID1392
Feature activation+4.76e-02

Pos logit contributions
 coffee+0.056
 band+0.053
 bath+0.050
 puppet+0.050
 DVD+0.048
Neg logit contributions
ver-0.072
ust-0.071
uders-0.069
achable-0.069
uding-0.068
Token out
Token ID503
Feature activation-2.64e-02

Pos logit contributions
 puppet+0.063
 coffee+0.062
 CD+0.061
 band+0.060
stand+0.059
Neg logit contributions
ver-0.072
 halfway-0.071
 ten-0.071
 anyone-0.070
ust-0.068
Token of
Token ID286
Feature activation+1.02e-01

Pos logit contributions
ver+0.043
 ten+0.042
 halfway+0.041
ust+0.040
 anyone+0.040
Neg logit contributions
 coffee-0.032
 band-0.030
uggle-0.029
 puppet-0.029
 CD-0.029
Token her
Token ID607
Feature activation+3.75e-02

Pos logit contributions
 band+0.112
 coffee+0.111
 puppet+0.108
eddy+0.101
cakes+0.099
Neg logit contributions
 heights-0.177
uders-0.177
 ten-0.176
achable-0.174
uding-0.172
Token bed
Token ID3996
Feature activation+1.76e-01

Pos logit contributions
 coffee+0.036
 band+0.035
eddy+0.034
 cheer+0.033
cakes+0.032
Neg logit contributions
uders-0.067
 heights-0.067
 ten-0.064
ust-0.064
 steep-0.064
Token.
Token ID13
Feature activation+3.67e-02

Pos logit contributions
 coffee+0.311
 DVD+0.300
 puppet+0.296
 bath+0.296
 band+0.295
Neg logit contributions
ver-0.202
 steep-0.167
ust-0.160
achable-0.155
 impossible-0.154
Token She
Token ID1375
Feature activation+2.29e-03

Pos logit contributions
 band+0.042
 coffee+0.042
 puppet+0.039
 bath+0.037
 DVD+0.035
Neg logit contributions
ver-0.069
ust-0.068
achable-0.067
uders-0.067
uding-0.066
Token put
Token ID1234
Feature activation+1.10e-01

Pos logit contributions
 coffee+0.003
 band+0.003
 puppet+0.003
 bath+0.002
 dish+0.002
Neg logit contributions
ust-0.004
ver-0.004
achable-0.004
uders-0.004
uding-0.004
Token on
Token ID319
Feature activation+1.92e-02

Pos logit contributions
 coffee+0.115
 puppet+0.109
 band+0.107
 video+0.107
 bath+0.104
Neg logit contributions
ver-0.202
 ten-0.198
 anyone-0.192
 halfway-0.187
 heights-0.186
Token her
Token ID607
Feature activation+1.97e-02

Pos logit contributions
 band+0.021
 coffee+0.021
 puppet+0.021
eddy+0.020
 bath+0.020
Neg logit contributions
 heights-0.033
 ten-0.033
achable-0.033
ver-0.032
uders-0.032
Token They
Token ID1119
Feature activation+7.47e-02

Pos logit contributions
 band+0.045
 coffee+0.043
 puppet+0.041
 bath+0.038
 DVD+0.037
Neg logit contributions
ver-0.062
achable-0.062
uders-0.061
ust-0.061
uding-0.059
Token tucked
Token ID29779
Feature activation+6.21e-02

Pos logit contributions
 coffee+0.096
 band+0.093
 puppet+0.086
 bath+0.085
 DVD+0.080
Neg logit contributions
ver-0.132
ust-0.131
achable-0.128
uders-0.128
uding-0.126
Token her
Token ID607
Feature activation+5.73e-03

Pos logit contributions
 coffee+0.062
 band+0.060
 puppet+0.054
 bath+0.053
 DVD+0.049
Neg logit contributions
ust-0.128
ver-0.128
achable-0.125
uders-0.125
uding-0.123
Token in
Token ID287
Feature activation-6.72e-02

Pos logit contributions
 coffee+0.008
 band+0.008
 puppet+0.007
 bath+0.007
 DVD+0.007
Neg logit contributions
ver-0.009
ust-0.009
uders-0.009
achable-0.009
uding-0.009
Token her
Token ID607
Feature activation+2.97e-02

Pos logit contributions
ver+0.099
 ten+0.098
achable+0.096
 steep+0.094
ust+0.094
Neg logit contributions
 coffee-0.092
 band-0.090
 puppet-0.087
cakes-0.085
 DVD-0.081
Token bed
Token ID3996
Feature activation+1.75e-01

Pos logit contributions
 coffee+0.026
 band+0.025
cakes+0.023
 puppet+0.022
 refreshed+0.022
Neg logit contributions
uders-0.058
ver-0.056
achable-0.056
 heights-0.056
uding-0.056
Token.
Token ID13
Feature activation+3.70e-02

Pos logit contributions
 coffee+0.280
 band+0.267
 bath+0.258
 puppet+0.257
 DVD+0.252
Neg logit contributions
ver-0.246
ust-0.223
uders-0.218
achable-0.218
 steep-0.212
Token They
Token ID1119
Feature activation+7.70e-02

Pos logit contributions
 band+0.049
 coffee+0.046
 puppet+0.044
 sound+0.040
 bath+0.040
Neg logit contributions
achable-0.063
ver-0.063
uders-0.062
ust-0.061
uding-0.059
Token gave
Token ID2921
Feature activation+5.20e-02

Pos logit contributions
 coffee+0.109
 band+0.102
 puppet+0.096
eddy+0.096
 bath+0.096
Neg logit contributions
ver-0.124
ust-0.121
achable-0.117
uders-0.115
uding-0.112
Token her
Token ID607
Feature activation-8.24e-03

Pos logit contributions
 coffee+0.061
 puppet+0.058
 band+0.058
 DVD+0.055
 bath+0.055
Neg logit contributions
 anyone-0.091
ust-0.088
ver-0.088
 ten-0.088
uders-0.085
Token a
Token ID257
Feature activation-2.90e-06

Pos logit contributions
 ten+0.010
 anyone+0.010
ver+0.010
ust+0.009
 whether+0.009
Neg logit contributions
ic-0.012
 coffee-0.012
 band-0.012
cakes-0.012
eddy-0.012
Token wheel
Token ID7825
Feature activation+2.25e-02

Pos logit contributions
 coffee+0.104
 puppet+0.096
 band+0.094
cakes+0.090
 DVD+0.086
Neg logit contributions
ver-0.132
ust-0.131
achable-0.130
uders-0.129
uding-0.129
Token.
Token ID13
Feature activation+1.98e-02

Pos logit contributions
 coffee+0.035
 puppet+0.031
 band+0.030
 bath+0.030
 refreshed+0.029
Neg logit contributions
ver-0.034
ust-0.032
uders-0.031
 steep-0.031
 impossible-0.030
Token
Token ID198
Feature activation-1.88e-03

Pos logit contributions
 coffee+0.022
 band+0.021
 puppet+0.019
 bath+0.019
 DVD+0.018
Neg logit contributions
ust-0.038
ver-0.038
uders-0.037
achable-0.037
uding-0.037
Token
Token ID198
Feature activation+2.75e-03

Pos logit contributions
ver+0.003
ust+0.003
achable+0.003
uders+0.003
uding+0.003
Neg logit contributions
 coffee-0.002
 band-0.002
 puppet-0.002
 bath-0.002
 DVD-0.002
TokenLater
Token ID18602
Feature activation-8.99e-03

Pos logit contributions
 coffee+0.004
 band+0.004
 puppet+0.004
 bath+0.004
 DVD+0.004
Neg logit contributions
ust-0.004
ver-0.004
achable-0.004
uders-0.004
uding-0.004
Token that
Token ID326
Feature activation+1.75e-01

Pos logit contributions
 anyone+0.014
uders+0.014
 anybody+0.013
ver+0.013
 heights+0.013
Neg logit contributions
 DVD-0.012
 coffee-0.011
 CD-0.011
 puppet-0.011
 band-0.011
Token day
Token ID1110
Feature activation+1.43e-01

Pos logit contributions
 coffee+0.241
cakes+0.234
 band+0.227
 puppet+0.224
aid+0.208
Neg logit contributions
ver-0.284
 steep-0.272
 impossible-0.255
 perspective-0.255
 halfway-0.247
Token,
Token ID11
Feature activation+4.69e-03

Pos logit contributions
 coffee+0.243
 band+0.238
 puppet+0.229
 DVD+0.217
 bath+0.216
Neg logit contributions
ver-0.193
uders-0.183
ust-0.180
achable-0.175
uding-0.174
Token Lily
Token ID20037
Feature activation+3.64e-02

Pos logit contributions
 coffee+0.005
 band+0.005
 puppet+0.005
 bath+0.005
 DVD+0.004
Neg logit contributions
ust-0.009
ver-0.009
achable-0.009
uders-0.009
uding-0.009
Token was
Token ID373
Feature activation+2.42e-03

Pos logit contributions
 coffee+0.043
 band+0.039
 DVD+0.037
 puppet+0.037
cakes+0.035
Neg logit contributions
ver-0.066
ust-0.065
uders-0.065
achable-0.063
uding-0.063
Token eating
Token ID6600
Feature activation+7.48e-02

Pos logit contributions
 coffee+0.004
 puppet+0.003
cakes+0.003
 band+0.003
eddy+0.003
Neg logit contributions
ver-0.004
ust-0.004
achable-0.004
 halfway-0.004
 impossible-0.003
Token He
Token ID679
Feature activation-2.51e-02

Pos logit contributions
 coffee+0.042
 band+0.041
 puppet+0.038
 bath+0.038
 DVD+0.036
Neg logit contributions
ver-0.048
ust-0.048
achable-0.047
uders-0.047
uding-0.045
Token jumped
Token ID11687
Feature activation+1.62e-02

Pos logit contributions
ver+0.051
ust+0.050
uders+0.049
uding+0.049
achable+0.049
Neg logit contributions
 band-0.029
 coffee-0.027
 puppet-0.026
 bath-0.023
 sound-0.022
Token out
Token ID503
Feature activation-2.07e-02

Pos logit contributions
 coffee+0.021
 band+0.020
 puppet+0.019
 bath+0.018
 DVD+0.018
Neg logit contributions
ver-0.028
ust-0.027
achable-0.026
uders-0.026
 impossible-0.026
Token of
Token ID286
Feature activation+1.09e-01

Pos logit contributions
ver+0.040
 ten+0.039
ust+0.039
 anyone+0.038
 heights+0.038
Neg logit contributions
 coffee-0.022
 band-0.018
 DVD-0.017
 bath-0.017
 puppet-0.017
Token his
Token ID465
Feature activation+3.33e-02

Pos logit contributions
 coffee+0.116
 band+0.112
 puppet+0.102
 bath+0.100
 DVD+0.093
Neg logit contributions
ver-0.216
ust-0.215
achable-0.211
uders-0.211
uding-0.207
Token bed
Token ID3996
Feature activation+1.75e-01

Pos logit contributions
 coffee+0.035
 band+0.030
cakes+0.030
 puppet+0.029
 refreshed+0.028
Neg logit contributions
uders-0.063
 heights-0.061
ver-0.060
uding-0.060
ust-0.059
Token and
Token ID290
Feature activation+6.36e-02

Pos logit contributions
 coffee+0.294
 band+0.276
 bath+0.269
 DVD+0.266
 puppet+0.265
Neg logit contributions
ver-0.223
 steep-0.202
ust-0.201
uders-0.201
achable-0.198
Token ran
Token ID4966
Feature activation+6.00e-03

Pos logit contributions
 coffee+0.086
eddy+0.079
 band+0.077
 bath+0.077
 DVD+0.076
Neg logit contributions
ver-0.097
achable-0.097
 steep-0.096
uders-0.096
ust-0.094
Token to
Token ID284
Feature activation+1.98e-02

Pos logit contributions
 coffee+0.008
 band+0.008
 puppet+0.007
 DVD+0.007
 bath+0.007
Neg logit contributions
ver-0.009
 ten-0.009
ust-0.009
 steep-0.009
achable-0.009
Token grandma
Token ID49890
Feature activation+4.04e-02

Pos logit contributions
 coffee+0.024
 band+0.023
 puppet+0.021
 bath+0.021
 DVD+0.020
Neg logit contributions
ver-0.036
ust-0.035
achable-0.035
uders-0.035
uding-0.034
Token's
Token ID338
Feature activation+6.30e-02

Pos logit contributions
 coffee+0.073
cakes+0.070
 band+0.070
ic+0.069
ugg+0.068
Neg logit contributions
 whether-0.040
 ten-0.040
 or-0.039
ver-0.037
 anyone-0.037
Token sn
Token ID3013
Feature activation+9.84e-03

Pos logit contributions
 coffee+0.026
 band+0.024
 bath+0.023
 puppet+0.023
 DVD+0.022
Neg logit contributions
ver-0.039
ust-0.038
achable-0.038
uders-0.037
uding-0.037
Tokenugg
Token ID6837
Feature activation+8.44e-02

Pos logit contributions
 puppet+0.011
 coffee+0.011
 video+0.011
 movie+0.010
 DVD+0.010
Neg logit contributions
ver-0.020
ared-0.019
achable-0.018
ust-0.018
OO-0.017
Tokenled
Token ID992
Feature activation+6.77e-04

Pos logit contributions
 coffee+0.129
 puppet+0.123
 DVD+0.123
 cheer+0.122
 bath+0.122
Neg logit contributions
uders-0.111
ver-0.108
ust-0.107
achable-0.106
uding-0.104
Token in
Token ID287
Feature activation-5.80e-02

Pos logit contributions
 coffee+0.001
 band+0.001
 puppet+0.001
 bath+0.001
 DVD+0.001
Neg logit contributions
ust-0.001
ver-0.001
achable-0.001
uding-0.001
uders-0.001
Token her
Token ID607
Feature activation+4.14e-02

Pos logit contributions
 ten+0.096
 whether+0.094
 halfway+0.092
 steep+0.090
 heights+0.090
Neg logit contributions
cakes-0.071
washer-0.067
ic-0.065
 coffee-0.063
up-0.062
Token bed
Token ID3996
Feature activation+1.74e-01

Pos logit contributions
 coffee+0.039
 band+0.036
cakes+0.034
 DVD+0.032
eddy+0.032
Neg logit contributions
 steep-0.077
 heights-0.077
achable-0.077
ver-0.077
uders-0.076
Token with
Token ID351
Feature activation+4.99e-02

Pos logit contributions
 coffee+0.276
 band+0.257
 puppet+0.252
 bath+0.249
 DVD+0.248
Neg logit contributions
ver-0.256
ust-0.232
achable-0.232
uding-0.222
uders-0.222
Token her
Token ID607
Feature activation+1.12e-02

Pos logit contributions
 coffee+0.064
 puppet+0.064
 band+0.062
washer+0.062
cakes+0.062
Neg logit contributions
 anyone-0.080
ver-0.074
 ten-0.073
 anybody-0.073
ust-0.073
Token gray
Token ID12768
Feature activation+2.16e-03

Pos logit contributions
 coffee+0.012
 band+0.011
 puppet+0.010
 bath+0.010
 DVD+0.010
Neg logit contributions
ver-0.022
ust-0.022
achable-0.022
uders-0.022
uding-0.021
Token sheet
Token ID9629
Feature activation+8.47e-02

Pos logit contributions
 coffee+0.002
 band+0.002
 DVD+0.002
 puppet+0.002
 refreshed+0.002
Neg logit contributions
ver-0.004
uders-0.004
achable-0.004
ust-0.004
 heights-0.004
Token and
Token ID290
Feature activation+3.52e-02

Pos logit contributions
 coffee+0.142
 band+0.129
 puppet+0.125
 DVD+0.124
Kids+0.121
Neg logit contributions
ver-0.120
ust-0.107
 steep-0.102
achable-0.101
 impossible-0.101
Token she
Token ID673
Feature activation+1.41e-02

Pos logit contributions
ver+0.040
ust+0.039
achable+0.039
uders+0.038
uding+0.038
Neg logit contributions
 coffee-0.015
 band-0.015
 puppet-0.014
 bath-0.013
 DVD-0.012
Token sat
Token ID3332
Feature activation-3.01e-02

Pos logit contributions
 band+0.018
 coffee+0.018
 puppet+0.017
 bath+0.016
 dish+0.015
Neg logit contributions
ust-0.025
achable-0.025
uders-0.025
ver-0.025
uding-0.024
Token up
Token ID510
Feature activation-2.77e-02

Pos logit contributions
ver+0.057
ust+0.056
achable+0.055
uders+0.054
uding+0.054
Neg logit contributions
 coffee-0.035
 band-0.032
 puppet-0.031
 bath-0.031
 DVD-0.029
Token in
Token ID287
Feature activation-5.29e-02

Pos logit contributions
ust+0.051
ver+0.051
uders+0.050
achable+0.049
uding+0.049
Neg logit contributions
 coffee-0.034
 band-0.033
 puppet-0.030
 bath-0.030
 DVD-0.028
Token her
Token ID607
Feature activation+4.47e-02

Pos logit contributions
 ten+0.080
 heights+0.076
ver+0.073
achable+0.073
 halfway+0.073
Neg logit contributions
 coffee-0.072
 band-0.070
 puppet-0.070
cakes-0.070
washer-0.070
Token bed
Token ID3996
Feature activation+1.74e-01

Pos logit contributions
 coffee+0.043
 band+0.040
 puppet+0.038
cakes+0.037
 video+0.036
Neg logit contributions
 steep-0.082
ust-0.081
ver-0.080
achable-0.080
uders-0.080
Token and
Token ID290
Feature activation+4.25e-02

Pos logit contributions
 coffee+0.275
 band+0.266
 puppet+0.255
 bath+0.252
 DVD+0.251
Neg logit contributions
ver-0.243
achable-0.225
ust-0.225
uders-0.216
uding-0.214
Token looked
Token ID3114
Feature activation+1.15e-02

Pos logit contributions
 coffee+0.062
 band+0.059
 puppet+0.056
 bath+0.055
 DVD+0.054
Neg logit contributions
ver-0.067
achable-0.065
ust-0.065
uders-0.063
uding-0.062
Token around
Token ID1088
Feature activation-3.18e-02

Pos logit contributions
 coffee+0.014
 band+0.013
 bath+0.012
 puppet+0.012
 refreshed+0.012
Neg logit contributions
uders-0.022
ver-0.022
ust-0.022
uding-0.021
achable-0.021
Token the
Token ID262
Feature activation+3.91e-02

Pos logit contributions
ust+0.051
ver+0.051
achable+0.051
uding+0.050
uders+0.050
Neg logit contributions
 coffee-0.044
 band-0.043
 puppet-0.040
 bath-0.039
 DVD-0.038
Token room
Token ID2119
Feature activation+1.40e-01

Pos logit contributions
 coffee+0.041
 band+0.039
 puppet+0.037
cakes+0.034
 DVD+0.033
Neg logit contributions
achable-0.072
ust-0.072
uders-0.071
 heights-0.070
 steep-0.070
Token sn
Token ID3013
Feature activation+1.09e-02

Pos logit contributions
 coffee+0.046
 band+0.045
 puppet+0.041
 bath+0.040
 DVD+0.037
Neg logit contributions
ust-0.083
ver-0.082
uders-0.082
achable-0.081
uding-0.080
Tokenuggle
Token ID33498
Feature activation+6.42e-02

Pos logit contributions
 puppet+0.011
 coffee+0.011
 video+0.010
 sound+0.010
 bath+0.009
Neg logit contributions
ver-0.022
ierce-0.020
ared-0.020
 steep-0.019
achable-0.019
Token up
Token ID510
Feature activation-5.25e-02

Pos logit contributions
 coffee+0.102
 bath+0.096
board+0.091
cakes+0.090
 band+0.090
Neg logit contributions
ver-0.090
achable-0.082
uders-0.080
uding-0.080
 halfway-0.075
Token in
Token ID287
Feature activation-6.43e-02

Pos logit contributions
ver+0.092
ust+0.089
achable+0.089
uders+0.087
uding+0.087
Neg logit contributions
 coffee-0.067
 band-0.064
 puppet-0.061
 bath-0.060
 DVD-0.057
Token their
Token ID511
Feature activation+1.04e-01

Pos logit contributions
 ten+0.099
 heights+0.091
 halfway+0.088
achable+0.088
 whether+0.086
Neg logit contributions
cakes-0.096
up-0.090
washer-0.085
ic-0.084
ugg-0.083
Token bed
Token ID3996
Feature activation+1.74e-01

Pos logit contributions
cakes+0.132
you+0.124
ic+0.124
uck+0.121
on+0.118
Neg logit contributions
 heights-0.159
 steep-0.157
 habitats-0.153
 roots-0.153
uders-0.147
Token.
Token ID13
Feature activation+2.69e-02

Pos logit contributions
 coffee+0.276
 band+0.269
 puppet+0.255
 bath+0.254
 DVD+0.243
Neg logit contributions
ver-0.244
ust-0.228
achable-0.224
uders-0.222
uding-0.217
Token Mom
Token ID11254
Feature activation+5.44e-02

Pos logit contributions
 coffee+0.029
 band+0.028
 puppet+0.025
 bath+0.025
 DVD+0.023
Neg logit contributions
ver-0.054
ust-0.053
achable-0.052
uders-0.052
uding-0.051
Token sits
Token ID10718
Feature activation-3.64e-02

Pos logit contributions
 coffee+0.074
 band+0.069
 bath+0.067
 sound+0.061
eddy+0.061
Neg logit contributions
ver-0.089
uders-0.085
 heights-0.084
uding-0.084
ust-0.083
Token next
Token ID1306
Feature activation-8.68e-03

Pos logit contributions
ver+0.059
 halfway+0.057
achable+0.056
 heights+0.055
uding+0.055
Neg logit contributions
 coffee-0.049
 bath-0.045
 video-0.043
 puppet-0.043
 band-0.041
Token to
Token ID284
Feature activation+4.44e-03

Pos logit contributions
 ten+0.011
 steep+0.010
 heights+0.010
 1+0.010
 vantage+0.009
Neg logit contributions
 coffee-0.015
 DVD-0.014
 puppet-0.013
wards-0.013
cakes-0.013
Token
Token ID198
Feature activation-1.48e-02

Pos logit contributions
ver+0.041
achable+0.040
ust+0.040
ierce+0.038
Near+0.038
Neg logit contributions
 coffee-0.034
 band-0.032
 puppet-0.030
 bath-0.029
 DVD-0.028
TokenHe
Token ID1544
Feature activation-2.67e-02

Pos logit contributions
ust+0.020
ver+0.019
achable+0.019
uding+0.018
uders+0.018
Neg logit contributions
 coffee-0.027
 band-0.025
 puppet-0.024
 bath-0.024
 DVD-0.023
Token lay
Token ID3830
Feature activation+3.17e-02

Pos logit contributions
ver+0.045
ust+0.045
uders+0.044
achable+0.044
uding+0.043
Neg logit contributions
 coffee-0.036
 band-0.036
 puppet-0.033
 bath-0.032
 DVD-0.030
Token in
Token ID287
Feature activation-5.39e-02

Pos logit contributions
 coffee+0.040
 band+0.038
 puppet+0.036
 bath+0.035
 DVD+0.033
Neg logit contributions
ver-0.057
ust-0.057
achable-0.056
uders-0.056
uding-0.055
Token his
Token ID465
Feature activation+3.02e-02

Pos logit contributions
ver+0.091
achable+0.089
 heights+0.088
uding+0.087
 steep+0.086
Neg logit contributions
 coffee-0.066
 band-0.063
 puppet-0.061
cakes-0.058
 bath-0.056
Token bed
Token ID3996
Feature activation+1.73e-01

Pos logit contributions
 coffee+0.025
 band+0.023
cakes+0.022
Happy+0.022
 puppet+0.021
Neg logit contributions
 steep-0.058
 heights-0.057
uders-0.057
ust-0.057
 anyone-0.057
Token,
Token ID11
Feature activation+1.88e-03

Pos logit contributions
 coffee+0.266
 band+0.251
 puppet+0.244
 bath+0.237
 DVD+0.234
Neg logit contributions
ver-0.265
ust-0.243
achable-0.240
uders-0.233
 impossible-0.232
Token hoping
Token ID7725
Feature activation-2.30e-02

Pos logit contributions
 coffee+0.003
 band+0.003
 puppet+0.002
 bath+0.002
 DVD+0.002
Neg logit contributions
ver-0.003
ust-0.003
achable-0.003
uders-0.003
uding-0.003
Token something
Token ID1223
Feature activation-5.84e-02

Pos logit contributions
ver+0.043
ust+0.043
achable+0.042
 heights+0.041
uders+0.041
Neg logit contributions
 coffee-0.026
 band-0.025
 puppet-0.024
 DVD-0.022
 bath-0.022
Token would
Token ID561
Feature activation-3.46e-02

Pos logit contributions
ver+0.100
ust+0.100
achable+0.097
uders+0.096
uding+0.094
Neg logit contributions
 coffee-0.078
 band-0.075
 puppet-0.071
 bath-0.069
 DVD-0.067
Token change
Token ID1487
Feature activation-3.43e-02

Pos logit contributions
ust+0.055
ver+0.054
achable+0.053
 impossible+0.053
 anyone+0.052
Neg logit contributions
 coffee-0.050
 puppet-0.046
 band-0.046
 DVD-0.045
eddy-0.044
Token.
Token ID13
Feature activation+1.93e-02

Pos logit contributions
 coffee+0.122
 band+0.118
 kettle+0.112
 puppet+0.112
 DVD+0.112
Neg logit contributions
 heights-0.099
 anyone-0.097
uders-0.097
uding-0.095
ust-0.094
Token He
Token ID679
Feature activation-3.46e-02

Pos logit contributions
 coffee+0.017
 band+0.015
 puppet+0.014
 bath+0.014
 DVD+0.013
Neg logit contributions
uders-0.043
ust-0.043
uding-0.042
ver-0.042
achable-0.042
Token gets
Token ID3011
Feature activation+4.26e-02

Pos logit contributions
ver+0.062
ust+0.061
achable+0.060
uders+0.060
uding+0.060
Neg logit contributions
 coffee-0.045
 band-0.044
 puppet-0.042
 bath-0.040
 DVD-0.037
Token into
Token ID656
Feature activation-5.24e-02

Pos logit contributions
 coffee+0.060
 puppet+0.060
 kettle+0.057
 video+0.057
cakes+0.056
Neg logit contributions
 anyone-0.061
ver-0.060
ust-0.058
 halfway-0.057
 ten-0.056
Token his
Token ID465
Feature activation+3.01e-02

Pos logit contributions
 anyone+0.081
 heights+0.080
 ten+0.079
 fail+0.077
achable+0.077
Neg logit contributions
cakes-0.069
 coffee-0.066
 band-0.063
ugg-0.062
uggle-0.062
Token bed
Token ID3996
Feature activation+1.73e-01

Pos logit contributions
cakes+0.030
 coffee+0.030
 band+0.028
ic+0.028
eddy+0.027
Neg logit contributions
 heights-0.052
uders-0.052
achable-0.051
 steep-0.051
ust-0.050
Token and
Token ID290
Feature activation+5.23e-02

Pos logit contributions
 coffee+0.295
 band+0.274
 puppet+0.270
 bath+0.268
 DVD+0.264
Neg logit contributions
ver-0.221
ust-0.196
 steep-0.189
achable-0.189
uders-0.185
Token pulls
Token ID16194
Feature activation+8.19e-03

Pos logit contributions
 coffee+0.065
 band+0.062
eddy+0.059
 puppet+0.057
 bath+0.056
Neg logit contributions
ver-0.085
 heights-0.085
achable-0.085
uders-0.085
ust-0.084
Token up
Token ID510
Feature activation-5.87e-02

Pos logit contributions
 coffee+0.009
 band+0.009
 puppet+0.008
 bath+0.008
 DVD+0.008
Neg logit contributions
ver-0.016
ust-0.016
achable-0.015
uders-0.015
uding-0.015
Token his
Token ID465
Feature activation+1.65e-03

Pos logit contributions
ver+0.095
achable+0.093
 heights+0.092
ust+0.091
uders+0.091
Neg logit contributions
 coffee-0.074
 band-0.073
 puppet-0.069
 bath-0.066
eddy-0.065
Token sheet
Token ID9629
Feature activation+9.02e-02

Pos logit contributions
 coffee+0.002
 band+0.002
 puppet+0.001
 DVD+0.001
cakes+0.001
Neg logit contributions
achable-0.003
ust-0.003
ver-0.003
uders-0.003
 heights-0.003
Token.
Token ID13
Feature activation+2.14e-02

Pos logit contributions
ver+0.075
ust+0.072
achable+0.069
 impossible+0.069
 anyone+0.068
Neg logit contributions
 coffee-0.083
 band-0.079
 puppet-0.077
 bath-0.076
 kettle-0.072
Token
Token ID220
Feature activation-1.52e-02

Pos logit contributions
 band+0.032
 coffee+0.030
 puppet+0.030
 DVD+0.028
eddy+0.027
Neg logit contributions
achable-0.033
ver-0.032
ust-0.031
uders-0.031
uding-0.031
Token
Token ID198
Feature activation-7.07e-03

Pos logit contributions
ust+0.033
uders+0.033
 heights+0.032
achable+0.032
uding+0.032
Neg logit contributions
 coffee-0.013
 band-0.012
 bath-0.011
 puppet-0.011
 DVD-0.010
Token
Token ID198
Feature activation-8.68e-04

Pos logit contributions
ver+0.014
ust+0.014
achable+0.013
uders+0.013
uding+0.013
Neg logit contributions
 coffee-0.008
 band-0.008
 puppet-0.007
 bath-0.007
 DVD-0.006
TokenLater
Token ID18602
Feature activation-7.71e-03

Pos logit contributions
ust+0.001
achable+0.001
ver+0.001
uders+0.001
uding+0.001
Neg logit contributions
 coffee-0.002
 band-0.002
 puppet-0.002
 bath-0.001
 DVD-0.001
Token that
Token ID326
Feature activation+1.73e-01

Pos logit contributions
 anyone+0.013
 halfway+0.012
achable+0.012
 anybody+0.012
uders+0.012
Neg logit contributions
 DVD-0.009
 puppet-0.009
 CD-0.009
 coffee-0.008
 band-0.008
Token day
Token ID1110
Feature activation+1.42e-01

Pos logit contributions
 puppet+0.256
cakes+0.247
 coffee+0.244
 band+0.240
up+0.228
Neg logit contributions
ver-0.245
One-0.227
 steep-0.221
 halfway-0.216
 impossible-0.213
Token,
Token ID11
Feature activation+2.91e-03

Pos logit contributions
 puppet+0.273
 coffee+0.269
 band+0.261
 DVD+0.252
 CD+0.249
Neg logit contributions
ver-0.152
 halfway-0.127
uders-0.127
 anyone-0.126
OO-0.120
Token Lily
Token ID20037
Feature activation+3.61e-02

Pos logit contributions
 band+0.004
 coffee+0.004
 puppet+0.003
 DVD+0.003
eddy+0.003
Neg logit contributions
ver-0.005
achable-0.005
ust-0.005
uders-0.005
 anyone-0.005
Token's
Token ID338
Feature activation+5.70e-02

Pos logit contributions
 coffee+0.039
 band+0.036
 puppet+0.033
 DVD+0.032
 bath+0.032
Neg logit contributions
ver-0.070
ust-0.070
uders-0.069
achable-0.068
uding-0.068
Token dad
Token ID9955
Feature activation+3.86e-02

Pos logit contributions
 coffee+0.088
 puppet+0.082
 band+0.082
 DVD+0.081
 refreshed+0.078
Neg logit contributions
ust-0.080
ver-0.077
uders-0.077
achable-0.077
uding-0.073
Token.
Token ID13
Feature activation+4.64e-02

Pos logit contributions
 coffee+0.099
 band+0.095
 puppet+0.089
 bath+0.087
 DVD+0.083
Neg logit contributions
ver-0.136
ust-0.135
uders-0.132
achable-0.132
uding-0.130
Token Tom
Token ID4186
Feature activation+4.02e-02

Pos logit contributions
 coffee+0.052
 band+0.049
 puppet+0.045
 bath+0.045
 DVD+0.043
Neg logit contributions
ust-0.092
ver-0.090
uders-0.088
achable-0.088
uding-0.087
Token jumped
Token ID11687
Feature activation+1.44e-02

Pos logit contributions
 coffee+0.048
 band+0.047
 puppet+0.044
 bath+0.041
 DVD+0.039
Neg logit contributions
ust-0.076
ver-0.074
achable-0.074
uders-0.074
uding-0.072
Token into
Token ID656
Feature activation-3.87e-02

Pos logit contributions
 coffee+0.017
 band+0.017
 puppet+0.015
 bath+0.015
 DVD+0.014
Neg logit contributions
ver-0.027
ust-0.027
achable-0.027
uders-0.027
uding-0.026
Token the
Token ID262
Feature activation+7.74e-02

Pos logit contributions
 heights+0.066
uders+0.065
achable+0.064
ust+0.064
uding+0.064
Neg logit contributions
 coffee-0.047
 band-0.046
 puppet-0.043
eddy-0.042
 bath-0.042
Token bath
Token ID7837
Feature activation+1.73e-01

Pos logit contributions
 coffee+0.092
eddy+0.091
 band+0.090
cakes+0.088
ugg+0.086
Neg logit contributions
 steep-0.123
 heights-0.114
uders-0.113
 ten-0.113
 furthe-0.112
Tokentub
Token ID37995
Feature activation+1.03e-01

Pos logit contributions
 coffee+0.250
Happy+0.233
 DVD+0.232
 band+0.230
 puppet+0.227
Neg logit contributions
ver-0.231
uders-0.222
uding-0.218
ust-0.213
 furthe-0.201
Token and
Token ID290
Feature activation+5.49e-02

Pos logit contributions
 coffee+0.159
 band+0.159
eddy+0.148
 puppet+0.147
 bath+0.146
Neg logit contributions
ver-0.140
ust-0.137
uding-0.135
uders-0.133
 steep-0.130
Token spl
Token ID4328
Feature activation-6.85e-03

Pos logit contributions
 coffee+0.078
eddy+0.077
 band+0.075
uggle+0.072
 DVD+0.072
Neg logit contributions
uders-0.079
ver-0.079
achable-0.077
 steep-0.077
uding-0.075
Tokenashed
Token ID5263
Feature activation+6.72e-02

Pos logit contributions
ust+0.009
ver+0.009
achable+0.008
ared+0.008
uders+0.008
Neg logit contributions
 coffee-0.012
 band-0.012
 puppet-0.012
 DVD-0.011
 bath-0.011
Token in
Token ID287
Feature activation-5.88e-02

Pos logit contributions
 coffee+0.098
 band+0.095
 puppet+0.093
 DVD+0.091
 CD+0.091
Neg logit contributions
ust-0.094
 halfway-0.091
 impossible-0.090
 anyone-0.089
uding-0.089
Token together
Token ID1978
Feature activation+2.17e-02

Pos logit contributions
 coffee+0.042
 band+0.041
 puppet+0.038
 bath+0.037
 DVD+0.036
Neg logit contributions
ver-0.049
ust-0.049
achable-0.047
uders-0.047
uding-0.046
Token."
Token ID526
Feature activation+4.04e-02

Pos logit contributions
 coffee+0.027
 band+0.027
 bath+0.024
 puppet+0.023
 dish+0.022
Neg logit contributions
uders-0.039
achable-0.039
ust-0.039
uding-0.038
ver-0.038
Token
Token ID198
Feature activation+7.85e-03

Pos logit contributions
 coffee+0.058
 band+0.056
 puppet+0.055
 DVD+0.051
 bath+0.051
Neg logit contributions
ver-0.059
achable-0.056
ust-0.056
 whether-0.055
uders-0.055
Token
Token ID198
Feature activation+9.53e-03

Pos logit contributions
 coffee+0.011
 band+0.010
 puppet+0.010
 bath+0.010
cakes+0.010
Neg logit contributions
ust-0.012
ver-0.012
achable-0.012
RR-0.011
ierce-0.011
TokenLater
Token ID18602
Feature activation-8.09e-03

Pos logit contributions
 coffee+0.014
 puppet+0.013
 band+0.012
 bath+0.012
 dish+0.012
Neg logit contributions
ust-0.015
ver-0.015
achable-0.014
Near-0.014
RR-0.014
Token that
Token ID326
Feature activation+1.73e-01

Pos logit contributions
 anyone+0.012
 anybody+0.011
 ten+0.011
 halfway+0.011
uders+0.010
Neg logit contributions
 DVD-0.011
 CD-0.011
 puppet-0.010
rolley-0.010
eddy-0.010
Token day
Token ID1110
Feature activation+1.41e-01

Pos logit contributions
cakes+0.296
 coffee+0.280
aid+0.271
up+0.264
 puppet+0.260
Neg logit contributions
ver-0.200
 perspective-0.196
 steep-0.192
One-0.180
 halfway-0.179
Token,
Token ID11
Feature activation+4.27e-03

Pos logit contributions
 coffee+0.265
 puppet+0.261
 band+0.260
eddy+0.248
 DVD+0.246
Neg logit contributions
ver-0.156
uders-0.137
 anyone-0.131
 halfway-0.131
ust-0.127
Token they
Token ID484
Feature activation+9.16e-02

Pos logit contributions
 coffee+0.004
 band+0.004
 bath+0.004
 puppet+0.004
 DVD+0.003
Neg logit contributions
ust-0.009
ver-0.009
achable-0.009
uders-0.009
uding-0.009
Token went
Token ID1816
Feature activation+1.75e-02

Pos logit contributions
 coffee+0.105
 band+0.104
 bath+0.094
 puppet+0.094
 DVD+0.086
Neg logit contributions
ust-0.175
ver-0.173
achable-0.171
uders-0.171
uding-0.168
Token to
Token ID284
Feature activation+1.72e-02

Pos logit contributions
ic+0.031
 coffee+0.030
 puppet+0.028
on+0.027
 panc+0.027
Neg logit contributions
 ten-0.019
 halfway-0.019
 steep-0.018
ierce-0.018
ver-0.017
Token!"
Token ID2474
Feature activation+4.39e-02

Pos logit contributions
ust+0.025
ver+0.025
achable+0.025
uders+0.024
uding+0.024
Neg logit contributions
 coffee-0.020
 band-0.020
 puppet-0.018
 bath-0.018
 DVD-0.017
Token
Token ID220
Feature activation-3.82e-03

Pos logit contributions
 puppet+0.069
 band+0.067
 DVD+0.064
eddy+0.064
 coffee+0.063
Neg logit contributions
achable-0.056
ver-0.054
 One-0.052
uding-0.052
 whether-0.052
Token
Token ID198
Feature activation-4.53e-03

Pos logit contributions
ust+0.008
uders+0.008
 heights+0.008
achable+0.008
uding+0.008
Neg logit contributions
 coffee-0.003
 band-0.003
 bath-0.003
 puppet-0.003
 DVD-0.003
Token
Token ID198
Feature activation+1.19e-04

Pos logit contributions
ver+0.008
ust+0.008
achable+0.008
uders+0.007
uding+0.007
Neg logit contributions
 coffee-0.006
 band-0.006
 puppet-0.006
 bath-0.005
 DVD-0.005
TokenLater
Token ID18602
Feature activation-3.76e-03

Pos logit contributions
 coffee+0.000
 band+0.000
 puppet+0.000
 bath+0.000
 DVD+0.000
Neg logit contributions
ust-0.000
achable-0.000
ver-0.000
uders-0.000
uding-0.000
Token that
Token ID326
Feature activation+1.73e-01

Pos logit contributions
 anyone+0.006
 halfway+0.006
 anybody+0.005
 ten+0.005
achable+0.005
Neg logit contributions
 DVD-0.005
 puppet-0.005
 CD-0.005
 bisc-0.004
 coffee-0.004
Token day
Token ID1110
Feature activation+1.41e-01

Pos logit contributions
cakes+0.264
 puppet+0.263
aid+0.258
up+0.257
 band+0.253
Neg logit contributions
ver-0.219
One-0.209
 halfway-0.208
 steep-0.197
 One-0.189
Token,
Token ID11
Feature activation+2.46e-03

Pos logit contributions
 puppet+0.278
 coffee+0.269
 band+0.264
 DVD+0.255
 CD+0.253
Neg logit contributions
ver-0.144
 anyone-0.121
 halfway-0.121
uders-0.120
OO-0.113
Token Lily
Token ID20037
Feature activation+3.52e-02

Pos logit contributions
 band+0.003
 coffee+0.003
 puppet+0.003
eddy+0.003
 DVD+0.003
Neg logit contributions
ver-0.004
achable-0.004
ust-0.004
 anyone-0.004
uders-0.004
Token and
Token ID290
Feature activation+6.36e-02

Pos logit contributions
 coffee+0.041
 band+0.039
 puppet+0.036
 DVD+0.036
 bath+0.035
Neg logit contributions
ver-0.064
uders-0.063
ust-0.063
achable-0.062
uding-0.061
Token her
Token ID607
Feature activation+9.50e-03

Pos logit contributions
 coffee+0.074
 band+0.071
 puppet+0.071
 DVD+0.065
 kettle+0.064
Neg logit contributions
ust-0.112
achable-0.111
 anyone-0.111
ver-0.110
uders-0.110
Token home
Token ID1363
Feature activation+4.38e-02

Pos logit contributions
 coffee+0.027
 band+0.025
 puppet+0.025
 DVD+0.023
eddy+0.023
Neg logit contributions
ver-0.035
ust-0.033
 steep-0.033
achable-0.033
 ten-0.033
Token and
Token ID290
Feature activation+4.85e-02

Pos logit contributions
 coffee+0.058
 band+0.055
 puppet+0.052
 bath+0.051
 DVD+0.049
Neg logit contributions
ver-0.076
ust-0.074
achable-0.073
uders-0.072
uding-0.071
Token lay
Token ID3830
Feature activation+2.59e-02

Pos logit contributions
 coffee+0.073
 band+0.068
eddy+0.068
 puppet+0.068
 DVD+0.067
Neg logit contributions
ver-0.071
 anyone-0.068
achable-0.068
ust-0.068
uders-0.067
Token in
Token ID287
Feature activation-5.88e-02

Pos logit contributions
 coffee+0.030
 band+0.030
 puppet+0.027
 bath+0.027
 DVD+0.025
Neg logit contributions
ust-0.049
ver-0.049
achable-0.048
uders-0.048
uding-0.047
Token his
Token ID465
Feature activation+2.71e-02

Pos logit contributions
 ten+0.102
ver+0.101
 steep+0.100
achable+0.100
 anyone+0.099
Neg logit contributions
 coffee-0.061
cakes-0.061
 band-0.059
 puppet-0.058
eddy-0.055
Token bed
Token ID3996
Feature activation+1.72e-01

Pos logit contributions
 coffee+0.028
 band+0.027
 puppet+0.026
 DVD+0.024
cakes+0.023
Neg logit contributions
ust-0.050
uders-0.049
achable-0.049
ver-0.049
 steep-0.049
Token.
Token ID13
Feature activation+2.35e-02

Pos logit contributions
 coffee+0.256
 band+0.246
 puppet+0.236
 bath+0.227
 DVD+0.222
Neg logit contributions
ver-0.269
ust-0.259
achable-0.252
uders-0.245
uding-0.243
Token Spot
Token ID15899
Feature activation-1.37e-02

Pos logit contributions
 coffee+0.026
 band+0.023
 bath+0.022
 DVD+0.021
 puppet+0.020
Neg logit contributions
ust-0.049
uders-0.047
ver-0.047
achable-0.046
uding-0.046
Token's
Token ID338
Feature activation+6.23e-02

Pos logit contributions
ust+0.025
ver+0.024
achable+0.024
uders+0.024
uding+0.023
Neg logit contributions
 coffee-0.017
 band-0.017
 puppet-0.015
 bath-0.015
 DVD-0.014
Token mom
Token ID1995
Feature activation+3.70e-02

Pos logit contributions
 coffee+0.093
 puppet+0.087
 band+0.086
cakes+0.084
 DVD+0.082
Neg logit contributions
ver-0.089
ust-0.089
uders-0.088
achable-0.087
 heights-0.086
Token was
Token ID373
Feature activation-1.78e-03

Pos logit contributions
 coffee+0.054
 bath+0.047
 DVD+0.047
 band+0.046
 puppet+0.046
Neg logit contributions
ver-0.061
ust-0.055
achable-0.055
uders-0.055
uding-0.054
Token She
Token ID1375
Feature activation-8.05e-03

Pos logit contributions
 band+0.031
 coffee+0.030
 puppet+0.028
 bath+0.026
 DVD+0.026
Neg logit contributions
ver-0.046
ust-0.045
achable-0.045
uders-0.045
 impossible-0.044
Token puts
Token ID7584
Feature activation+8.88e-02

Pos logit contributions
ver+0.015
ust+0.015
uders+0.015
achable+0.015
uding+0.014
Neg logit contributions
 coffee-0.009
 band-0.009
 puppet-0.008
 bath-0.008
 DVD-0.007
Token her
Token ID607
Feature activation+1.21e-02

Pos logit contributions
 coffee+0.111
 puppet+0.111
 band+0.106
eddy+0.102
 video+0.102
Neg logit contributions
ver-0.141
 anyone-0.140
 ten-0.139
 halfway-0.131
 anybody-0.130
Token in
Token ID287
Feature activation-6.41e-02

Pos logit contributions
 coffee+0.014
 band+0.014
 puppet+0.013
 bath+0.012
 DVD+0.012
Neg logit contributions
ver-0.021
ust-0.021
uders-0.021
achable-0.021
uding-0.020
Token her
Token ID607
Feature activation+3.24e-02

Pos logit contributions
ver+0.114
achable+0.111
ust+0.111
uders+0.110
uding+0.108
Neg logit contributions
 coffee-0.076
 band-0.074
 puppet-0.070
 bath-0.067
 DVD-0.064
Token bed
Token ID3996
Feature activation+1.72e-01

Pos logit contributions
 coffee+0.031
 band+0.029
cakes+0.027
 puppet+0.027
eddy+0.027
Neg logit contributions
ver-0.061
uders-0.061
ust-0.060
 heights-0.060
achable-0.060
Token and
Token ID290
Feature activation+5.44e-02

Pos logit contributions
 coffee+0.255
 band+0.245
 puppet+0.233
 bath+0.232
 DVD+0.222
Neg logit contributions
ver-0.269
ust-0.253
achable-0.248
uders-0.245
uding-0.241
Token t
Token ID256
Feature activation-5.46e-02

Pos logit contributions
 coffee+0.070
eddy+0.068
 band+0.068
ic+0.064
 bath+0.063
Neg logit contributions
ver-0.083
 heights-0.082
uders-0.082
 ten-0.081
 steep-0.080
Tokenucks
Token ID6238
Feature activation+6.23e-02

Pos logit contributions
ust+0.096
ver+0.089
ared+0.087
uders+0.086
uding+0.083
Neg logit contributions
 coffee-0.076
 refreshed-0.071
 puppet-0.069
 video-0.068
 cheer-0.065
Token her
Token ID607
Feature activation+4.30e-03

Pos logit contributions
 coffee+0.078
 puppet+0.075
 band+0.074
 bath+0.070
 DVD+0.069
Neg logit contributions
ver-0.108
 anyone-0.104
ust-0.103
 ten-0.102
uders-0.100
Token in
Token ID287
Feature activation-7.68e-02

Pos logit contributions
 coffee+0.006
 band+0.005
 puppet+0.005
 bath+0.005
 DVD+0.005
Neg logit contributions
ver-0.007
ust-0.007
achable-0.007
uders-0.007
uding-0.007
Token.
Token ID13
Feature activation+2.93e-02

Pos logit contributions
 coffee+0.181
ugg+0.175
 band+0.173
 bath+0.171
rolley+0.169
Neg logit contributions
ver-0.119
ust-0.110
 impossible-0.105
 anyone-0.104
 ten-0.104
Token She
Token ID1375
Feature activation-5.91e-03

Pos logit contributions
 coffee+0.022
 band+0.018
 bath+0.016
 puppet+0.016
 kisses+0.015
Neg logit contributions
ust-0.070
ver-0.068
uders-0.068
uding-0.067
achable-0.067
Token sat
Token ID3332
Feature activation-2.21e-02

Pos logit contributions
ust+0.012
uders+0.012
uding+0.012
ver+0.012
achable+0.012
Neg logit contributions
 band-0.007
 coffee-0.006
 puppet-0.006
 bath-0.005
 kisses-0.005
Token on
Token ID319
Feature activation+1.84e-02

Pos logit contributions
ver+0.041
ust+0.040
achable+0.040
uders+0.039
uding+0.039
Neg logit contributions
 coffee-0.026
 band-0.024
 bath-0.023
 puppet-0.023
 video-0.021
Token her
Token ID607
Feature activation+1.45e-02

Pos logit contributions
 coffee+0.021
 band+0.021
 puppet+0.019
 bath+0.019
 DVD+0.018
Neg logit contributions
ver-0.034
ust-0.033
achable-0.033
uders-0.033
uding-0.032
Token bed
Token ID3996
Feature activation+1.72e-01

Pos logit contributions
 coffee+0.009
 band+0.009
 puppet+0.008
 bath+0.007
 DVD+0.007
Neg logit contributions
ver-0.034
ust-0.033
achable-0.033
uders-0.033
uding-0.032
Token and
Token ID290
Feature activation+5.61e-02

Pos logit contributions
 coffee+0.266
 band+0.254
 bath+0.243
 puppet+0.242
 DVD+0.233
Neg logit contributions
ver-0.259
achable-0.238
ust-0.237
uders-0.232
uding-0.228
Token c
Token ID269
Feature activation+3.97e-02

Pos logit contributions
 coffee+0.079
 band+0.076
 puppet+0.071
 bath+0.070
 DVD+0.067
Neg logit contributions
ver-0.091
ust-0.090
achable-0.089
uders-0.088
uding-0.086
Tokenuddled
Token ID32745
Feature activation-2.10e-03

Pos logit contributions
 coffee+0.052
 puppet+0.049
 band+0.049
 bath+0.047
 cheer+0.047
Neg logit contributions
ust-0.068
ver-0.067
achable-0.066
uders-0.066
uding-0.063
Token her
Token ID607
Feature activation+1.14e-03

Pos logit contributions
ver+0.004
ust+0.004
achable+0.004
uders+0.004
uding+0.004
Neg logit contributions
 coffee-0.002
 band-0.002
 puppet-0.002
 bath-0.002
 DVD-0.002
Token t
Token ID256
Feature activation-5.52e-02

Pos logit contributions
 coffee+0.001
 band+0.001
 puppet+0.001
 bath+0.001
 DVD+0.001
Neg logit contributions
ver-0.002
ust-0.002
achable-0.002
uders-0.002
uding-0.002
Token if
Token ID611
Feature activation-8.94e-03

Pos logit contributions
ver+0.003
ust+0.003
achable+0.003
uders+0.003
uding+0.003
Neg logit contributions
 coffee-0.004
 band-0.003
 puppet-0.003
 bath-0.003
 DVD-0.003
Token she
Token ID673
Feature activation-3.71e-02

Pos logit contributions
ver+0.019
 anyone+0.018
ust+0.018
achable+0.017
uders+0.017
Neg logit contributions
 coffee-0.008
 puppet-0.008
 band-0.008
 DVD-0.008
eddy-0.007
Token could
Token ID714
Feature activation-5.12e-02

Pos logit contributions
uders+0.079
 heights+0.079
uding+0.076
achable+0.075
 perspective+0.073
Neg logit contributions
 band-0.040
 coffee-0.036
 puppet-0.035
 dish-0.034
washer-0.032
Token request
Token ID2581
Feature activation-1.61e-02

Pos logit contributions
ver+0.099
ust+0.098
achable+0.096
uders+0.094
uding+0.094
Neg logit contributions
 coffee-0.058
 band-0.055
 puppet-0.052
 bath-0.049
 DVD-0.048
Token some
Token ID617
Feature activation-4.26e-02

Pos logit contributions
uders+0.036
ust+0.036
achable+0.035
uding+0.035
ver+0.035
Neg logit contributions
 coffee-0.017
 band-0.016
 cake-0.013
 bath-0.013
 dish-0.013
Token av
Token ID1196
Feature activation-2.72e-01

Pos logit contributions
uders+0.082
achable+0.079
ver+0.077
uding+0.077
ust+0.075
Neg logit contributions
 band-0.058
 coffee-0.057
 dish-0.050
 bath-0.049
 cake-0.049
Tokenoc
Token ID420
Feature activation-2.56e-02

Pos logit contributions
achable+0.465
uders+0.462
ver+0.445
ust+0.444
uding+0.436
Neg logit contributions
 band-0.367
 coffee-0.358
 puppet-0.330
eddy-0.324
 bath-0.319
Tokenados
Token ID22484
Feature activation-1.72e-01

Pos logit contributions
ust+0.048
 steep+0.048
achable+0.047
ver+0.046
 impossible+0.044
Neg logit contributions
 band-0.031
 coffee-0.030
cakes-0.029
eddy-0.028
 dish-0.028
Token from
Token ID422
Feature activation-7.11e-02

Pos logit contributions
uders+0.320
achable+0.319
ust+0.316
ver+0.312
uding+0.311
Neg logit contributions
 coffee-0.205
 band-0.197
 puppet-0.180
 bath-0.178
 dish-0.165
Token the
Token ID262
Feature activation+1.30e-02

Pos logit contributions
ust+0.181
ver+0.177
 steep+0.166
uders+0.165
OO+0.163
Neg logit contributions
 coffee-0.061
 band-0.053
 bath-0.045
 dish-0.042
 puppet-0.038
Token store
Token ID3650
Feature activation+3.95e-02

Pos logit contributions
 coffee+0.014
 band+0.014
 bath+0.012
 puppet+0.012
 dish+0.012
Neg logit contributions
ver-0.026
ust-0.026
uders-0.026
achable-0.025
uding-0.025
Token store
Token ID3650
Feature activation+6.11e-02

Pos logit contributions
 band+0.031
 refreshed+0.030
 coffee+0.030
 puppet+0.030
 cheer+0.030
Neg logit contributions
 ten-0.038
achable-0.038
chard-0.036
 anyone-0.036
 heights-0.036
Token and
Token ID290
Feature activation+1.77e-02

Pos logit contributions
 coffee+0.086
 puppet+0.085
 band+0.085
 DVD+0.082
 bath+0.082
Neg logit contributions
ver-0.096
 whether-0.090
uding-0.088
achable-0.088
ust-0.088
Token forgot
Token ID16453
Feature activation-3.44e-04

Pos logit contributions
 coffee+0.028
eddy+0.027
 puppet+0.027
 DVD+0.027
 CD+0.026
Neg logit contributions
ver-0.024
chard-0.022
 ten-0.022
 anyone-0.022
 whether-0.021
Token to
Token ID284
Feature activation-2.01e-02

Pos logit contributions
ust+0.001
ver+0.001
achable+0.001
 anyone+0.000
 whether+0.000
Neg logit contributions
 band-0.000
 coffee-0.000
 puppet-0.000
 DVD-0.000
 bath-0.000
Token buy
Token ID2822
Feature activation+5.69e-02

Pos logit contributions
ver+0.037
ust+0.037
achable+0.036
uders+0.036
uding+0.035
Neg logit contributions
 coffee-0.024
 band-0.023
 puppet-0.022
 bath-0.021
 DVD-0.020
Token av
Token ID1196
Feature activation-2.65e-01

Pos logit contributions
 coffee+0.069
 band+0.064
 bath+0.058
 puppet+0.056
 dish+0.054
Neg logit contributions
ust-0.110
ver-0.110
uders-0.109
achable-0.108
uding-0.107
Tokenoc
Token ID420
Feature activation-1.56e-02

Pos logit contributions
uders+0.467
achable+0.467
ver+0.452
ust+0.449
uding+0.439
Neg logit contributions
 band-0.347
 coffee-0.336
eddy-0.303
 puppet-0.302
 dish-0.297
Tokenados
Token ID22484
Feature activation-1.67e-01

Pos logit contributions
ust+0.030
 steep+0.029
achable+0.029
ver+0.029
 impossible+0.027
Neg logit contributions
 band-0.018
 coffee-0.018
cakes-0.018
 dish-0.016
ic-0.016
Token.
Token ID13
Feature activation-2.00e-03

Pos logit contributions
uders+0.328
achable+0.325
ust+0.319
ver+0.316
uding+0.316
Neg logit contributions
 coffee-0.192
 band-0.179
 bath-0.160
 puppet-0.158
 dish-0.152
Token Lily
Token ID20037
Feature activation+2.27e-02

Pos logit contributions
ver+0.003
ust+0.003
achable+0.003
uders+0.003
uding+0.003
Neg logit contributions
 band-0.003
 coffee-0.003
 puppet-0.003
 DVD-0.003
 bath-0.002
Token was
Token ID373
Feature activation-8.85e-03

Pos logit contributions
 band+0.028
 coffee+0.028
 puppet+0.026
 bath+0.025
 dish+0.023
Neg logit contributions
ust-0.041
ver-0.041
uders-0.040
achable-0.040
 heights-0.039
Token still
Token ID991
Feature activation-6.47e-02

Pos logit contributions
ust+0.104
uders+0.101
uding+0.101
achable+0.101
RR+0.098
Neg logit contributions
 coffee-0.025
 band-0.022
 bath-0.019
 puppet-0.016
 cup-0.016
Token couldn
Token ID3521
Feature activation-7.59e-02

Pos logit contributions
uders+0.117
ust+0.113
RR+0.113
uding+0.112
achable+0.111
Neg logit contributions
 coffee-0.077
 band-0.074
 refreshed-0.071
 sound-0.069
 bath-0.068
Token't
Token ID470
Feature activation-9.73e-02

Pos logit contributions
ust+0.136
achable+0.132
uding+0.132
uders+0.131
ver+0.130
Neg logit contributions
 coffee-0.098
 band-0.095
 bath-0.089
 puppet-0.085
 DVD-0.081
Token find
Token ID1064
Feature activation+4.77e-03

Pos logit contributions
uders+0.195
ust+0.193
ver+0.192
 habitats+0.188
achable+0.186
Neg logit contributions
 band-0.101
 bath-0.097
 coffee-0.094
 cheer-0.088
 sound-0.087
Token any
Token ID597
Feature activation-8.95e-02

Pos logit contributions
 coffee+0.005
 band+0.005
 bath+0.005
 puppet+0.004
 cup+0.004
Neg logit contributions
ust-0.010
ver-0.010
achable-0.009
uders-0.009
uding-0.009
Token av
Token ID1196
Feature activation-2.64e-01

Pos logit contributions
ver+0.182
achable+0.176
uders+0.174
ust+0.172
RR+0.169
Neg logit contributions
 band-0.106
 coffee-0.105
 bath-0.096
 puppet-0.090
 sound-0.089
Tokenoc
Token ID420
Feature activation-2.84e-02

Pos logit contributions
achable+0.562
uders+0.547
ver+0.514
ust+0.513
uding+0.505
Neg logit contributions
 band-0.249
on-0.224
eddy-0.204
 coffee-0.203
s-0.197
Tokenados
Token ID22484
Feature activation-1.67e-01

Pos logit contributions
ust+0.056
achable+0.055
 steep+0.054
ver+0.054
ierce+0.050
Neg logit contributions
 band-0.031
 coffee-0.030
ic-0.029
cakes-0.028
 dish-0.028
Token.
Token ID13
Feature activation-1.22e-02

Pos logit contributions
achable+0.322
uders+0.318
ust+0.317
uding+0.309
ver+0.305
Neg logit contributions
 coffee-0.185
 band-0.176
 puppet-0.161
 bath-0.158
 dish-0.149
Token Finally
Token ID9461
Feature activation-6.35e-02

Pos logit contributions
ust+0.025
uders+0.025
ver+0.025
achable+0.024
uding+0.024
Neg logit contributions
 coffee-0.012
 band-0.011
 bath-0.010
 puppet-0.010
 DVD-0.009
Token,
Token ID11
Feature activation-2.68e-02

Pos logit contributions
ust+0.107
ver+0.105
achable+0.104
uders+0.103
uding+0.101
Neg logit contributions
 coffee-0.090
 band-0.087
 bath-0.081
 puppet-0.081
 DVD-0.075
Token girl
Token ID2576
Feature activation+3.36e-02

Pos logit contributions
 coffee+0.013
cakes+0.012
 band+0.012
 refreshed+0.012
 puppet+0.011
Neg logit contributions
ust-0.025
 steep-0.025
ver-0.024
uders-0.024
 heights-0.024
Token who
Token ID508
Feature activation-5.93e-03

Pos logit contributions
 coffee+0.062
 band+0.060
 puppet+0.057
 bath+0.056
cakes+0.056
Neg logit contributions
ust-0.037
ver-0.037
achable-0.037
uders-0.036
uding-0.036
Token didn
Token ID1422
Feature activation-5.17e-02

Pos logit contributions
ust+0.006
 rarely+0.006
ver+0.006
 impossible+0.006
 steep+0.006
Neg logit contributions
 coffee-0.011
 band-0.011
 puppet-0.011
cakes-0.011
eddy-0.010
Token't
Token ID470
Feature activation-1.05e-01

Pos logit contributions
ver+0.078
ust+0.076
achable+0.075
uders+0.073
uding+0.072
Neg logit contributions
 coffee-0.080
 band-0.078
 puppet-0.075
 bath-0.072
 DVD-0.069
Token like
Token ID588
Feature activation-3.08e-02

Pos logit contributions
ust+0.121
 anyone+0.117
 rarely+0.116
ierce+0.111
 ten+0.108
Neg logit contributions
 puppet-0.189
 coffee-0.189
cakes-0.186
 band-0.184
eddy-0.184
Token av
Token ID1196
Feature activation-2.63e-01

Pos logit contributions
 heights+0.054
ust+0.053
achable+0.053
uders+0.053
ver+0.053
Neg logit contributions
 band-0.036
 coffee-0.036
 puppet-0.035
 DVD-0.033
 bath-0.032
Tokenoc
Token ID420
Feature activation-2.47e-02

Pos logit contributions
achable+0.434
ver+0.432
ust+0.430
uders+0.428
uding+0.414
Neg logit contributions
 band-0.369
 coffee-0.360
 puppet-0.332
 bath-0.322
 dish-0.311
Tokenados
Token ID22484
Feature activation-1.62e-01

Pos logit contributions
ust+0.047
ver+0.045
 steep+0.045
achable+0.044
ierce+0.042
Neg logit contributions
 band-0.031
 coffee-0.031
cakes-0.028
 cookies-0.026
 dish-0.026
Token.
Token ID13
Feature activation-5.61e-03

Pos logit contributions
ver+0.270
ust+0.268
achable+0.261
uders+0.259
uding+0.255
Neg logit contributions
 coffee-0.222
 band-0.217
 puppet-0.204
 bath-0.198
 DVD-0.192
Token She
Token ID1375
Feature activation-3.50e-02

Pos logit contributions
ver+0.013
ust+0.013
uders+0.012
uding+0.012
achable+0.012
Neg logit contributions
 coffee-0.005
 band-0.004
 bath-0.004
 puppet-0.004
 dish-0.003
Token always
Token ID1464
Feature activation-1.54e-02

Pos logit contributions
ver+0.064
 heights+0.064
uders+0.063
ust+0.063
uding+0.062
Neg logit contributions
 band-0.045
 coffee-0.044
 puppet-0.040
 bath-0.039
 dish-0.038
Token who
Token ID508
Feature activation+9.57e-04

Pos logit contributions
 coffee+0.053
 band+0.052
 puppet+0.049
 bath+0.048
 DVD+0.046
Neg logit contributions
ver-0.051
ust-0.051
uders-0.049
achable-0.049
uding-0.048
Token liked
Token ID8288
Feature activation-4.83e-02

Pos logit contributions
 coffee+0.002
 band+0.002
cakes+0.002
 puppet+0.002
eddy+0.002
Neg logit contributions
ver-0.001
ust-0.001
 rarely-0.001
 impossible-0.001
 steep-0.001
Token to
Token ID284
Feature activation-2.50e-02

Pos logit contributions
 heights+0.071
 anyone+0.068
achable+0.067
ust+0.067
 ten+0.067
Neg logit contributions
 puppet-0.067
 DVD-0.066
 coffee-0.064
 band-0.062
 refreshed-0.062
Token collect
Token ID2824
Feature activation-2.61e-02

Pos logit contributions
achable+0.044
ver+0.043
 heights+0.042
 ten+0.042
ust+0.042
Neg logit contributions
 coffee-0.029
eddy-0.028
 band-0.027
 puppet-0.027
 DVD-0.026
Token or
Token ID393
Feature activation-4.40e-02

Pos logit contributions
ver+0.046
ust+0.045
achable+0.044
uders+0.044
uding+0.043
Neg logit contributions
 coffee-0.034
 band-0.033
 puppet-0.031
 bath-0.030
 DVD-0.029
Tokennam
Token ID7402
Feature activation-2.61e-01

Pos logit contributions
ver+0.032
ust+0.031
uders+0.030
achable+0.029
uding+0.028
Neg logit contributions
 coffee-0.104
 band-0.102
 bath-0.097
 puppet-0.097
 dish-0.093
Tokenents
Token ID658
Feature activation-1.58e-01

Pos logit contributions
ust+0.219
ver+0.215
uders+0.202
achable+0.202
uding+0.193
Neg logit contributions
 coffee-0.583
 band-0.569
 puppet-0.549
 bath-0.543
 DVD-0.527
Token.
Token ID13
Feature activation+1.37e-03

Pos logit contributions
ver+0.256
ust+0.248
uders+0.238
achable+0.236
uding+0.233
Neg logit contributions
 coffee-0.232
 band-0.222
 puppet-0.213
 bath-0.208
 DVD-0.203
Token Everywhere
Token ID48201
Feature activation-1.34e-01

Pos logit contributions
 coffee+0.002
 band+0.001
 bath+0.001
 puppet+0.001
 dish+0.001
Neg logit contributions
ust-0.003
ver-0.003
uders-0.003
achable-0.003
uding-0.003
Token she
Token ID673
Feature activation-3.79e-03

Pos logit contributions
ver+0.305
ust+0.302
uders+0.297
achable+0.296
uding+0.291
Neg logit contributions
 coffee-0.101
 band-0.096
 puppet-0.087
 bath-0.082
 DVD-0.076
Token went
Token ID1816
Feature activation-1.82e-02

Pos logit contributions
ver+0.007
ust+0.007
uders+0.006
achable+0.006
uding+0.006
Neg logit contributions
 coffee-0.005
 band-0.005
 puppet-0.004
 bath-0.004
 DVD-0.004
Token something
Token ID1223
Feature activation-7.72e-02

Pos logit contributions
 coffee+0.029
 band+0.027
 puppet+0.024
 bath+0.024
 sound+0.022
Neg logit contributions
uders-0.044
ver-0.043
ust-0.043
uding-0.042
achable-0.042
Token new
Token ID649
Feature activation-8.38e-02

Pos logit contributions
ver+0.140
ust+0.140
uders+0.137
achable+0.137
uding+0.135
Neg logit contributions
 coffee-0.095
 band-0.092
 puppet-0.085
 bath-0.083
 DVD-0.079
Token!
Token ID0
Feature activation-5.12e-03

Pos logit contributions
ver+0.140
ust+0.139
achable+0.135
uders+0.135
uding+0.133
Neg logit contributions
 coffee-0.115
 band-0.112
 puppet-0.104
 bath-0.104
 DVD-0.099
Token She
Token ID1375
Feature activation-1.89e-02

Pos logit contributions
ver+0.009
ust+0.008
uders+0.008
achable+0.008
 anyone+0.008
Neg logit contributions
 coffee-0.007
 band-0.007
 puppet-0.007
 bath-0.006
 sound-0.006
Token thought
Token ID1807
Feature activation+1.52e-02

Pos logit contributions
ver+0.032
ust+0.032
achable+0.031
uders+0.031
uding+0.031
Neg logit contributions
 coffee-0.025
 band-0.024
 puppet-0.023
 bath-0.022
 DVD-0.021
Token av
Token ID1196
Feature activation-2.60e-01

Pos logit contributions
 coffee+0.016
 band+0.016
 puppet+0.015
 bath+0.014
 DVD+0.014
Neg logit contributions
ver-0.030
ust-0.029
achable-0.029
uders-0.029
 heights-0.028
Tokenoc
Token ID420
Feature activation-1.90e-02

Pos logit contributions
uders+0.420
achable+0.418
ust+0.415
ver+0.414
uding+0.401
Neg logit contributions
 band-0.363
 coffee-0.360
 puppet-0.336
 bath-0.318
eddy-0.313
Tokenados
Token ID22484
Feature activation-1.60e-01

Pos logit contributions
ust+0.034
 steep+0.033
ver+0.033
achable+0.032
 impossible+0.031
Neg logit contributions
 band-0.024
 coffee-0.024
cakes-0.022
eddy-0.022
uck-0.021
Token were
Token ID547
Feature activation-7.39e-03

Pos logit contributions
ver+0.278
ust+0.270
achable+0.256
uders+0.256
uding+0.253
Neg logit contributions
 coffee-0.219
 band-0.208
 puppet-0.197
 bath-0.196
 DVD-0.189
Token the
Token ID262
Feature activation+1.81e-02

Pos logit contributions
ver+0.014
uders+0.014
ust+0.013
achable+0.013
uding+0.013
Neg logit contributions
 coffee-0.009
 band-0.008
 puppet-0.008
 bath-0.008
 dish-0.008
Token most
Token ID749
Feature activation-8.23e-02

Pos logit contributions
 coffee+0.021
 band+0.020
 sound+0.018
 bath+0.018
 dish+0.018
Neg logit contributions
uders-0.037
ver-0.035
achable-0.035
RR-0.035
ierce-0.034
Token "
Token ID366
Feature activation-8.36e-02

Pos logit contributions
ver+0.039
ust+0.039
achable+0.038
uders+0.038
uding+0.037
Neg logit contributions
 coffee-0.036
 band-0.036
 puppet-0.033
 bath-0.033
 DVD-0.031
TokenI
Token ID40
Feature activation-1.91e-02

Pos logit contributions
ust+0.137
ver+0.130
achable+0.126
 whether+0.125
Near+0.125
Neg logit contributions
 coffee-0.119
 bath-0.115
 puppet-0.114
 band-0.110
 DVD-0.109
Token will
Token ID481
Feature activation+5.03e-02

Pos logit contributions
uders+0.033
achable+0.032
ust+0.031
 heights+0.031
uding+0.031
Neg logit contributions
 band-0.027
 coffee-0.027
 puppet-0.025
 bath-0.025
 dish-0.023
Token buy
Token ID2822
Feature activation+6.26e-02

Pos logit contributions
 coffee+0.063
 band+0.060
 puppet+0.058
 bath+0.055
 DVD+0.054
Neg logit contributions
ver-0.090
ust-0.088
achable-0.087
uding-0.086
uders-0.086
Token more
Token ID517
Feature activation-4.59e-02

Pos logit contributions
 coffee+0.066
 band+0.063
 puppet+0.059
 bath+0.057
 DVD+0.054
Neg logit contributions
ver-0.123
ust-0.123
achable-0.120
uders-0.120
uding-0.118
Token av
Token ID1196
Feature activation-2.60e-01

Pos logit contributions
ver+0.088
ust+0.088
achable+0.086
uders+0.086
uding+0.085
Neg logit contributions
 coffee-0.056
 band-0.054
 puppet-0.048
 bath-0.048
 DVD-0.045
Tokenoc
Token ID420
Feature activation-2.04e-02

Pos logit contributions
achable+0.455
uders+0.448
ust+0.439
ver+0.433
uding+0.428
Neg logit contributions
 band-0.347
 coffee-0.336
 puppet-0.306
eddy-0.294
 bath-0.293
Tokenados
Token ID22484
Feature activation-1.63e-01

Pos logit contributions
ust+0.037
achable+0.036
ver+0.036
 steep+0.036
 impossible+0.034
Neg logit contributions
 band-0.026
 coffee-0.025
cakes-0.023
eddy-0.023
 dish-0.022
Token tomorrow
Token ID9439
Feature activation-2.57e-02

Pos logit contributions
achable+0.315
uders+0.307
ust+0.305
uding+0.299
ver+0.297
Neg logit contributions
 coffee-0.193
 band-0.182
 puppet-0.167
 bath-0.160
 dish-0.156
Token.
Token ID13
Feature activation-6.61e-03

Pos logit contributions
ust+0.040
ver+0.040
achable+0.039
uders+0.039
uding+0.038
Neg logit contributions
 coffee-0.038
 band-0.037
 puppet-0.035
 bath-0.034
 DVD-0.032
Token You
Token ID921
Feature activation-1.05e-02

Pos logit contributions
ust+0.012
ver+0.012
uders+0.012
achable+0.011
uding+0.011
Neg logit contributions
 coffee-0.009
 band-0.008
 puppet-0.007
 DVD-0.007
 bath-0.007
Token tree
Token ID5509
Feature activation-6.05e-02

Pos logit contributions
ver+0.182
ust+0.179
uders+0.172
achable+0.171
uding+0.170
Neg logit contributions
 coffee-0.157
 band-0.146
 puppet-0.140
 bath-0.140
 DVD-0.139
Token could
Token ID714
Feature activation-5.84e-02

Pos logit contributions
ver+0.102
ust+0.099
achable+0.097
uders+0.097
uding+0.095
Neg logit contributions
 coffee-0.084
 band-0.080
 puppet-0.075
 bath-0.075
 DVD-0.073
Token see
Token ID766
Feature activation+1.19e-02

Pos logit contributions
ver+0.106
ust+0.106
uders+0.103
achable+0.103
uding+0.101
Neg logit contributions
 coffee-0.072
 band-0.070
 puppet-0.064
 bath-0.063
 DVD-0.059
Token lots
Token ID6041
Feature activation-6.91e-02

Pos logit contributions
 coffee+0.012
 band+0.011
 puppet+0.010
 dish+0.010
 sound+0.010
Neg logit contributions
ver-0.024
ust-0.024
achable-0.024
uders-0.024
uding-0.023
Token of
Token ID286
Feature activation+2.96e-02

Pos logit contributions
ust+0.159
ver+0.156
 heights+0.152
achable+0.152
 impossible+0.152
Neg logit contributions
 coffee-0.050
 band-0.049
 puppet-0.044
 bath-0.042
 DVD-0.040
Token av
Token ID1196
Feature activation-2.59e-01

Pos logit contributions
 coffee+0.036
 band+0.036
 sound+0.033
 dish+0.031
 bath+0.031
Neg logit contributions
ver-0.059
uders-0.056
ierce-0.054
achable-0.054
ust-0.053
Tokenoc
Token ID420
Feature activation-2.54e-02

Pos logit contributions
achable+0.470
ver+0.469
uders+0.457
ust+0.454
ierce+0.441
Neg logit contributions
 band-0.317
 coffee-0.300
eddy-0.274
 dish-0.271
 puppet-0.271
Tokenados
Token ID22484
Feature activation-1.58e-01

Pos logit contributions
ust+0.050
ver+0.049
achable+0.049
 steep+0.048
ierce+0.046
Neg logit contributions
 band-0.027
 coffee-0.026
cakes-0.026
ic-0.025
on-0.024
Token that
Token ID326
Feature activation+9.53e-02

Pos logit contributions
ver+0.259
ust+0.258
uders+0.249
achable+0.249
uding+0.246
Neg logit contributions
 coffee-0.221
 band-0.215
 puppet-0.201
 bath-0.198
 DVD-0.191
Token the
Token ID262
Feature activation+1.07e-03

Pos logit contributions
 coffee+0.125
 band+0.121
 puppet+0.113
 bath+0.111
 DVD+0.105
Neg logit contributions
ust-0.164
ver-0.164
achable-0.161
uders-0.160
uding-0.157
Token supplier
Token ID22693
Feature activation-8.13e-02

Pos logit contributions
 band+0.001
 coffee+0.001
 dish+0.001
 sound+0.001
 bath+0.001
Neg logit contributions
ver-0.002
ust-0.002
uders-0.002
achable-0.002
ierce-0.002
Token away
Token ID1497
Feature activation+2.33e-04

Pos logit contributions
 coffee+0.010
 puppet+0.010
 band+0.010
eddy+0.009
 DVD+0.009
Neg logit contributions
 impossible-0.012
 steep-0.012
achable-0.012
ust-0.011
 anyone-0.011
Token.
Token ID13
Feature activation+1.37e-02

Pos logit contributions
 coffee+0.000
 band+0.000
 puppet+0.000
 bath+0.000
 DVD+0.000
Neg logit contributions
ver-0.000
ust-0.000
achable-0.000
uders-0.000
uding-0.000
Token She
Token ID1375
Feature activation-1.42e-02

Pos logit contributions
 coffee+0.018
 band+0.018
 puppet+0.017
 bath+0.016
 DVD+0.015
Neg logit contributions
ver-0.024
ust-0.023
achable-0.023
uders-0.023
uding-0.022
Token learned
Token ID4499
Feature activation+4.79e-02

Pos logit contributions
ver+0.024
ust+0.024
achable+0.023
uders+0.023
uding+0.023
Neg logit contributions
 coffee-0.019
 band-0.018
 puppet-0.017
 bath-0.017
 DVD-0.016
Token that
Token ID326
Feature activation+9.74e-02

Pos logit contributions
 coffee+0.035
 band+0.033
 puppet+0.031
 bath+0.029
 DVD+0.028
Neg logit contributions
ust-0.110
ver-0.109
achable-0.108
uders-0.105
 heights-0.105
Token av
Token ID1196
Feature activation-2.58e-01

Pos logit contributions
 coffee+0.138
 band+0.135
 puppet+0.133
 DVD+0.126
 bath+0.123
Neg logit contributions
ust-0.151
ver-0.150
achable-0.147
 heights-0.145
uders-0.145
Tokenoc
Token ID420
Feature activation-1.28e-02

Pos logit contributions
ver+0.362
ust+0.360
uders+0.345
achable+0.345
uding+0.339
Neg logit contributions
 coffee-0.426
 band-0.412
 puppet-0.392
 bath-0.388
 DVD-0.371
Tokenados
Token ID22484
Feature activation-1.47e-01

Pos logit contributions
ust+0.021
ver+0.021
achable+0.020
 steep+0.020
uders+0.020
Neg logit contributions
 coffee-0.018
 band-0.018
cakes-0.016
eddy-0.016
 puppet-0.016
Token are
Token ID389
Feature activation+3.92e-02

Pos logit contributions
ver+0.245
ust+0.239
uders+0.230
achable+0.226
uding+0.225
Neg logit contributions
 coffee-0.209
 band-0.198
 puppet-0.190
 bath-0.184
 DVD-0.181
Token good
Token ID922
Feature activation+1.28e-02

Pos logit contributions
 coffee+0.053
 band+0.052
 sound+0.045
 bath+0.045
 puppet+0.043
Neg logit contributions
uders-0.071
uding-0.068
ver-0.068
achable-0.068
RR-0.067
Token for
Token ID329
Feature activation+1.84e-02

Pos logit contributions
 coffee+0.017
 band+0.016
 puppet+0.015
 bath+0.015
 DVD+0.014
Neg logit contributions
ver-0.022
ust-0.022
uders-0.022
uding-0.021
achable-0.021
Token said
Token ID531
Feature activation+6.34e-02

Pos logit contributions
ust+0.067
ver+0.067
uders+0.066
achable+0.065
uding+0.065
Neg logit contributions
 coffee-0.042
 band-0.042
 puppet-0.039
 bath-0.037
 dish-0.034
Token,
Token ID11
Feature activation-3.10e-02

Pos logit contributions
 coffee+0.076
 band+0.072
 puppet+0.069
 bath+0.067
 DVD+0.064
Neg logit contributions
ver-0.118
ust-0.116
achable-0.114
uders-0.112
uding-0.111
Token "
Token ID366
Feature activation-9.28e-02

Pos logit contributions
ver+0.049
ust+0.049
achable+0.048
uders+0.048
uding+0.047
Neg logit contributions
 coffee-0.045
 band-0.044
 puppet-0.041
 bath-0.041
 DVD-0.039
TokenI
Token ID40
Feature activation-2.75e-02

Pos logit contributions
ust+0.167
ver+0.166
achable+0.162
uders+0.161
uding+0.159
Neg logit contributions
 coffee-0.118
 band-0.113
 puppet-0.106
 bath-0.104
 DVD-0.099
Token love
Token ID1842
Feature activation+4.72e-02

Pos logit contributions
uders+0.041
achable+0.040
ust+0.040
uding+0.040
 heights+0.039
Neg logit contributions
 band-0.043
 coffee-0.043
 puppet-0.040
 bath-0.040
 dish-0.037
Token av
Token ID1196
Feature activation-2.55e-01

Pos logit contributions
 coffee+0.051
 band+0.049
 puppet+0.044
 bath+0.043
 dish+0.040
Neg logit contributions
ver-0.095
ust-0.095
uders-0.092
achable-0.092
uding-0.090
Tokenoc
Token ID420
Feature activation-1.28e-02

Pos logit contributions
achable+0.475
uders+0.472
ust+0.456
ver+0.451
uding+0.443
Neg logit contributions
 band-0.311
 coffee-0.295
 puppet-0.271
eddy-0.264
 dish-0.261
Tokenados
Token ID22484
Feature activation-1.57e-01

Pos logit contributions
ust+0.024
achable+0.023
 steep+0.023
ver+0.023
ierce+0.022
Neg logit contributions
 band-0.016
 coffee-0.015
cakes-0.014
 dish-0.014
eddy-0.014
Token!
Token ID0
Feature activation-2.50e-02

Pos logit contributions
achable+0.272
uders+0.269
ust+0.269
ver+0.264
uding+0.262
Neg logit contributions
 coffee-0.215
 band-0.205
 puppet-0.193
 bath-0.186
 dish-0.180
Token They
Token ID1119
Feature activation+4.48e-02

Pos logit contributions
ust+0.045
uders+0.044
ver+0.044
achable+0.043
uding+0.043
Neg logit contributions
 coffee-0.032
 band-0.030
 puppet-0.028
 bath-0.027
 DVD-0.027
Token are
Token ID389
Feature activation+5.70e-02

Pos logit contributions
 coffee+0.053
 band+0.052
 puppet+0.048
 bath+0.047
 dish+0.044
Neg logit contributions
ver-0.082
ust-0.082
achable-0.081
uders-0.081
uding-0.079
Token something
Token ID1223
Feature activation-6.93e-02

Pos logit contributions
 coffee+0.038
 band+0.035
 puppet+0.031
 bath+0.031
 sound+0.029
Neg logit contributions
uders-0.059
ver-0.057
uding-0.056
ust-0.056
achable-0.056
Token new
Token ID649
Feature activation-7.82e-02

Pos logit contributions
ver+0.127
ust+0.127
uders+0.125
achable+0.125
uding+0.123
Neg logit contributions
 coffee-0.084
 band-0.081
 puppet-0.075
 bath-0.073
 DVD-0.069
Token!
Token ID0
Feature activation+3.47e-03

Pos logit contributions
ver+0.131
ust+0.131
achable+0.127
uders+0.127
uding+0.125
Neg logit contributions
 coffee-0.107
 band-0.104
 puppet-0.097
 bath-0.096
 DVD-0.091
Token She
Token ID1375
Feature activation-1.28e-02

Pos logit contributions
 coffee+0.005
 band+0.005
 puppet+0.004
 bath+0.004
 sound+0.004
Neg logit contributions
ver-0.006
ust-0.006
uders-0.005
 anyone-0.005
achable-0.005
Token thought
Token ID1807
Feature activation+2.16e-02

Pos logit contributions
ver+0.021
ust+0.021
achable+0.021
uders+0.020
uding+0.020
Neg logit contributions
 coffee-0.018
 band-0.017
 puppet-0.016
 bath-0.016
 DVD-0.015
Token av
Token ID1196
Feature activation-2.54e-01

Pos logit contributions
 coffee+0.023
 band+0.023
 puppet+0.021
 bath+0.020
 DVD+0.019
Neg logit contributions
ver-0.042
ust-0.042
achable-0.041
uders-0.041
uding-0.040
Tokenoc
Token ID420
Feature activation-1.25e-02

Pos logit contributions
uders+0.400
achable+0.398
ust+0.398
ver+0.398
uding+0.384
Neg logit contributions
 coffee-0.363
 band-0.362
 puppet-0.338
 bath-0.322
 DVD-0.314
Tokenados
Token ID22484
Feature activation-1.52e-01

Pos logit contributions
ust+0.022
 steep+0.022
ver+0.021
achable+0.020
 impossible+0.020
Neg logit contributions
 coffee-0.016
 band-0.016
cakes-0.015
eddy-0.015
uck-0.014
Token were
Token ID547
Feature activation-1.20e-03

Pos logit contributions
ver+0.264
ust+0.257
achable+0.245
uders+0.244
uding+0.242
Neg logit contributions
 coffee-0.205
 band-0.196
 puppet-0.184
 bath-0.184
 DVD-0.177
Token the
Token ID262
Feature activation+2.65e-02

Pos logit contributions
ver+0.002
uders+0.002
ust+0.002
achable+0.002
uding+0.002
Neg logit contributions
 coffee-0.002
 band-0.001
 puppet-0.001
 bath-0.001
 dish-0.001
Token most
Token ID749
Feature activation-7.90e-02

Pos logit contributions
 coffee+0.029
 band+0.028
 sound+0.026
 dish+0.025
 bath+0.025
Neg logit contributions
uders-0.055
ver-0.053
achable-0.052
RR-0.052
OO-0.052
Token.
Token ID13
Feature activation+6.00e-03

Pos logit contributions
 coffee+0.024
 band+0.023
 bath+0.022
 puppet+0.022
 DVD+0.021
Neg logit contributions
ver-0.020
ust-0.019
uders-0.019
achable-0.019
uding-0.019
Token Did
Token ID7731
Feature activation-6.14e-03

Pos logit contributions
 coffee+0.007
 band+0.007
 puppet+0.006
 bath+0.006
 DVD+0.006
Neg logit contributions
ust-0.011
ver-0.011
achable-0.011
uders-0.011
uding-0.011
Token you
Token ID345
Feature activation-1.92e-03

Pos logit contributions
ver+0.013
ust+0.013
achable+0.013
uding+0.013
uders+0.013
Neg logit contributions
 coffee-0.006
 band-0.005
 bath-0.005
 puppet-0.005
 sound-0.004
Token know
Token ID760
Feature activation+3.77e-02

Pos logit contributions
ust+0.003
ver+0.003
uders+0.003
achable+0.003
uding+0.003
Neg logit contributions
 band-0.002
 coffee-0.002
 bath-0.002
 puppet-0.002
 sound-0.002
Token that
Token ID326
Feature activation+1.01e-01

Pos logit contributions
 coffee+0.047
 band+0.045
 bath+0.040
 that+0.040
 kisses+0.039
Neg logit contributions
uders-0.072
uding-0.072
ust-0.072
UN-0.071
ver-0.070
Token av
Token ID1196
Feature activation-2.51e-01

Pos logit contributions
 coffee+0.118
 band+0.114
 bath+0.102
 puppet+0.100
 sound+0.096
Neg logit contributions
ver-0.200
ust-0.199
achable-0.196
uding-0.194
uders-0.194
Tokenoc
Token ID420
Feature activation-1.41e-02

Pos logit contributions
achable+0.455
uders+0.447
ver+0.439
ust+0.437
uding+0.425
Neg logit contributions
 band-0.316
 coffee-0.297
 puppet-0.276
 sound-0.264
 dish-0.264
Tokenados
Token ID22484
Feature activation-1.61e-01

Pos logit contributions
ust+0.026
 steep+0.026
achable+0.026
ver+0.025
 impossible+0.024
Neg logit contributions
 band-0.018
 coffee-0.017
cakes-0.016
eddy-0.016
 dish-0.016
Token are
Token ID389
Feature activation+3.08e-02

Pos logit contributions
ust+0.281
achable+0.279
ver+0.277
uders+0.275
uding+0.271
Neg logit contributions
 coffee-0.206
 band-0.201
 puppet-0.184
 bath-0.182
 dish-0.172
Token very
Token ID845
Feature activation-6.06e-02

Pos logit contributions
 coffee+0.041
 band+0.036
 dish+0.035
 cake+0.035
 sound+0.034
Neg logit contributions
ver-0.059
uders-0.057
 perspective-0.056
ared-0.055
ust-0.055
Token healthy
Token ID5448
Feature activation-7.40e-03

Pos logit contributions
uders+0.125
uding+0.122
ver+0.122
achable+0.119
 heights+0.117
Neg logit contributions
 coffee-0.068
 band-0.061
 dish-0.057
 sound-0.055
 refreshed-0.053
Token Maybe
Token ID6674
Feature activation-5.35e-02

Pos logit contributions
 band+0.027
 coffee+0.026
 puppet+0.025
 bath+0.023
 DVD+0.023
Neg logit contributions
ver-0.033
achable-0.032
ust-0.032
uders-0.032
ierce-0.031
Token they
Token ID484
Feature activation+6.38e-02

Pos logit contributions
ust+0.118
ver+0.118
achable+0.116
uders+0.116
uding+0.114
Neg logit contributions
 coffee-0.046
 band-0.044
 puppet-0.039
 bath-0.038
 DVD-0.033
Token could
Token ID714
Feature activation-2.41e-02

Pos logit contributions
 band+0.072
 coffee+0.064
 kiss+0.061
 puppet+0.061
 dish+0.059
Neg logit contributions
uders-0.124
 heights-0.124
achable-0.123
uding-0.122
RR-0.117
Token grow
Token ID1663
Feature activation-3.81e-02

Pos logit contributions
ver+0.046
ust+0.046
uders+0.045
achable+0.045
uding+0.044
Neg logit contributions
 coffee-0.028
 band-0.027
 puppet-0.024
 bath-0.024
 DVD-0.022
Token more
Token ID517
Feature activation-2.86e-02

Pos logit contributions
ver+0.072
ust+0.072
uders+0.071
achable+0.071
uding+0.070
Neg logit contributions
 coffee-0.044
 band-0.043
 puppet-0.039
 bath-0.039
 DVD-0.035
Token av
Token ID1196
Feature activation-2.51e-01

Pos logit contributions
ver+0.054
ust+0.052
achable+0.051
uders+0.051
uding+0.050
Neg logit contributions
 coffee-0.036
 band-0.035
 puppet-0.031
 bath-0.031
 sound-0.029
Tokenoc
Token ID420
Feature activation-1.58e-02

Pos logit contributions
ust+0.401
ver+0.401
achable+0.398
uders+0.393
uding+0.382
Neg logit contributions
 band-0.360
 coffee-0.358
 puppet-0.331
 bath-0.322
eddy-0.310
Tokenados
Token ID22484
Feature activation-1.39e-01

Pos logit contributions
ust+0.028
ver+0.027
 steep+0.026
achable+0.026
 impossible+0.025
Neg logit contributions
 coffee-0.021
 band-0.021
cakes-0.019
eddy-0.019
 dish-0.018
Token and
Token ID290
Feature activation+1.31e-02

Pos logit contributions
ust+0.217
ver+0.217
achable+0.212
uders+0.212
uding+0.207
Neg logit contributions
 coffee-0.205
 band-0.200
 puppet-0.187
 bath-0.184
 DVD-0.175
Token share
Token ID2648
Feature activation+2.54e-02

Pos logit contributions
 coffee+0.015
 band+0.015
 puppet+0.014
 bath+0.013
 DVD+0.012
Neg logit contributions
ver-0.025
ust-0.025
achable-0.024
uders-0.024
uding-0.024
Token them
Token ID606
Feature activation+4.70e-05

Pos logit contributions
 coffee+0.027
 band+0.026
 puppet+0.023
 bath+0.023
 DVD+0.021
Neg logit contributions
ver-0.051
ust-0.051
achable-0.050
uders-0.050
uding-0.049
Token on
Token ID319
Feature activation-8.46e-04

Pos logit contributions
 coffee+0.041
 puppet+0.038
 band+0.038
cakes+0.036
eddy+0.035
Neg logit contributions
ver-0.063
 halfway-0.059
ust-0.057
 impossible-0.057
 steep-0.056
Token,
Token ID11
Feature activation-1.62e-02

Pos logit contributions
ust+0.001
ver+0.001
achable+0.001
uders+0.001
uding+0.001
Neg logit contributions
 coffee-0.001
 band-0.001
 puppet-0.001
 bath-0.001
 DVD-0.001
Token whenever
Token ID8797
Feature activation+1.21e-02

Pos logit contributions
ver+0.027
 anyone+0.026
ust+0.026
 rarely+0.025
 ten+0.025
Neg logit contributions
 coffee-0.022
 band-0.021
 puppet-0.021
eddy-0.019
 DVD-0.019
Token they
Token ID484
Feature activation+7.39e-02

Pos logit contributions
 coffee+0.011
 band+0.011
 puppet+0.009
 bath+0.009
 DVD+0.008
Neg logit contributions
ust-0.026
ver-0.026
achable-0.025
uders-0.025
uding-0.025
Token wanted
Token ID2227
Feature activation-2.82e-02

Pos logit contributions
 band+0.074
 coffee+0.069
 bath+0.066
 dish+0.065
 puppet+0.061
Neg logit contributions
achable-0.156
ust-0.152
uders-0.151
ver-0.148
uding-0.147
Token av
Token ID1196
Feature activation-2.51e-01

Pos logit contributions
ust+0.061
uders+0.060
ver+0.060
achable+0.060
uding+0.057
Neg logit contributions
 coffee-0.029
 band-0.027
 bath-0.025
 dish-0.023
 cake-0.021
Tokenoc
Token ID420
Feature activation-7.65e-03

Pos logit contributions
achable+0.426
uders+0.421
ust+0.412
ver+0.408
uding+0.400
Neg logit contributions
 band-0.342
 coffee-0.330
 puppet-0.307
 bath-0.297
eddy-0.295
Tokenados
Token ID22484
Feature activation-1.55e-01

Pos logit contributions
ust+0.014
achable+0.014
 steep+0.014
ver+0.014
 impossible+0.013
Neg logit contributions
 band-0.009
 coffee-0.009
cakes-0.008
 dish-0.008
 kisses-0.008
Token,
Token ID11
Feature activation-3.24e-02

Pos logit contributions
achable+0.260
ust+0.259
uders+0.258
ver+0.253
uding+0.251
Neg logit contributions
 coffee-0.211
 band-0.207
 bath-0.190
 puppet-0.187
 dish-0.176
Token they
Token ID484
Feature activation+7.61e-02

Pos logit contributions
 anyone+0.062
ver+0.061
ust+0.059
 heights+0.059
 impossible+0.058
Neg logit contributions
 band-0.033
 coffee-0.032
eddy-0.031
 puppet-0.031
 DVD-0.031
Token would
Token ID561
Feature activation-1.07e-02

Pos logit contributions
 band+0.097
 coffee+0.087
 puppet+0.086
 dish+0.084
 bath+0.083
Neg logit contributions
uders-0.138
achable-0.136
 heights-0.136
uding-0.132
RR-0.131
Token happy
Token ID3772
Feature activation+4.96e-02

Pos logit contributions
 coffee+0.005
 band+0.004
 puppet+0.004
 bath+0.004
 DVD+0.004
Neg logit contributions
ver-0.006
ust-0.006
 impossible-0.006
achable-0.006
 steep-0.005
Token that
Token ID326
Feature activation+1.07e-01

Pos logit contributions
 coffee+0.060
 band+0.059
 puppet+0.054
 DVD+0.054
 bath+0.054
Neg logit contributions
ver-0.089
ust-0.089
uders-0.087
 heights-0.087
uding-0.086
Token it
Token ID340
Feature activation+1.97e-02

Pos logit contributions
 coffee+0.099
 band+0.094
 bath+0.083
 puppet+0.081
 dish+0.076
Neg logit contributions
ust-0.228
achable-0.224
uders-0.224
ver-0.222
uding-0.219
Token produced
Token ID4635
Feature activation-6.21e-03

Pos logit contributions
 coffee+0.026
 band+0.025
 puppet+0.023
 bath+0.023
 DVD+0.022
Neg logit contributions
ver-0.034
ust-0.034
achable-0.033
uders-0.033
uding-0.033
Token more
Token ID517
Feature activation-3.28e-02

Pos logit contributions
uders+0.012
ver+0.012
ust+0.012
achable+0.012
uding+0.012
Neg logit contributions
 coffee-0.007
 band-0.007
 bath-0.006
 puppet-0.006
 dish-0.006
Token av
Token ID1196
Feature activation-2.50e-01

Pos logit contributions
uders+0.062
achable+0.060
ver+0.060
uding+0.057
RR+0.057
Neg logit contributions
 coffee-0.042
 band-0.041
 dish-0.037
 sound-0.036
 bath-0.036
Tokenoc
Token ID420
Feature activation-1.91e-02

Pos logit contributions
achable+0.411
uders+0.407
ver+0.405
ust+0.404
uding+0.389
Neg logit contributions
 band-0.345
 coffee-0.341
 puppet-0.314
 bath-0.306
eddy-0.299
Tokenados
Token ID22484
Feature activation-1.38e-01

Pos logit contributions
ust+0.035
achable+0.034
ver+0.034
 steep+0.034
uders+0.032
Neg logit contributions
 band-0.022
 coffee-0.022
cakes-0.021
eddy-0.021
ic-0.021
Token than
Token ID621
Feature activation-1.11e-01

Pos logit contributions
ver+0.225
ust+0.219
 impossible+0.207
uding+0.205
uders+0.204
Neg logit contributions
 coffee-0.200
 band-0.196
 puppet-0.183
 bath-0.181
 DVD-0.179
Token ever
Token ID1683
Feature activation-9.01e-02

Pos logit contributions
ust+0.204
uders+0.202
achable+0.202
RR+0.195
uding+0.194
Neg logit contributions
 coffee-0.137
 band-0.130
 sound-0.115
 dish-0.115
 bath-0.113
Token before
Token ID878
Feature activation-6.73e-02

Pos logit contributions
ver+0.142
ust+0.140
achable+0.138
uders+0.138
ierce+0.133
Neg logit contributions
 coffee-0.138
 band-0.126
 puppet-0.119
 bath-0.118
 refreshed-0.117
Token promise
Token ID6991
Feature activation+4.89e-02

Pos logit contributions
uders+0.021
achable+0.020
 heights+0.020
ust+0.020
uding+0.020
Neg logit contributions
 band-0.018
 coffee-0.018
 bath-0.016
 puppet-0.016
 dish-0.016
Token I
Token ID314
Feature activation-4.81e-02

Pos logit contributions
 coffee+0.068
 band+0.065
 bath+0.059
 puppet+0.057
 dish+0.056
Neg logit contributions
ust-0.086
ver-0.084
achable-0.082
uders-0.082
uding-0.079
Token won
Token ID1839
Feature activation-6.84e-02

Pos logit contributions
uders+0.088
 heights+0.085
achable+0.085
uding+0.084
ust+0.082
Neg logit contributions
 band-0.062
 coffee-0.060
 bath-0.055
 puppet-0.054
 dish-0.052
Token't
Token ID470
Feature activation-1.24e-01

Pos logit contributions
ust+0.138
ver+0.127
uders+0.127
achable+0.127
 steep+0.125
Neg logit contributions
 coffee-0.083
 band-0.079
 bath-0.070
 puppet-0.067
 video-0.067
Token tell
Token ID1560
Feature activation+2.65e-02

Pos logit contributions
ver+0.255
uders+0.250
achable+0.246
ust+0.246
uding+0.243
Neg logit contributions
 band-0.131
 coffee-0.130
 bath-0.113
 sound-0.110
 dish-0.102
Token anyone
Token ID2687
Feature activation-2.50e-01

Pos logit contributions
 coffee+0.028
 band+0.025
 cake+0.022
 bath+0.021
 cookies+0.021
Neg logit contributions
ust-0.055
ver-0.055
achable-0.054
uding-0.054
 steep-0.053
Token."
Token ID526
Feature activation+9.09e-03

Pos logit contributions
achable+0.465
uders+0.460
uding+0.455
ver+0.442
ust+0.441
Neg logit contributions
 coffee-0.317
 band-0.290
 puppet-0.261
 bath-0.257
 kisses-0.249
Token The
Token ID383
Feature activation+9.01e-03

Pos logit contributions
 coffee+0.011
 band+0.011
 puppet+0.010
 bath+0.010
 DVD+0.009
Neg logit contributions
ver-0.017
ust-0.016
achable-0.016
uders-0.016
uding-0.016
Token rabbit
Token ID22746
Feature activation-4.41e-02

Pos logit contributions
 band+0.012
 coffee+0.012
 puppet+0.011
 bath+0.011
 sound+0.011
Neg logit contributions
ver-0.017
ust-0.016
uders-0.016
achable-0.015
uding-0.015
Token agreed
Token ID4987
Feature activation+4.77e-03

Pos logit contributions
uders+0.090
ust+0.090
achable+0.088
ver+0.088
uding+0.087
Neg logit contributions
 band-0.046
 coffee-0.043
 puppet-0.041
 bath-0.037
 sound-0.035
Token and
Token ID290
Feature activation+4.53e-03

Pos logit contributions
 DVD+0.008
 coffee+0.008
eddy+0.008
 band+0.008
 bath+0.008
Neg logit contributions
ver-0.006
ust-0.005
 impossible-0.005
 whether-0.005
achable-0.005
Token the
Token ID262
Feature activation+3.49e-02

Pos logit contributions
 coffee+0.014
 band+0.014
 puppet+0.013
 bath+0.012
eddy+0.012
Neg logit contributions
ver-0.026
achable-0.026
ust-0.026
uders-0.026
uding-0.025
Token store
Token ID3650
Feature activation+7.84e-02

Pos logit contributions
 band+0.043
 coffee+0.043
 puppet+0.041
eddy+0.039
 DVD+0.038
Neg logit contributions
achable-0.058
 ten-0.056
 heights-0.056
ust-0.056
 impossible-0.055
Token to
Token ID284
Feature activation-1.21e-02

Pos logit contributions
 coffee+0.126
 band+0.119
 puppet+0.117
 bath+0.116
 DVD+0.115
Neg logit contributions
ver-0.118
ust-0.106
uding-0.104
 ten-0.103
 whether-0.103
Token get
Token ID651
Feature activation+2.53e-02

Pos logit contributions
achable+0.020
 ten+0.020
ver+0.020
 anyone+0.019
uding+0.019
Neg logit contributions
 coffee-0.015
 band-0.015
 puppet-0.015
eddy-0.015
 DVD-0.014
Token more
Token ID517
Feature activation-3.01e-02

Pos logit contributions
 puppet+0.035
 band+0.032
 CD+0.032
 coffee+0.032
 DVD+0.031
Neg logit contributions
 anyone-0.040
 impossible-0.039
ver-0.039
ust-0.038
 ten-0.038
Token av
Token ID1196
Feature activation-2.49e-01

Pos logit contributions
ver+0.052
ust+0.052
uders+0.051
achable+0.051
uding+0.050
Neg logit contributions
 coffee-0.040
 band-0.039
 puppet-0.036
 bath-0.035
 DVD-0.033
Tokenoc
Token ID420
Feature activation-9.34e-03

Pos logit contributions
ver+0.360
ust+0.359
achable+0.348
uders+0.348
uding+0.340
Neg logit contributions
 coffee-0.400
 band-0.390
 puppet-0.368
 bath-0.363
 DVD-0.348
Tokenados
Token ID22484
Feature activation-1.41e-01

Pos logit contributions
ust+0.016
ver+0.015
achable+0.015
 steep+0.015
 impossible+0.014
Neg logit contributions
 coffee-0.013
 band-0.013
 dish-0.011
eddy-0.011
cakes-0.011
Token.
Token ID13
Feature activation+1.16e-02

Pos logit contributions
ver+0.225
ust+0.222
uders+0.207
achable+0.206
uding+0.206
Neg logit contributions
 coffee-0.203
 band-0.197
 puppet-0.188
 DVD-0.182
 bath-0.181
Token Gary
Token ID10936
Feature activation-8.07e-02

Pos logit contributions
 coffee+0.017
 band+0.017
 puppet+0.016
 bath+0.016
 DVD+0.015
Neg logit contributions
ust-0.018
ver-0.018
achable-0.018
uders-0.017
uding-0.017
Token looked
Token ID3114
Feature activation+2.06e-02

Pos logit contributions
ust+0.155
ver+0.154
achable+0.151
uders+0.151
uding+0.148
Neg logit contributions
 coffee-0.090
 band-0.087
 puppet-0.080
 bath-0.078
 DVD-0.074
Token went
Token ID1816
Feature activation-1.82e-02

Pos logit contributions
ver+0.007
ust+0.007
uders+0.006
achable+0.006
uding+0.006
Neg logit contributions
 coffee-0.005
 band-0.005
 puppet-0.004
 bath-0.004
 DVD-0.004
Token she
Token ID673
Feature activation-4.13e-03

Pos logit contributions
ver+0.027
uders+0.026
ust+0.026
 heights+0.025
achable+0.025
Neg logit contributions
 coffee-0.029
 band-0.028
 puppet-0.027
 DVD-0.026
 bath-0.026
Token searched
Token ID16499
Feature activation-5.75e-02

Pos logit contributions
ust+0.007
ver+0.007
achable+0.007
uders+0.007
uding+0.007
Neg logit contributions
 band-0.005
 coffee-0.005
 puppet-0.005
 bath-0.005
 dish-0.005
Token for
Token ID329
Feature activation+1.89e-02

Pos logit contributions
achable+0.117
ust+0.117
uders+0.116
ver+0.115
uding+0.113
Neg logit contributions
 coffee-0.063
 band-0.061
 bath-0.055
 puppet-0.052
 dish-0.050
Token or
Token ID393
Feature activation-3.01e-02

Pos logit contributions
 band+0.021
 coffee+0.019
 cake+0.016
 bath+0.016
 cookies+0.016
Neg logit contributions
ver-0.042
ust-0.042
ierce-0.041
achable-0.041
uders-0.041
Tokennam
Token ID7402
Feature activation-2.49e-01

Pos logit contributions
ver+0.026
uders+0.026
ust+0.026
uding+0.024
achable+0.023
Neg logit contributions
 coffee-0.066
 band-0.066
 bath-0.062
 puppet-0.062
 sound-0.062
Tokenents
Token ID658
Feature activation-1.54e-01

Pos logit contributions
ver+0.203
ust+0.202
achable+0.193
uders+0.192
uding+0.184
Neg logit contributions
 coffee-0.553
 band-0.543
 puppet-0.521
 bath-0.516
 DVD-0.501
Token,
Token ID11
Feature activation-3.46e-02

Pos logit contributions
ver+0.255
ust+0.244
uders+0.235
achable+0.232
uding+0.229
Neg logit contributions
 coffee-0.224
 band-0.213
 puppet-0.203
 bath-0.199
 DVD-0.196
Token and
Token ID290
Feature activation+1.87e-02

Pos logit contributions
ver+0.055
ust+0.054
achable+0.053
uders+0.052
 heights+0.052
Neg logit contributions
 coffee-0.050
 band-0.049
 puppet-0.047
 bath-0.045
 DVD-0.044
Token the
Token ID262
Feature activation+9.90e-03

Pos logit contributions
 coffee+0.023
 band+0.022
 puppet+0.020
 bath+0.020
 dish+0.018
Neg logit contributions
ust-0.035
ver-0.035
uders-0.034
achable-0.034
uding-0.033
Token more
Token ID517
Feature activation-2.38e-02

Pos logit contributions
 band+0.011
 coffee+0.011
 sound+0.010
 cake+0.010
 dish+0.010
Neg logit contributions
ver-0.021
ierce-0.021
ust-0.020
uders-0.020
achable-0.020
Token every
Token ID790
Feature activation-1.83e-02

Pos logit contributions
ver+0.077
ust+0.076
achable+0.074
uders+0.074
uding+0.073
Neg logit contributions
 coffee-0.072
 band-0.070
 puppet-0.066
 bath-0.064
 DVD-0.062
Token day
Token ID1110
Feature activation+9.47e-02

Pos logit contributions
ver+0.039
ust+0.039
achable+0.038
uders+0.038
uding+0.038
Neg logit contributions
 coffee-0.016
 band-0.015
 puppet-0.014
 bath-0.013
 DVD-0.013
Token to
Token ID284
Feature activation-2.64e-02

Pos logit contributions
 coffee+0.130
 band+0.127
 puppet+0.118
 bath+0.116
 DVD+0.111
Neg logit contributions
ver-0.157
ust-0.157
achable-0.153
uders-0.153
uding-0.150
Token supply
Token ID5127
Feature activation+2.31e-02

Pos logit contributions
ver+0.050
ust+0.050
uders+0.049
achable+0.049
uding+0.048
Neg logit contributions
 coffee-0.031
 band-0.030
 puppet-0.027
 bath-0.027
 dish-0.025
Token the
Token ID262
Feature activation-1.62e-02

Pos logit contributions
 coffee+0.028
 band+0.027
 puppet+0.025
 bath+0.025
 DVD+0.023
Neg logit contributions
ver-0.042
ust-0.042
achable-0.041
uders-0.041
uding-0.040
Token av
Token ID1196
Feature activation-2.49e-01

Pos logit contributions
ver+0.031
uders+0.030
ierce+0.029
achable+0.029
ust+0.029
Neg logit contributions
 band-0.020
 coffee-0.020
 dish-0.018
 sound-0.018
 bath-0.018
Tokenoc
Token ID420
Feature activation-1.83e-04

Pos logit contributions
uders+0.404
ver+0.404
achable+0.402
ust+0.397
uding+0.384
Neg logit contributions
 band-0.345
 coffee-0.344
 puppet-0.317
 bath-0.309
 dish-0.305
Tokenados
Token ID22484
Feature activation-1.39e-01

Pos logit contributions
ver+0.000
ust+0.000
achable+0.000
 steep+0.000
 impossible+0.000
Neg logit contributions
 band-0.000
 coffee-0.000
eddy-0.000
 dish-0.000
cakes-0.000
Token.
Token ID13
Feature activation+4.02e-03

Pos logit contributions
ver+0.243
ust+0.243
uders+0.239
achable+0.239
uding+0.233
Neg logit contributions
 coffee-0.179
 band-0.173
 puppet-0.161
 bath-0.158
 DVD-0.149
Token And
Token ID843
Feature activation+2.96e-02

Pos logit contributions
 coffee+0.005
 band+0.005
 bath+0.004
 puppet+0.004
 DVD+0.004
Neg logit contributions
ust-0.007
uders-0.007
ver-0.007
achable-0.007
uding-0.007
Token the
Token ID262
Feature activation+1.75e-02

Pos logit contributions
 coffee+0.044
 band+0.044
 puppet+0.041
 bath+0.040
 DVD+0.040
Neg logit contributions
ver-0.047
ust-0.045
 impossible-0.044
 heights-0.043
 anyone-0.043
Token worked
Token ID3111
Feature activation-5.85e-03

Pos logit contributions
ver+0.022
ust+0.022
achable+0.022
uders+0.022
uding+0.021
Neg logit contributions
 coffee-0.022
 band-0.021
 puppet-0.020
 bath-0.020
 DVD-0.019
Token hard
Token ID1327
Feature activation-4.81e-02

Pos logit contributions
uders+0.013
achable+0.012
uding+0.012
ust+0.012
RR+0.011
Neg logit contributions
 band-0.006
 coffee-0.006
 sound-0.005
 puppet-0.005
 bath-0.005
Token and
Token ID290
Feature activation+6.29e-03

Pos logit contributions
ust+0.097
ver+0.095
uders+0.094
achable+0.094
uding+0.091
Neg logit contributions
 coffee-0.052
 band-0.050
 bath-0.044
 puppet-0.044
 dish-0.040
Token never
Token ID1239
Feature activation-7.85e-02

Pos logit contributions
 coffee+0.009
 band+0.009
 puppet+0.009
 bath+0.008
 DVD+0.008
Neg logit contributions
ver-0.010
ust-0.010
achable-0.010
uders-0.010
uding-0.009
Token told
Token ID1297
Feature activation-3.18e-03

Pos logit contributions
ust+0.124
ver+0.124
uders+0.121
achable+0.121
uding+0.118
Neg logit contributions
 coffee-0.114
 band-0.113
 puppet-0.104
 bath-0.103
 DVD-0.097
Token anybody
Token ID9599
Feature activation-2.49e-01

Pos logit contributions
ver+0.006
ust+0.006
uders+0.006
achable+0.006
uding+0.006
Neg logit contributions
 coffee-0.004
 band-0.003
 bath-0.003
 puppet-0.003
 video-0.003
Token a
Token ID257
Feature activation-5.48e-02

Pos logit contributions
uders+0.439
ust+0.437
achable+0.436
ver+0.436
uding+0.432
Neg logit contributions
 coffee-0.326
 band-0.305
 puppet-0.286
 bath-0.275
 dish-0.261
Token lie
Token ID6486
Feature activation-3.28e-02

Pos logit contributions
ver+0.097
ust+0.097
uders+0.094
achable+0.094
uding+0.092
Neg logit contributions
 coffee-0.071
 band-0.069
 puppet-0.064
 bath-0.063
 DVD-0.059
Token.
Token ID13
Feature activation+1.54e-03

Pos logit contributions
ver+0.052
ust+0.050
uders+0.049
achable+0.048
uding+0.048
Neg logit contributions
 coffee-0.047
 band-0.047
 bath-0.044
 puppet-0.043
 DVD-0.042
Token
Token ID220
Feature activation-2.95e-02

Pos logit contributions
 coffee+0.002
 band+0.002
 puppet+0.002
 bath+0.001
 DVD+0.001
Neg logit contributions
ust-0.003
ver-0.003
achable-0.003
uders-0.003
uding-0.003
Token
Token ID198
Feature activation-2.01e-02

Pos logit contributions
uders+0.068
 heights+0.066
achable+0.066
uding+0.066
ust+0.066
Neg logit contributions
 coffee-0.021
 band-0.021
 bath-0.018
 puppet-0.017
 DVD-0.016
Token Maggie
Token ID33014
Feature activation-3.88e-02

Pos logit contributions
 coffee+0.001
 band+0.001
 puppet+0.001
 bath+0.001
 DVD+0.001
Neg logit contributions
ver-0.001
ust-0.001
achable-0.001
uders-0.001
uding-0.001
Token breathed
Token ID39545
Feature activation+4.03e-02

Pos logit contributions
ver+0.069
ust+0.067
uders+0.066
achable+0.065
uding+0.065
Neg logit contributions
 coffee-0.051
 band-0.046
 bath-0.045
 puppet-0.043
 DVD-0.043
Token a
Token ID257
Feature activation+1.62e-02

Pos logit contributions
 coffee+0.053
 band+0.052
 puppet+0.048
 bath+0.047
 DVD+0.044
Neg logit contributions
ust-0.071
ver-0.070
uders-0.069
achable-0.068
uding-0.067
Token sigh
Token ID19680
Feature activation+2.90e-03

Pos logit contributions
eddy+0.027
 coffee+0.025
cakes+0.024
rolley+0.023
Kids+0.022
Neg logit contributions
 steep-0.021
 impossible-0.021
ver-0.019
RR-0.019
ust-0.019
Token of
Token ID286
Feature activation+8.56e-02

Pos logit contributions
 coffee+0.005
 band+0.004
 puppet+0.004
 DVD+0.004
uggle+0.004
Neg logit contributions
ver-0.004
ust-0.004
 impossible-0.004
 steep-0.004
uding-0.003
Token relief
Token ID8259
Feature activation+1.23e-01

Pos logit contributions
 coffee+0.111
 band+0.109
 puppet+0.107
eddy+0.106
 bath+0.101
Neg logit contributions
 heights-0.140
achable-0.138
 impossible-0.137
ver-0.135
ust-0.134
Token and
Token ID290
Feature activation+3.18e-02

Pos logit contributions
 coffee+0.216
 band+0.211
uggle+0.209
 DVD+0.208
eddy+0.207
Neg logit contributions
ver-0.129
uding-0.127
 heights-0.122
uders-0.121
 impossible-0.120
Token happily
Token ID18177
Feature activation-1.29e-01

Pos logit contributions
 coffee+0.047
eddy+0.045
 bath+0.044
 band+0.043
 DVD+0.043
Neg logit contributions
ver-0.050
achable-0.047
ust-0.047
 anyone-0.046
uders-0.046
Token sc
Token ID629
Feature activation-7.19e-02

Pos logit contributions
ver+0.180
ust+0.160
 ten+0.153
 ignored+0.150
uding+0.149
Neg logit contributions
 coffee-0.218
 DVD-0.203
eddy-0.203
 video-0.197
 CD-0.193
Tokenur
Token ID333
Feature activation-1.81e-01

Pos logit contributions
uders+0.091
ust+0.089
achable+0.089
uding+0.087
ver+0.087
Neg logit contributions
 coffee-0.126
 band-0.126
 puppet-0.117
 bath-0.115
 DVD-0.112
Tokenried
Token ID2228
Feature activation-9.88e-02

Pos logit contributions
ver+0.124
ust+0.119
achable+0.113
uders+0.113
uding+0.110
Neg logit contributions
 coffee-0.435
 band-0.421
 bath-0.408
 puppet-0.407
 DVD-0.397
Token it
Token ID340
Feature activation+7.29e-02

Pos logit contributions
 heights+0.098
 ten+0.097
 anyone+0.096
achable+0.091
 halfway+0.090
Neg logit contributions
cakes-0.089
 coffee-0.088
ugg-0.087
eddy-0.084
uggle-0.083
Token.
Token ID13
Feature activation+2.81e-02

Pos logit contributions
 coffee+0.111
 band+0.105
 puppet+0.100
 bath+0.098
 DVD+0.096
Neg logit contributions
ver-0.109
ust-0.108
achable-0.105
 impossible-0.103
uding-0.103
Token She
Token ID1375
Feature activation+1.32e-03

Pos logit contributions
 coffee+0.033
 band+0.032
 puppet+0.030
 bath+0.029
 DVD+0.028
Neg logit contributions
ver-0.053
ust-0.052
achable-0.051
uders-0.051
uding-0.050
Token played
Token ID2826
Feature activation+8.28e-02

Pos logit contributions
 band+0.002
 coffee+0.002
 puppet+0.001
 bath+0.001
 DVD+0.001
Neg logit contributions
ust-0.002
ver-0.002
achable-0.002
uders-0.002
uding-0.002
Token a
Token ID257
Feature activation+3.01e-03

Pos logit contributions
 coffee+0.116
eddy+0.114
ugg+0.107
rolley+0.106
cakes+0.105
Neg logit contributions
 ten-0.127
 heights-0.125
achable-0.123
ver-0.123
 whether-0.117
Token song
Token ID3496
Feature activation+8.10e-02

Pos logit contributions
 coffee+0.004
cakes+0.004
eddy+0.003
 kisses+0.003
 band+0.003
Neg logit contributions
ust-0.005
achable-0.005
RR-0.005
 steep-0.005
ver-0.005
Token that
Token ID326
Feature activation+1.36e-01

Pos logit contributions
 coffee+0.130
 band+0.122
 bath+0.118
eddy+0.116
 dish+0.112
Neg logit contributions
ver-0.121
 ten-0.115
ust-0.106
 impossible-0.105
 whether-0.105
Token she
Token ID673
Feature activation+1.23e-02

Pos logit contributions
 coffee+0.163
 band+0.157
 puppet+0.145
 bath+0.144
 DVD+0.140
Neg logit contributions
ver-0.247
ust-0.241
uders-0.236
achable-0.234
 anyone-0.232
Token learned
Token ID4499
Feature activation+4.26e-02

Pos logit contributions
 band+0.016
 coffee+0.016
 puppet+0.015
 bath+0.014
 DVD+0.013
Neg logit contributions
ust-0.021
ver-0.021
achable-0.021
uders-0.021
uding-0.021
Token from
Token ID422
Feature activation-7.96e-02

Pos logit contributions
 coffee+0.055
 band+0.052
 puppet+0.047
 bath+0.046
 sound+0.044
Neg logit contributions
ver-0.078
uders-0.078
ust-0.077
achable-0.076
uding-0.076
Token her
Token ID607
Feature activation-1.14e-02

Pos logit contributions
ver+0.178
ust+0.177
uders+0.166
uding+0.166
achable+0.164
Neg logit contributions
 coffee-0.076
 band-0.070
 puppet-0.063
 bath-0.059
 sound-0.056
Token away
Token ID1497
Feature activation+2.02e-04

Pos logit contributions
ust+0.060
ver+0.060
achable+0.059
uders+0.058
uding+0.058
Neg logit contributions
 coffee-0.038
 band-0.036
 puppet-0.033
 bath-0.032
 DVD-0.031
Token.
Token ID13
Feature activation+8.24e-03

Pos logit contributions
 coffee+0.000
 band+0.000
 puppet+0.000
 bath+0.000
 DVD+0.000
Neg logit contributions
ver-0.000
ust-0.000
uders-0.000
achable-0.000
uding-0.000
Token Lily
Token ID20037
Feature activation+2.99e-02

Pos logit contributions
 band+0.011
 coffee+0.011
 puppet+0.011
 dish+0.010
 DVD+0.010
Neg logit contributions
ver-0.013
ust-0.013
achable-0.013
 impossible-0.012
uders-0.012
Token felt
Token ID2936
Feature activation+1.40e-02

Pos logit contributions
 coffee+0.039
 band+0.036
 bath+0.034
 puppet+0.034
 DVD+0.033
Neg logit contributions
ver-0.053
ust-0.052
achable-0.051
uders-0.051
uding-0.050
Token happy
Token ID3772
Feature activation+8.68e-02

Pos logit contributions
 coffee+0.020
 puppet+0.020
eddy+0.019
 band+0.019
cakes+0.019
Neg logit contributions
ver-0.022
 impossible-0.022
ust-0.021
 anyone-0.021
achable-0.021
Token that
Token ID326
Feature activation+1.29e-01

Pos logit contributions
 coffee+0.148
 DVD+0.145
 kettle+0.139
 puppet+0.135
cakes+0.135
Neg logit contributions
 heights-0.109
 whether-0.108
ust-0.107
 anyone-0.106
ver-0.104
Token she
Token ID673
Feature activation+3.42e-03

Pos logit contributions
 coffee+0.123
 band+0.117
 puppet+0.113
 DVD+0.103
 bath+0.100
Neg logit contributions
ver-0.271
ust-0.264
achable-0.260
 anyone-0.258
 impossible-0.258
Token could
Token ID714
Feature activation-2.85e-02

Pos logit contributions
 coffee+0.006
 band+0.005
 DVD+0.005
 bath+0.005
 puppet+0.005
Neg logit contributions
ver-0.005
ust-0.004
uders-0.004
achable-0.004
uding-0.004
Token help
Token ID1037
Feature activation+2.92e-02

Pos logit contributions
ver+0.051
ust+0.049
achable+0.049
uders+0.047
uding+0.047
Neg logit contributions
 coffee-0.038
 band-0.033
 puppet-0.033
 DVD-0.032
 bath-0.031
Token the
Token ID262
Feature activation-1.81e-02

Pos logit contributions
 coffee+0.035
 band+0.033
 puppet+0.032
 DVD+0.031
 bath+0.031
Neg logit contributions
ver-0.052
ust-0.052
achable-0.051
 heights-0.051
uders-0.051
Token bird
Token ID6512
Feature activation-7.67e-02

Pos logit contributions
ust+0.033
achable+0.032
uders+0.032
ver+0.032
 heights+0.031
Neg logit contributions
 coffee-0.022
 band-0.020
 puppet-0.020
 DVD-0.020
 bath-0.019
Token day
Token ID1110
Feature activation+1.22e-01

Pos logit contributions
ust+0.254
ver+0.245
ierce+0.243
achable+0.235
 steep+0.233
Neg logit contributions
 coffee-0.168
 band-0.165
 puppet-0.161
 DVD-0.154
 refreshed-0.152
Token,
Token ID11
Feature activation-1.44e-02

Pos logit contributions
 coffee+0.178
 band+0.171
 bath+0.162
 puppet+0.156
 DVD+0.148
Neg logit contributions
ust-0.207
achable-0.200
uders-0.199
ver-0.198
uding-0.197
Token she
Token ID673
Feature activation+4.65e-03

Pos logit contributions
ver+0.027
achable+0.026
 anyone+0.026
ust+0.026
uders+0.025
Neg logit contributions
 coffee-0.015
 band-0.015
 puppet-0.015
 DVD-0.014
eddy-0.013
Token drew
Token ID9859
Feature activation+7.60e-02

Pos logit contributions
 coffee+0.006
 band+0.006
 puppet+0.006
 bath+0.006
 DVD+0.005
Neg logit contributions
ver-0.008
ust-0.008
achable-0.008
uders-0.008
uding-0.008
Token a
Token ID257
Feature activation-2.45e-03

Pos logit contributions
 coffee+0.129
 bath+0.122
 band+0.120
uggle+0.120
 refreshed+0.120
Neg logit contributions
 anyone-0.093
 ten-0.091
ver-0.091
achable-0.088
ust-0.085
Token picture
Token ID4286
Feature activation+8.47e-02

Pos logit contributions
ust+0.004
achable+0.004
 impossible+0.004
 steep+0.004
uders+0.004
Neg logit contributions
 coffee-0.003
 band-0.003
ugg-0.003
 bath-0.003
uggle-0.003
Token of
Token ID286
Feature activation+5.02e-02

Pos logit contributions
 coffee+0.102
 refreshed+0.096
 band+0.094
 bath+0.092
Kids+0.089
Neg logit contributions
ver-0.143
 ten-0.141
 anyone-0.136
 eleven-0.131
 1-0.129
Token her
Token ID607
Feature activation-1.34e-02

Pos logit contributions
 coffee+0.069
 band+0.067
 puppet+0.065
ugg+0.064
uggle+0.064
Neg logit contributions
 anyone-0.075
 heights-0.074
achable-0.074
uders-0.074
 ten-0.073
Token dog
Token ID3290
Feature activation+1.92e-02

Pos logit contributions
ver+0.024
ust+0.023
achable+0.023
uders+0.023
uding+0.022
Neg logit contributions
 coffee-0.018
 band-0.017
 puppet-0.016
 bath-0.016
 DVD-0.015
Token,
Token ID11
Feature activation-2.58e-02

Pos logit contributions
 coffee+0.028
 band+0.027
 puppet+0.025
 bath+0.025
 refreshed+0.024
Neg logit contributions
ver-0.030
uders-0.029
ust-0.029
achable-0.029
uding-0.028
Token Spot
Token ID15899
Feature activation-4.30e-02

Pos logit contributions
ust+0.046
ver+0.045
uders+0.045
achable+0.044
uding+0.044
Neg logit contributions
 coffee-0.034
 band-0.033
 puppet-0.031
 bath-0.030
 DVD-0.029
Token each
Token ID1123
Feature activation+2.78e-02

Pos logit contributions
 coffee+0.067
 band+0.064
 puppet+0.060
 bath+0.059
 DVD+0.057
Neg logit contributions
ver-0.075
ust-0.074
uders-0.072
achable-0.072
uding-0.071
Token had
Token ID550
Feature activation+3.04e-02

Pos logit contributions
 coffee+0.044
 band+0.040
 puppet+0.040
eddy+0.039
uggle+0.038
Neg logit contributions
ver-0.038
 ten-0.038
ust-0.037
 anyone-0.036
 rarely-0.035
Token a
Token ID257
Feature activation-1.43e-02

Pos logit contributions
 band+0.046
 coffee+0.045
 puppet+0.044
eddy+0.043
uggle+0.043
Neg logit contributions
 ten-0.042
ust-0.042
 anyone-0.042
uders-0.041
ver-0.040
Token special
Token ID2041
Feature activation+4.09e-02

Pos logit contributions
 impossible+0.020
ust+0.020
ver+0.020
 ten+0.019
achable+0.019
Neg logit contributions
 coffee-0.019
 band-0.019
eddy-0.018
 puppet-0.017
cakes-0.017
Token purple
Token ID14032
Feature activation-7.65e-03

Pos logit contributions
 coffee+0.038
 refreshed+0.038
 band+0.037
eddy+0.036
 puppet+0.035
Neg logit contributions
 impossible-0.069
 ten-0.069
ver-0.069
 age-0.068
achable-0.067
Token dress
Token ID6576
Feature activation+1.02e-01

Pos logit contributions
uders+0.014
 ten+0.014
achable+0.014
uding+0.014
 anyone+0.013
Neg logit contributions
 coffee-0.007
 refreshed-0.007
 band-0.006
 puppet-0.006
hes-0.006
Token on
Token ID319
Feature activation-2.55e-02

Pos logit contributions
 band+0.171
 coffee+0.166
 refreshed+0.162
Kids+0.160
 bath+0.159
Neg logit contributions
ver-0.125
ust-0.108
uders-0.107
 ten-0.107
 whether-0.103
Token,
Token ID11
Feature activation-2.40e-02

Pos logit contributions
achable+0.048
ver+0.048
uders+0.048
ust+0.047
uding+0.046
Neg logit contributions
 band-0.028
 coffee-0.028
 puppet-0.025
 bath-0.024
 DVD-0.023
Token just
Token ID655
Feature activation-7.92e-02

Pos logit contributions
ver+0.034
achable+0.034
 whether+0.033
ust+0.033
uders+0.033
Neg logit contributions
 band-0.034
 coffee-0.033
 bath-0.032
 puppet-0.032
eddy-0.031
Token for
Token ID329
Feature activation+1.62e-02

Pos logit contributions
ver+0.084
ust+0.083
achable+0.082
uders+0.081
uding+0.080
Neg logit contributions
 band-0.152
 coffee-0.150
 puppet-0.145
 bath-0.142
eddy-0.138
Token the
Token ID262
Feature activation-9.17e-03

Pos logit contributions
 band+0.020
 coffee+0.020
 puppet+0.019
eddy+0.018
 bath+0.018
Neg logit contributions
uders-0.027
 anyone-0.027
ust-0.027
ver-0.027
achable-0.026
Token"
Token ID1
Feature activation+1.73e-02

Pos logit contributions
ver+0.001
ust+0.001
achable+0.001
uders+0.001
uding+0.001
Neg logit contributions
 coffee-0.001
 band-0.001
 puppet-0.001
 bath-0.001
 DVD-0.001
TokenWow
Token ID22017
Feature activation-2.38e-02

Pos logit contributions
 coffee+0.024
 band+0.023
 puppet+0.022
 bath+0.022
 DVD+0.021
Neg logit contributions
ust-0.027
achable-0.027
ver-0.027
uders-0.026
uding-0.026
Token,
Token ID11
Feature activation-2.74e-03

Pos logit contributions
ust+0.040
achable+0.039
ver+0.039
uding+0.039
uders+0.038
Neg logit contributions
 coffee-0.033
 band-0.032
 puppet-0.030
 bath-0.030
 dish-0.027
Token that
Token ID326
Feature activation+1.41e-01

Pos logit contributions
 anyone+0.005
 ten+0.004
uders+0.004
 anybody+0.004
ust+0.004
Neg logit contributions
eddy-0.004
 coffee-0.004
 DVD-0.004
uggle-0.004
rolley-0.003
Token's
Token ID338
Feature activation+3.03e-02

Pos logit contributions
 coffee+0.158
eddy+0.151
 DVD+0.147
 band+0.146
ugg+0.145
Neg logit contributions
uders-0.245
ust-0.244
 impossible-0.243
achable-0.242
 heights-0.239
Token cool
Token ID3608
Feature activation+2.79e-02

Pos logit contributions
 coffee+0.039
 band+0.035
 bath+0.032
 puppet+0.032
 sound+0.032
Neg logit contributions
ver-0.059
uding-0.055
uders-0.055
ust-0.055
ierce-0.054
Token!"
Token ID2474
Feature activation+4.41e-02

Pos logit contributions
 coffee+0.053
 band+0.052
 puppet+0.050
 DVD+0.050
 bath+0.049
Neg logit contributions
ust-0.029
uders-0.029
 heights-0.028
achable-0.028
ver-0.027
Token Lily
Token ID20037
Feature activation+5.28e-02

Pos logit contributions
 coffee+0.071
eddy+0.068
 band+0.068
uggle+0.068
 DVD+0.067
Neg logit contributions
ver-0.056
 anyone-0.055
achable-0.054
uders-0.053
 heights-0.053
Token said
Token ID531
Feature activation+1.08e-01

Pos logit contributions
 coffee+0.054
 band+0.050
 bath+0.048
 DVD+0.047
 puppet+0.045
Neg logit contributions
ver-0.104
ust-0.102
uders-0.101
achable-0.100
uding-0.098
Token.
Token ID13
Feature activation+2.62e-02

Pos logit contributions
 coffee+0.186
 puppet+0.175
 band+0.173
 bath+0.171
 DVD+0.169
Neg logit contributions
ver-0.148
ust-0.130
achable-0.126
 halfway-0.125
uding-0.124
Token
Token ID198
Feature activation-1.13e-02

Pos logit contributions
 coffee+0.031
 band+0.030
 puppet+0.027
 bath+0.027
 DVD+0.025
Neg logit contributions
ust-0.050
ver-0.049
uders-0.049
achable-0.048
uding-0.048
Token but
Token ID475
Feature activation-4.75e-02

Pos logit contributions
ust+0.028
ver+0.028
uders+0.027
achable+0.027
uding+0.026
Neg logit contributions
 coffee-0.032
 band-0.031
 puppet-0.029
 bath-0.029
 DVD-0.027
Token all
Token ID477
Feature activation-6.80e-02

Pos logit contributions
ust+0.117
uders+0.113
uding+0.112
ierce+0.111
RR+0.110
Neg logit contributions
 band-0.030
 coffee-0.028
 sound-0.024
 bath-0.024
 refreshed-0.021
Token of
Token ID286
Feature activation+3.46e-02

Pos logit contributions
ver+0.106
 anyone+0.106
 steep+0.105
 impossible+0.104
ust+0.103
Neg logit contributions
 coffee-0.101
 CD-0.092
 DVD-0.092
 band-0.092
eddy-0.091
Token the
Token ID262
Feature activation+9.92e-04

Pos logit contributions
 coffee+0.036
 band+0.035
 bath+0.031
 puppet+0.029
 sound+0.027
Neg logit contributions
ver-0.073
ust-0.072
uders-0.070
uding-0.069
achable-0.069
Token seats
Token ID8632
Feature activation-2.37e-03

Pos logit contributions
 band+0.001
 coffee+0.001
 bath+0.001
 puppet+0.001
 sound+0.001
Neg logit contributions
ver-0.002
uders-0.002
ust-0.002
achable-0.002
uding-0.002
Token were
Token ID547
Feature activation+9.80e-04

Pos logit contributions
ver+0.004
ust+0.004
uders+0.004
achable+0.004
uding+0.004
Neg logit contributions
 coffee-0.003
 band-0.003
 puppet-0.003
 bath-0.003
 DVD-0.003
Token too
Token ID1165
Feature activation-7.69e-02

Pos logit contributions
 band+0.001
 coffee+0.001
 bath+0.001
 puppet+0.001
 sound+0.001
Neg logit contributions
ver-0.002
uders-0.002
ust-0.002
RR-0.002
achable-0.002
Token hard
Token ID1327
Feature activation-6.72e-02

Pos logit contributions
uders+0.156
uding+0.154
ver+0.144
achable+0.143
 habitats+0.141
Neg logit contributions
 coffee-0.091
 band-0.090
 sound-0.076
 bath-0.076
 cup-0.075
Token.
Token ID13
Feature activation-2.89e-03

Pos logit contributions
ver+0.106
ust+0.104
 impossible+0.101
uding+0.100
achable+0.100
Neg logit contributions
 coffee-0.099
 band-0.097
 puppet-0.091
 bath-0.087
 DVD-0.087
Token It
Token ID632
Feature activation+1.74e-02

Pos logit contributions
ust+0.006
uders+0.006
ver+0.006
uding+0.006
achable+0.006
Neg logit contributions
 coffee-0.003
 band-0.003
 bath-0.002
 puppet-0.002
 DVD-0.002
Token didn
Token ID1422
Feature activation-3.73e-02

Pos logit contributions
 band+0.018
 coffee+0.016
 puppet+0.015
 bath+0.015
 sound+0.014
Neg logit contributions
uders-0.037
ust-0.036
ver-0.036
achable-0.036
uding-0.036
Token and
Token ID290
Feature activation+4.13e-02

Pos logit contributions
ver+0.003
ust+0.003
achable+0.003
uders+0.003
uding+0.003
Neg logit contributions
 coffee-0.002
 band-0.002
 puppet-0.002
 bath-0.002
 DVD-0.002
Token fell
Token ID3214
Feature activation+2.67e-02

Pos logit contributions
 coffee+0.058
 band+0.053
 bath+0.052
 puppet+0.052
eddy+0.052
Neg logit contributions
ver-0.065
achable-0.064
 steep-0.063
uders-0.063
 ten-0.062
Token to
Token ID284
Feature activation+1.67e-02

Pos logit contributions
 coffee+0.032
 band+0.030
 puppet+0.029
 bath+0.028
 DVD+0.026
Neg logit contributions
ver-0.049
ust-0.049
achable-0.048
uders-0.048
uding-0.047
Token the
Token ID262
Feature activation+3.44e-02

Pos logit contributions
 coffee+0.019
 band+0.019
 puppet+0.018
 bath+0.017
 DVD+0.016
Neg logit contributions
ver-0.031
achable-0.030
ust-0.030
uders-0.030
uding-0.030
Token floor
Token ID4314
Feature activation+6.89e-02

Pos logit contributions
 coffee+0.048
 band+0.047
 puppet+0.044
 bath+0.043
 DVD+0.041
Neg logit contributions
ver-0.058
ust-0.058
achable-0.055
uders-0.055
uding-0.055
Token.
Token ID13
Feature activation+2.57e-02

Pos logit contributions
 coffee+0.098
 band+0.095
 puppet+0.089
 bath+0.088
 DVD+0.084
Neg logit contributions
ver-0.110
ust-0.109
achable-0.107
uders-0.107
uding-0.105
Token Lily
Token ID20037
Feature activation+3.99e-02

Pos logit contributions
 coffee+0.032
 band+0.032
 puppet+0.031
 bath+0.028
 sound+0.028
Neg logit contributions
ver-0.044
achable-0.043
ust-0.043
uders-0.042
uding-0.041
Token laughed
Token ID13818
Feature activation+1.70e-02

Pos logit contributions
 coffee+0.048
 band+0.045
 puppet+0.042
 bath+0.042
 DVD+0.039
Neg logit contributions
ver-0.074
ust-0.073
uders-0.072
achable-0.072
uding-0.070
Token.
Token ID13
Feature activation+3.66e-02

Pos logit contributions
 coffee+0.027
 band+0.025
 bath+0.024
 puppet+0.024
 kettle+0.024
Neg logit contributions
ust-0.024
ver-0.024
achable-0.023
 impossible-0.022
 heights-0.022
Token She
Token ID1375
Feature activation-5.59e-04

Pos logit contributions
 coffee+0.038
 band+0.037
 puppet+0.033
 bath+0.033
 DVD+0.030
Neg logit contributions
ust-0.074
ver-0.074
uders-0.072
achable-0.072
uding-0.071
Token pulled
Token ID5954
Feature activation+1.83e-02

Pos logit contributions
ver+0.001
ust+0.001
uders+0.001
uding+0.001
achable+0.001
Neg logit contributions
 band-0.001
 coffee-0.001
 puppet-0.001
 bath-0.000
 sound-0.000
Token was
Token ID373
Feature activation+3.93e-03

Pos logit contributions
ver+0.048
ust+0.047
achable+0.046
uders+0.046
uding+0.045
Neg logit contributions
 coffee-0.033
 band-0.033
 puppet-0.031
 bath-0.029
 DVD-0.028
Token so
Token ID523
Feature activation+1.94e-02

Pos logit contributions
 coffee+0.006
 band+0.006
 puppet+0.005
 bath+0.005
 DVD+0.005
Neg logit contributions
ver-0.006
ust-0.006
achable-0.006
uders-0.006
uding-0.006
Token ugly
Token ID13400
Feature activation-3.35e-02

Pos logit contributions
 coffee+0.027
 band+0.027
 puppet+0.025
 bath+0.024
 DVD+0.023
Neg logit contributions
ver-0.032
ust-0.032
uders-0.031
achable-0.031
uding-0.031
Token that
Token ID326
Feature activation+1.21e-01

Pos logit contributions
ust+0.067
ver+0.067
achable+0.065
uders+0.065
uding+0.064
Neg logit contributions
 coffee-0.036
 band-0.034
 puppet-0.031
 bath-0.030
 DVD-0.028
Token everyone
Token ID2506
Feature activation-8.03e-02

Pos logit contributions
 coffee+0.120
 band+0.114
 puppet+0.104
 bath+0.101
 DVD+0.094
Neg logit contributions
ust-0.248
ver-0.248
achable-0.244
uders-0.243
uding-0.239
Token was
Token ID373
Feature activation-2.41e-02

Pos logit contributions
ver+0.127
ust+0.127
uders+0.123
achable+0.122
uding+0.120
Neg logit contributions
 coffee-0.117
 band-0.114
 puppet-0.107
 bath-0.106
 DVD-0.101
Token afraid
Token ID7787
Feature activation-7.39e-02

Pos logit contributions
ust+0.037
ver+0.036
achable+0.035
uders+0.035
uding+0.035
Neg logit contributions
 coffee-0.036
 band-0.035
 puppet-0.034
 bath-0.033
 DVD-0.032
Token of
Token ID286
Feature activation+3.08e-02

Pos logit contributions
ust+0.149
ver+0.149
uders+0.145
achable+0.144
uding+0.142
Neg logit contributions
 coffee-0.074
 band-0.072
 puppet-0.066
 bath-0.063
 DVD-0.060
Token him
Token ID683
Feature activation-4.90e-02

Pos logit contributions
 coffee+0.033
 band+0.030
 bath+0.027
 puppet+0.027
 dish+0.024
Neg logit contributions
ver-0.066
ust-0.064
achable-0.062
uders-0.061
uding-0.060
Token.
Token ID13
Feature activation+6.59e-03

Pos logit contributions
ver+0.082
ust+0.082
achable+0.080
uders+0.080
uding+0.078
Neg logit contributions
 coffee-0.067
 band-0.065
 puppet-0.061
 bath-0.060
 DVD-0.056
Token
Token ID220
Feature activation-2.67e-02

Pos logit contributions
 coffee+0.006
 bath+0.005
 band+0.005
 puppet+0.005
 DVD+0.005
Neg logit contributions
ust-0.014
ver-0.014
uders-0.014
achable-0.014
uding-0.013
Token,
Token ID11
Feature activation-2.95e-02

Pos logit contributions
 coffee+0.014
 band+0.014
 puppet+0.013
 bath+0.013
 DVD+0.013
Neg logit contributions
ver-0.014
ust-0.013
uders-0.013
achable-0.013
uding-0.013
Token taking
Token ID2263
Feature activation+2.76e-02

Pos logit contributions
ver+0.045
ust+0.044
uders+0.044
 heights+0.043
achable+0.043
Neg logit contributions
 coffee-0.041
 band-0.040
 puppet-0.038
 bath-0.038
 DVD-0.038
Token turns
Token ID4962
Feature activation-9.29e-05

Pos logit contributions
 coffee+0.037
 band+0.035
 puppet+0.035
 bath+0.033
 DVD+0.033
Neg logit contributions
ust-0.044
ver-0.044
uders-0.043
 heights-0.043
achable-0.042
Token and
Token ID290
Feature activation+6.30e-03

Pos logit contributions
uders+0.000
ver+0.000
 heights+0.000
uding+0.000
ust+0.000
Neg logit contributions
 coffee-0.000
 band-0.000
 puppet-0.000
 DVD-0.000
 bath-0.000
Token having
Token ID1719
Feature activation+1.23e-02

Pos logit contributions
 coffee+0.009
 band+0.009
eddy+0.009
 puppet+0.009
 DVD+0.008
Neg logit contributions
 heights-0.009
uders-0.009
uding-0.009
achable-0.009
 ten-0.009
Token so
Token ID523
Feature activation-7.41e-03

Pos logit contributions
 coffee+0.020
 band+0.019
 puppet+0.018
eddy+0.018
 bath+0.018
Neg logit contributions
ust-0.017
 heights-0.017
ver-0.017
achable-0.016
uders-0.016
Token much
Token ID881
Feature activation-5.29e-02

Pos logit contributions
ver+0.010
ust+0.010
achable+0.009
uders+0.009
 steep+0.009
Neg logit contributions
 coffee-0.013
 band-0.012
 puppet-0.012
 bath-0.012
 kettle-0.011
Token fun
Token ID1257
Feature activation-1.19e-02

Pos logit contributions
ust+0.077
ver+0.076
achable+0.075
uders+0.074
 heights+0.073
Neg logit contributions
 coffee-0.082
 band-0.081
 puppet-0.077
 bath-0.074
 DVD-0.073
Token.
Token ID13
Feature activation+6.20e-03

Pos logit contributions
ust+0.017
uders+0.017
ver+0.017
 heights+0.017
uding+0.017
Neg logit contributions
 coffee-0.018
 band-0.018
 puppet-0.017
 bath-0.016
 DVD-0.016
Token
Token ID198
Feature activation-1.87e-02

Pos logit contributions
 coffee+0.005
 DVD+0.004
 bath+0.004
 video+0.004
 band+0.004
Neg logit contributions
ust-0.014
uders-0.014
 heights-0.014
ver-0.014
uding-0.014
Token
Token ID198
Feature activation-1.05e-02

Pos logit contributions
ust+0.038
ver+0.038
uders+0.038
achable+0.037
uding+0.037
Neg logit contributions
 coffee-0.019
 band-0.018
 puppet-0.016
 bath-0.016
 DVD-0.015
Token door
Token ID3420
Feature activation-1.03e-03

Pos logit contributions
 coffee+0.010
 band+0.010
 puppet+0.009
 bath+0.009
 DVD+0.008
Neg logit contributions
ver-0.021
ust-0.021
achable-0.021
uders-0.021
uding-0.020
Token and
Token ID290
Feature activation+1.69e-02

Pos logit contributions
ust+0.002
ver+0.002
uders+0.002
achable+0.002
uding+0.002
Neg logit contributions
 coffee-0.001
 band-0.001
 puppet-0.001
 bath-0.001
 DVD-0.001
Token see
Token ID766
Feature activation+2.88e-02

Pos logit contributions
 coffee+0.022
 band+0.022
 puppet+0.020
 bath+0.020
 DVD+0.019
Neg logit contributions
ust-0.029
ver-0.029
uders-0.029
achable-0.028
uding-0.028
Token what
Token ID644
Feature activation-2.01e-02

Pos logit contributions
 band+0.039
 coffee+0.039
 puppet+0.034
 bath+0.034
 kisses+0.032
Neg logit contributions
uders-0.051
ust-0.051
uding-0.049
achable-0.049
ver-0.048
Token was
Token ID373
Feature activation-6.88e-02

Pos logit contributions
ver+0.037
 anyone+0.035
ust+0.035
achable+0.033
 anybody+0.033
Neg logit contributions
 coffee-0.024
 band-0.022
 puppet-0.022
 bath-0.021
 DVD-0.021
Token inside
Token ID2641
Feature activation-4.73e-02

Pos logit contributions
ust+0.141
ver+0.139
uders+0.136
achable+0.136
uding+0.135
Neg logit contributions
 coffee-0.071
 band-0.069
 puppet-0.062
 bath-0.060
 DVD-0.056
Token,
Token ID11
Feature activation-2.30e-02

Pos logit contributions
ver+0.077
ust+0.076
achable+0.074
uders+0.074
uding+0.072
Neg logit contributions
 band-0.065
 coffee-0.065
 puppet-0.062
 bath-0.059
 DVD-0.058
Token but
Token ID475
Feature activation-4.80e-02

Pos logit contributions
ver+0.026
ust+0.026
achable+0.025
uders+0.025
uding+0.024
Neg logit contributions
 coffee-0.043
 band-0.043
 puppet-0.041
 bath-0.040
 DVD-0.039
Token it
Token ID340
Feature activation+2.03e-02

Pos logit contributions
ust+0.113
uders+0.111
uding+0.110
achable+0.108
ver+0.108
Neg logit contributions
 coffee-0.038
 band-0.036
 bath-0.029
 puppet-0.028
 sound-0.026
Token was
Token ID373
Feature activation-4.12e-02

Pos logit contributions
 coffee+0.019
 band+0.019
 puppet+0.017
 bath+0.016
 sound+0.015
Neg logit contributions
ust-0.043
ver-0.042
uders-0.042
achable-0.042
uding-0.042
Token stuck
Token ID7819
Feature activation-6.24e-02

Pos logit contributions
uders+0.087
uding+0.086
ants+0.085
ierce+0.084
ver+0.083
Neg logit contributions
 coffee-0.045
 band-0.044
 sound-0.040
 bath-0.040
 cup-0.039
Token and
Token ID290
Feature activation-1.11e-02

Pos logit contributions
 coffee+0.025
 band+0.024
 puppet+0.023
 bath+0.023
 DVD+0.022
Neg logit contributions
ver-0.029
ust-0.028
uders-0.027
achable-0.027
uding-0.027
Token said
Token ID531
Feature activation+4.80e-02

Pos logit contributions
ver+0.018
ust+0.017
 impossible+0.017
 rarely+0.016
 whether+0.016
Neg logit contributions
 coffee-0.016
 bath-0.015
 DVD-0.015
eddy-0.015
 CD-0.015
Token that
Token ID326
Feature activation+1.05e-01

Pos logit contributions
 coffee+0.072
 band+0.069
 puppet+0.066
 bath+0.066
 DVD+0.063
Neg logit contributions
ver-0.076
ust-0.073
achable-0.072
uders-0.070
uding-0.069
Token the
Token ID262
Feature activation-6.42e-04

Pos logit contributions
 coffee+0.131
 band+0.127
 puppet+0.118
 bath+0.116
 DVD+0.110
Neg logit contributions
ver-0.189
ust-0.188
achable-0.184
uders-0.183
uding-0.180
Token penny
Token ID26369
Feature activation-7.12e-02

Pos logit contributions
ver+0.001
ust+0.001
uders+0.001
achable+0.001
uding+0.001
Neg logit contributions
 coffee-0.001
 band-0.001
 puppet-0.001
 bath-0.001
 DVD-0.001
Token could
Token ID714
Feature activation-5.11e-02

Pos logit contributions
ver+0.129
ust+0.124
uders+0.119
achable+0.117
uding+0.116
Neg logit contributions
 coffee-0.093
 band-0.085
 bath-0.082
 puppet-0.079
 DVD-0.079
Token help
Token ID1037
Feature activation+1.19e-02

Pos logit contributions
ver+0.094
ust+0.094
uders+0.092
achable+0.092
uding+0.091
Neg logit contributions
 coffee-0.061
 band-0.059
 puppet-0.054
 bath-0.053
 DVD-0.050
Token the
Token ID262
Feature activation-2.77e-02

Pos logit contributions
 coffee+0.014
 band+0.014
 puppet+0.013
 bath+0.013
 DVD+0.012
Neg logit contributions
ver-0.022
ust-0.022
uders-0.021
achable-0.021
uding-0.021
Token ideas
Token ID4213
Feature activation-2.34e-02

Pos logit contributions
ust+0.046
ver+0.045
achable+0.045
uders+0.044
uding+0.044
Neg logit contributions
 coffee-0.039
 band-0.037
 puppet-0.035
 bath-0.034
 DVD-0.033
Token get
Token ID651
Feature activation-1.57e-02

Pos logit contributions
ver+0.040
ust+0.039
achable+0.038
uders+0.037
 impossible+0.037
Neg logit contributions
 coffee-0.032
 band-0.030
 puppet-0.029
 bath-0.028
 DVD-0.027
Token spread
Token ID4104
Feature activation+1.72e-02

Pos logit contributions
ver+0.029
ust+0.029
uders+0.028
achable+0.028
uding+0.028
Neg logit contributions
 coffee-0.019
 band-0.019
 bath-0.017
 puppet-0.017
 DVD-0.016
Token girl
Token ID2576
Feature activation+4.63e-02

Pos logit contributions
 coffee+0.029
cakes+0.026
 DVD+0.025
 refreshed+0.025
 puppet+0.024
Neg logit contributions
 heights-0.050
 impossible-0.050
 steep-0.050
ver-0.049
ust-0.049
Token saw
Token ID2497
Feature activation+1.11e-02

Pos logit contributions
 coffee+0.076
 band+0.072
 puppet+0.069
 DVD+0.069
 bath+0.067
Neg logit contributions
ver-0.063
uders-0.062
uding-0.060
ust-0.060
achable-0.059
Token the
Token ID262
Feature activation+1.35e-02

Pos logit contributions
 coffee+0.013
 band+0.013
 puppet+0.012
 bath+0.011
 DVD+0.011
Neg logit contributions
ver-0.021
achable-0.020
uders-0.020
ust-0.020
uding-0.020
Token mineral
Token ID18352
Feature activation-8.53e-02

Pos logit contributions
 coffee+0.019
 band+0.019
 bath+0.018
 puppet+0.017
 dish+0.017
Neg logit contributions
ver-0.024
uders-0.023
ust-0.023
uding-0.022
achable-0.022
Token and
Token ID290
Feature activation+2.32e-02

Pos logit contributions
ver+0.125
ust+0.124
 impossible+0.119
achable+0.119
 heights+0.118
Neg logit contributions
 coffee-0.127
 band-0.122
 DVD-0.116
eddy-0.116
 puppet-0.114
Token decided
Token ID3066
Feature activation-4.98e-02

Pos logit contributions
 coffee+0.038
 band+0.037
 puppet+0.035
 bath+0.034
 DVD+0.033
Neg logit contributions
ver-0.033
ust-0.033
achable-0.032
uders-0.032
uding-0.031
Token she
Token ID673
Feature activation-2.96e-02

Pos logit contributions
ver+0.094
ust+0.094
achable+0.092
uders+0.091
uding+0.090
Neg logit contributions
 coffee-0.057
 band-0.055
 puppet-0.051
 bath-0.050
 DVD-0.048
Token wanted
Token ID2227
Feature activation-4.12e-02

Pos logit contributions
ust+0.042
uders+0.042
ver+0.042
achable+0.042
 heights+0.041
Neg logit contributions
 band-0.047
 coffee-0.047
 puppet-0.044
 bath-0.043
 dish-0.041
Token to
Token ID284
Feature activation-4.40e-02

Pos logit contributions
ver+0.075
ust+0.074
achable+0.074
uders+0.073
 heights+0.072
Neg logit contributions
 coffee-0.048
 band-0.047
 puppet-0.045
 bath-0.043
 DVD-0.042
Token take
Token ID1011
Feature activation+3.55e-02

Pos logit contributions
ver+0.084
ust+0.083
achable+0.082
uders+0.082
uding+0.081
Neg logit contributions
 coffee-0.050
 band-0.048
 puppet-0.045
 bath-0.043
 DVD-0.042
Token it
Token ID340
Feature activation+2.62e-02

Pos logit contributions
 coffee+0.042
 puppet+0.040
 band+0.039
 DVD+0.038
 kettle+0.038
Neg logit contributions
 anyone-0.062
 heights-0.061
ver-0.061
 ten-0.060
achable-0.059
Token sky
Token ID6766
Feature activation-1.91e-03

Pos logit contributions
 coffee+0.001
 band+0.001
 puppet+0.001
 bath+0.001
 DVD+0.001
Neg logit contributions
ust-0.003
ver-0.003
achable-0.003
uders-0.003
uding-0.003
Token light
Token ID1657
Feature activation+1.24e-02

Pos logit contributions
 impossible+0.003
ust+0.003
 steep+0.003
 heights+0.003
ver+0.003
Neg logit contributions
 coffee-0.003
ugg-0.003
 DVD-0.003
Kids-0.003
 band-0.003
Token and
Token ID290
Feature activation+8.08e-03

Pos logit contributions
 coffee+0.020
 band+0.018
 puppet+0.018
ugg+0.018
 DVD+0.018
Neg logit contributions
ust-0.017
 impossible-0.017
 heights-0.017
 steep-0.016
 anyone-0.016
Token pretty
Token ID2495
Feature activation-1.26e-02

Pos logit contributions
 coffee+0.010
 band+0.010
 puppet+0.009
 bath+0.009
 DVD+0.009
Neg logit contributions
ver-0.014
achable-0.014
ust-0.014
uders-0.014
 heights-0.014
Token.
Token ID13
Feature activation-1.16e-02

Pos logit contributions
ust+0.019
 heights+0.019
achable+0.018
uders+0.018
ver+0.018
Neg logit contributions
 coffee-0.019
 band-0.018
 puppet-0.017
 bath-0.017
 DVD-0.017
Token All
Token ID1439
Feature activation-8.57e-02

Pos logit contributions
ust+0.023
ver+0.023
uders+0.023
achable+0.022
uding+0.022
Neg logit contributions
 coffee-0.013
 band-0.012
 bath-0.011
 puppet-0.011
 DVD-0.010
Token the
Token ID262
Feature activation+5.39e-03

Pos logit contributions
ver+0.142
ust+0.142
 anyone+0.139
 rarely+0.138
 impossible+0.137
Neg logit contributions
 coffee-0.116
 puppet-0.107
 band-0.106
 CD-0.102
 DVD-0.102
Token animals
Token ID4695
Feature activation-7.85e-02

Pos logit contributions
 band+0.006
 coffee+0.006
 sound+0.006
 bath+0.005
 puppet+0.005
Neg logit contributions
ver-0.011
ust-0.010
achable-0.010
uders-0.010
uding-0.010
Token and
Token ID290
Feature activation+1.21e-02

Pos logit contributions
ver+0.128
ust+0.126
achable+0.121
uders+0.121
uding+0.119
Neg logit contributions
 coffee-0.114
 band-0.107
 puppet-0.103
 bath-0.101
 DVD-0.098
Token plants
Token ID6134
Feature activation-8.23e-02

Pos logit contributions
 coffee+0.014
 band+0.014
 puppet+0.013
 bath+0.012
 sound+0.012
Neg logit contributions
ust-0.023
ver-0.023
achable-0.023
uders-0.022
uding-0.022
Token loved
Token ID6151
Feature activation-4.40e-02

Pos logit contributions
ver+0.130
ust+0.122
achable+0.119
uders+0.117
 heights+0.117
Neg logit contributions
 coffee-0.126
 band-0.115
 puppet-0.115
 DVD-0.113
eddy-0.109
Token to
Token ID284
Feature activation+1.26e-02

Pos logit contributions
ver+0.101
ust+0.100
achable+0.098
uders+0.098
uding+0.096
Neg logit contributions
 coffee-0.065
 band-0.062
 puppet-0.058
 bath-0.056
 DVD-0.055
Token see
Token ID766
Feature activation+4.26e-02

Pos logit contributions
 coffee+0.016
 band+0.014
 puppet+0.014
eddy+0.013
 bath+0.013
Neg logit contributions
ver-0.022
achable-0.022
ust-0.022
uding-0.021
 anyone-0.021
Token the
Token ID262
Feature activation+1.42e-02

Pos logit contributions
 coffee+0.061
 band+0.059
 puppet+0.056
 bath+0.055
 DVD+0.052
Neg logit contributions
ver-0.069
ust-0.068
achable-0.066
uders-0.066
uding-0.065
Token rock
Token ID3881
Feature activation-3.43e-02

Pos logit contributions
 band+0.018
 coffee+0.016
 bath+0.016
 sound+0.015
 puppet+0.015
Neg logit contributions
ver-0.028
uders-0.028
ust-0.027
uding-0.027
ierce-0.026
Token.
Token ID13
Feature activation+1.05e-02

Pos logit contributions
ver+0.049
ust+0.047
 impossible+0.045
achable+0.044
 steep+0.044
Neg logit contributions
 coffee-0.057
 band-0.053
 bath-0.052
 DVD-0.051
eddy-0.051
Token He
Token ID679
Feature activation-4.28e-02

Pos logit contributions
 coffee+0.017
 band+0.017
 puppet+0.016
 bath+0.015
eddy+0.015
Neg logit contributions
ver-0.013
achable-0.013
 impossible-0.013
 steep-0.013
 ten-0.012
Token said
Token ID531
Feature activation+6.34e-02

Pos logit contributions
ust+0.096
uders+0.093
 heights+0.091
uding+0.091
achable+0.091
Neg logit contributions
 band-0.047
 puppet-0.040
 coffee-0.036
 bath-0.032
 cup-0.032
Token,
Token ID11
Feature activation-3.30e-02

Pos logit contributions
 coffee+0.090
 band+0.089
 puppet+0.082
 bath+0.080
 dish+0.075
Neg logit contributions
ust-0.105
achable-0.103
uders-0.103
uding-0.101
ver-0.101
Token "
Token ID366
Feature activation-8.65e-02

Pos logit contributions
ust+0.056
ver+0.055
uders+0.054
achable+0.054
uding+0.053
Neg logit contributions
 coffee-0.045
 band-0.044
 puppet-0.041
 bath-0.040
 DVD-0.038
TokenWow
Token ID22017
Feature activation-4.07e-02

Pos logit contributions
ust+0.118
RR+0.113
achable+0.112
Near+0.111
uding+0.109
Neg logit contributions
 coffee-0.145
 puppet-0.133
 band-0.132
 bath-0.130
 dish-0.128
Token,
Token ID11
Feature activation-1.75e-02

Pos logit contributions
ust+0.064
achable+0.063
ver+0.063
uders+0.063
uding+0.062
Neg logit contributions
 coffee-0.060
 band-0.059
 puppet-0.055
 bath-0.055
 DVD-0.051
Token over
Token ID625
Feature activation-6.90e-02

Pos logit contributions
ust+0.068
ver+0.068
uders+0.066
uding+0.066
achable+0.066
Neg logit contributions
 coffee-0.058
 band-0.056
 puppet-0.052
 bath-0.051
 DVD-0.049
Token and
Token ID290
Feature activation+3.89e-02

Pos logit contributions
 ten+0.092
ver+0.092
 whether+0.091
uding+0.089
 heights+0.088
Neg logit contributions
 coffee-0.105
 band-0.104
 bath-0.099
 puppet-0.099
 DVD-0.098
Token said
Token ID531
Feature activation+6.31e-02

Pos logit contributions
 coffee+0.060
 bath+0.055
uggle+0.054
 band+0.052
eddy+0.052
Neg logit contributions
ver-0.060
ust-0.053
 whether-0.053
achable-0.053
 1-0.053
Token,
Token ID11
Feature activation-3.25e-02

Pos logit contributions
 coffee+0.098
 band+0.097
 puppet+0.092
 bath+0.091
 DVD+0.088
Neg logit contributions
ver-0.094
ust-0.089
achable-0.087
uders-0.086
uding-0.084
Token "
Token ID366
Feature activation-8.92e-02

Pos logit contributions
ver+0.045
achable+0.044
ust+0.043
uding+0.042
uders+0.041
Neg logit contributions
 coffee-0.053
 band-0.052
 bath-0.049
 puppet-0.049
 DVD-0.047
TokenExc
Token ID40127
Feature activation-1.64e-01

Pos logit contributions
ust+0.142
ver+0.132
achable+0.126
Near+0.126
uding+0.126
Neg logit contributions
 coffee-0.135
 band-0.129
 puppet-0.128
 bath-0.126
 DVD-0.124
Tokenuse
Token ID1904
Feature activation-4.43e-02

Pos logit contributions
ver+0.119
ust+0.114
 heights+0.108
achable+0.107
uding+0.104
Neg logit contributions
 coffee-0.376
 band-0.361
 puppet-0.358
 bath-0.353
 DVD-0.348
Token me
Token ID502
Feature activation-6.70e-02

Pos logit contributions
ver+0.079
ust+0.077
achable+0.076
uders+0.075
uding+0.074
Neg logit contributions
 coffee-0.060
 band-0.057
 puppet-0.052
 bath-0.051
 cup-0.048
Token,
Token ID11
Feature activation-1.37e-02

Pos logit contributions
ust+0.104
ver+0.102
uders+0.102
achable+0.102
uding+0.100
Neg logit contributions
 coffee-0.101
 band-0.097
 puppet-0.092
 bath-0.090
 DVD-0.086
Token the
Token ID262
Feature activation+2.28e-02

Pos logit contributions
ver+0.019
ust+0.018
achable+0.017
uders+0.017
 impossible+0.017
Neg logit contributions
 band-0.023
 coffee-0.022
 puppet-0.021
 bath-0.021
 DVD-0.021
Token item
Token ID2378
Feature activation-2.42e-02

Pos logit contributions
 coffee+0.024
 band+0.023
 puppet+0.022
 bath+0.020
 DVD+0.020
Neg logit contributions
ust-0.044
ver-0.044
uders-0.043
achable-0.043
uding-0.043
Token happy
Token ID3772
Feature activation+5.29e-02

Pos logit contributions
 coffee+0.007
 band+0.006
 puppet+0.006
 bath+0.006
 video+0.006
Neg logit contributions
ver-0.007
ust-0.007
achable-0.007
 impossible-0.007
 steep-0.007
Token to
Token ID284
Feature activation-3.68e-02

Pos logit contributions
 coffee+0.062
 band+0.061
 puppet+0.056
 bath+0.055
 DVD+0.053
Neg logit contributions
ver-0.098
ust-0.097
uders-0.095
achable-0.095
uding-0.094
Token find
Token ID1064
Feature activation+1.61e-02

Pos logit contributions
ver+0.064
ust+0.063
achable+0.062
uders+0.062
uding+0.061
Neg logit contributions
 coffee-0.049
 band-0.045
 puppet-0.044
 DVD-0.041
 bath-0.041
Token you
Token ID345
Feature activation-1.67e-02

Pos logit contributions
 coffee+0.021
 band+0.020
 puppet+0.019
 bath+0.019
 DVD+0.018
Neg logit contributions
ver-0.028
ust-0.028
achable-0.027
uders-0.027
uding-0.027
Token,
Token ID11
Feature activation-2.96e-02

Pos logit contributions
ust+0.026
ver+0.025
uders+0.025
achable+0.025
uding+0.025
Neg logit contributions
 coffee-0.025
 band-0.025
 puppet-0.023
 bath-0.023
 DVD-0.022
Token Twe
Token ID24205
Feature activation-2.15e-01

Pos logit contributions
ver+0.048
ust+0.047
uders+0.047
achable+0.047
uding+0.046
Neg logit contributions
 coffee-0.043
 band-0.042
 puppet-0.039
 bath-0.039
 DVD-0.036
Tokenety
Token ID2963
Feature activation-1.17e-01

Pos logit contributions
achable+0.227
uders+0.227
 heights+0.221
ver+0.220
 impossible+0.214
Neg logit contributions
 band-0.427
eddy-0.417
 coffee-0.400
 puppet-0.385
 bath-0.383
Token!
Token ID0
Feature activation-7.01e-03

Pos logit contributions
ver+0.171
ust+0.170
uders+0.163
achable+0.162
uding+0.160
Neg logit contributions
 coffee-0.186
 band-0.179
 puppet-0.167
 bath-0.167
 DVD-0.160
Token Let
Token ID3914
Feature activation+3.95e-02

Pos logit contributions
ver+0.013
ust+0.013
achable+0.012
uders+0.012
uding+0.012
Neg logit contributions
 coffee-0.009
 band-0.008
 puppet-0.008
 bath-0.008
 DVD-0.007
Token's
Token ID338
Feature activation+1.73e-02

Pos logit contributions
 coffee+0.040
 puppet+0.037
 band+0.037
 DVD+0.034
 bath+0.033
Neg logit contributions
ust-0.079
ver-0.078
uders-0.076
achable-0.075
uding-0.075
Token go
Token ID467
Feature activation+2.73e-02

Pos logit contributions
 coffee+0.017
 band+0.017
 bath+0.015
 puppet+0.015
 DVD+0.014
Neg logit contributions
ver-0.035
ust-0.035
uders-0.034
achable-0.034
uding-0.034
Token,
Token ID11
Feature activation-8.80e-03

Pos logit contributions
ver+0.032
ust+0.032
uders+0.032
achable+0.032
uding+0.031
Neg logit contributions
 coffee-0.017
 band-0.017
 puppet-0.015
 bath-0.015
 DVD-0.014
Token modest
Token ID12949
Feature activation+2.62e-02

Pos logit contributions
ust+0.014
ver+0.014
achable+0.013
uders+0.013
 steep+0.013
Neg logit contributions
 coffee-0.013
 band-0.012
 puppet-0.012
 bath-0.011
 DVD-0.011
Token barn
Token ID25203
Feature activation+6.37e-03

Pos logit contributions
 coffee+0.032
 band+0.031
 puppet+0.028
 bath+0.028
 DVD+0.026
Neg logit contributions
ver-0.049
ust-0.048
achable-0.047
uders-0.047
uding-0.046
Token.
Token ID13
Feature activation-2.95e-03

Pos logit contributions
 coffee+0.010
 band+0.010
 bath+0.009
 puppet+0.009
 refreshed+0.009
Neg logit contributions
ver-0.009
uders-0.008
achable-0.008
uding-0.008
ust-0.008
Token Two
Token ID4930
Feature activation-3.90e-02

Pos logit contributions
ust+0.006
ver+0.006
uders+0.005
uding+0.005
achable+0.005
Neg logit contributions
 coffee-0.004
 band-0.003
 bath-0.003
 puppet-0.003
 DVD-0.003
Token mis
Token ID2984
Feature activation-1.63e-01

Pos logit contributions
ver+0.069
achable+0.069
ust+0.068
uding+0.067
uders+0.067
Neg logit contributions
 coffee-0.051
 band-0.051
 puppet-0.046
 bath-0.045
 dish-0.043
Tokenchie
Token ID3043
Feature activation-1.46e-01

Pos logit contributions
ver+0.151
achable+0.151
uders+0.145
ust+0.145
uding+0.137
Neg logit contributions
 band-0.340
 coffee-0.334
 puppet-0.318
 bath-0.314
eddy-0.304
Tokenvous
Token ID31222
Feature activation-1.21e-02

Pos logit contributions
ver+0.195
ust+0.194
achable+0.187
uders+0.187
uding+0.182
Neg logit contributions
 coffee-0.250
 band-0.244
 puppet-0.231
 bath-0.229
 DVD-0.219
Token kittens
Token ID45584
Feature activation-8.02e-02

Pos logit contributions
ver+0.021
ust+0.021
achable+0.021
uding+0.020
uders+0.019
Neg logit contributions
 coffee-0.017
 band-0.017
 puppet-0.016
 bath-0.015
 dish-0.015
Token lived
Token ID5615
Feature activation-4.06e-02

Pos logit contributions
ust+0.148
achable+0.143
ver+0.141
 heights+0.140
uders+0.140
Neg logit contributions
 band-0.099
 coffee-0.098
 bath-0.092
 puppet-0.091
 dish-0.088
Token in
Token ID287
Feature activation-7.48e-02

Pos logit contributions
ust+0.074
ver+0.074
achable+0.073
uders+0.073
 heights+0.071
Neg logit contributions
 coffee-0.049
 band-0.049
 puppet-0.045
 bath-0.044
 DVD-0.041
Token
Token ID198
Feature activation-1.76e-02

Pos logit contributions
 coffee+0.017
 band+0.016
 puppet+0.015
 bath+0.015
 DVD+0.014
Neg logit contributions
ver-0.028
ust-0.027
achable-0.027
uders-0.027
uding-0.026
Token
Token ID198
Feature activation-1.02e-02

Pos logit contributions
ver+0.033
ust+0.033
achable+0.032
uders+0.032
uding+0.032
Neg logit contributions
 coffee-0.021
 band-0.020
 puppet-0.018
 bath-0.018
 DVD-0.017
TokenThe
Token ID464
Feature activation+1.56e-02

Pos logit contributions
ver+0.017
ust+0.017
uders+0.016
achable+0.016
uding+0.016
Neg logit contributions
 coffee-0.014
 band-0.014
 puppet-0.013
 bath-0.013
 DVD-0.012
Token animals
Token ID4695
Feature activation-5.41e-02

Pos logit contributions
 coffee+0.025
 band+0.025
 puppet+0.023
 bath+0.023
 DVD+0.022
Neg logit contributions
ver-0.023
ust-0.022
achable-0.022
uders-0.022
uding-0.021
Token sc
Token ID629
Feature activation-7.26e-02

Pos logit contributions
ver+0.087
ust+0.083
uders+0.080
achable+0.080
uding+0.079
Neg logit contributions
 coffee-0.083
 band-0.074
 puppet-0.073
 bath-0.072
 DVD-0.072
Tokenur
Token ID333
Feature activation-1.83e-01

Pos logit contributions
ver+0.103
ust+0.100
uders+0.093
ierce+0.092
achable+0.092
Neg logit contributions
 coffee-0.127
 band-0.118
 bath-0.115
 puppet-0.115
 DVD-0.111
Tokenried
Token ID2228
Feature activation-9.21e-02

Pos logit contributions
ust+0.149
ver+0.149
achable+0.145
uders+0.141
uding+0.135
Neg logit contributions
 band-0.403
 coffee-0.402
 puppet-0.385
 bath-0.375
 DVD-0.363
Token off
Token ID572
Feature activation+1.48e-04

Pos logit contributions
ver+0.142
 halfway+0.138
 ten+0.138
 impossible+0.138
 heights+0.137
Neg logit contributions
 coffee-0.128
 band-0.121
 puppet-0.117
eddy-0.117
 DVD-0.116
Token,
Token ID11
Feature activation-1.09e-02

Pos logit contributions
 coffee+0.000
 band+0.000
 puppet+0.000
 bath+0.000
 DVD+0.000
Neg logit contributions
ver-0.000
ust-0.000
uders-0.000
achable-0.000
uding-0.000
Token leaving
Token ID4305
Feature activation+5.49e-02

Pos logit contributions
ver+0.015
ust+0.015
achable+0.015
uders+0.014
uding+0.014
Neg logit contributions
 coffee-0.018
 band-0.017
 puppet-0.016
 bath-0.016
eddy-0.016
Token the
Token ID262
Feature activation+3.67e-02

Pos logit contributions
 coffee+0.042
 band+0.042
 bath+0.035
 puppet+0.034
 sound+0.033
Neg logit contributions
ust-0.133
achable-0.127
ver-0.125
uders-0.123
uding-0.121
Token his
Token ID465
Feature activation-2.07e-02

Pos logit contributions
uders+0.065
ust+0.065
achable+0.063
ver+0.061
uding+0.061
Neg logit contributions
 coffee-0.054
 band-0.054
 puppet-0.048
 bath-0.048
 dish-0.046
Token neighbor
Token ID4780
Feature activation-2.47e-02

Pos logit contributions
ust+0.042
ver+0.041
uders+0.041
achable+0.040
uding+0.040
Neg logit contributions
 coffee-0.024
 band-0.024
 puppet-0.022
 bath-0.021
 dish-0.020
Token if
Token ID611
Feature activation-7.98e-03

Pos logit contributions
uders+0.036
ust+0.036
achable+0.035
uding+0.034
RR+0.033
Neg logit contributions
 coffee-0.041
 band-0.039
 puppet-0.037
 bath-0.037
 dish-0.035
Token he
Token ID339
Feature activation-4.42e-02

Pos logit contributions
ver+0.017
ust+0.016
uders+0.016
achable+0.016
uding+0.016
Neg logit contributions
 coffee-0.008
 band-0.007
 puppet-0.007
 bath-0.007
 DVD-0.006
Token knew
Token ID2993
Feature activation-3.72e-02

Pos logit contributions
 heights+0.090
uders+0.088
achable+0.087
uding+0.086
 perspective+0.082
Neg logit contributions
 band-0.049
 puppet-0.046
washer-0.043
 coffee-0.043
 dish-0.040
Token anyone
Token ID2687
Feature activation-2.33e-01

Pos logit contributions
uders+0.069
ust+0.068
achable+0.067
uding+0.067
RR+0.066
Neg logit contributions
 coffee-0.046
 band-0.044
 bath-0.040
 puppet-0.039
 dish-0.037
Token who
Token ID508
Feature activation-3.69e-02

Pos logit contributions
ver+0.401
ust+0.400
achable+0.391
uders+0.390
uding+0.383
Neg logit contributions
 coffee-0.308
 band-0.299
 puppet-0.279
 bath-0.273
 DVD-0.260
Token could
Token ID714
Feature activation-6.04e-02

Pos logit contributions
ust+0.060
achable+0.060
uders+0.059
ver+0.059
uding+0.058
Neg logit contributions
 coffee-0.052
 band-0.052
 puppet-0.048
 bath-0.047
 DVD-0.045
Token fix
Token ID4259
Feature activation-1.67e-02

Pos logit contributions
ust+0.117
ver+0.117
uders+0.115
achable+0.114
uding+0.112
Neg logit contributions
 coffee-0.067
 band-0.065
 puppet-0.059
 bath-0.058
 DVD-0.054
Token the
Token ID262
Feature activation-6.32e-03

Pos logit contributions
ust+0.033
ver+0.033
achable+0.033
uders+0.032
uding+0.032
Neg logit contributions
 coffee-0.018
 band-0.017
 puppet-0.016
 bath-0.015
 DVD-0.014
Token TV
Token ID3195
Feature activation-1.45e-02

Pos logit contributions
ver+0.011
ust+0.011
uders+0.011
achable+0.011
uding+0.011
Neg logit contributions
 coffee-0.008
 band-0.008
 puppet-0.007
 bath-0.007
 DVD-0.006