TOP ACTIVATIONS
MAX = 8.249

sorts of adventures in the vast ocean . She was happy
am further out into the deep ocean . Sure enough ,
. She looked around the vast ocean and didn 't see
colourful flowers , through the lush forests deep in thought .
many dangers lurking in the deep blue sea . But he
a lot safer in the dark ". The boy nodded ,
the sun rises in the opposite direction ". Jack thought this
, through the lush forests deep in thought . He admired
drove the plane through the deep blue sky until it was
It will glow in the dark and scare away the bad
good to roll in the lush green grass and jump high
repl anted deeper into the dark forest . <|endoftext|> M olly
He soared through the dark night ! He felt happy
lay it down in the deep , green grass .
water and disappeared into the deep blue sea . <|endoftext|> M
big creatures lurking in the deep dark waters .
She loved swimming in the deep , blue sea . Everywhere
was all alone in the deep , dark blue water .
. He lived in the deep , blue sea . He
forest and fallen into the deep hole . They were heart

MIN ACTIVATIONS
MIN = -7.426

and decided to give the hat to Sarah as a gift
are sorry and give the hat back to the bald man
They gave the hat back to Mama Bird and
, but reluctantly gave the hat back to the man .
laughs . She gives the hat back to Sam . "
. She gives him the cap . Tom takes
felt ashamed and gave the doll back . When
the swing and gave his doll a big hug . He
nods . She gives the hat to Ben . He puts
She gave the scarf to Tom the next day
asked Tom to give her lamp back . Tom
and he quickly handed the bracelet back to the woman .
down and gave Lily the necklace . She put it around
, so she gave the chain back to the boy .
Tom nods and gives the stone to Sue . Sue holds
Tim my gave the hat back and apologized again .
ara smiles and gives the snail to Ben . Ben holds
felt bad and gave the jewel back to his friend .
Ben and Lily and gives them a kiss . Then they
ever after ." They gave them some cake and juice and

INTERVAL 4.330 - 8.249
CONTAINS 0.074%

work shot up high in the sky . They burst open
that everyone should sleep at night . Every night people all
saw a jet in the deep sky . The little boy
got them from flying in the sky and collecting things along
I will not touch it again ." The mouse

INTERVAL 0.411 - 4.330
CONTAINS 39.207%

was there to keep her safe and happy .
This made the kids sad . They did not know what
€ The animals laughed at her . They all
and shades of colors . She liked it . She smiled
heard the birds singing again . She took a deep breath

INTERVAL -3.507 - 0.411
CONTAINS 59.938%

under the oak tree and talk . One day
held the wrap all the way home , not wanting to
ball . Do you want to play with me ?"
high , and Joey reached out to grab the bird .
sw am and sw am until she saw a cute oct

INTERVAL -7.426 - -3.507
CONTAINS 0.781%

she could use the small box . He said yes .
worked hard and used many blocks to make the walls ,
The girl and her friends looked at the sky
home , Aunt ie gave Lily a big hug and said
day , he found a piece of rope on the ground
Token sorts
Token ID10524
Feature activation+3.25e-01

Pos logit contributions
ggy+0.000
 yes+0.000
 doll+0.000
ggie+0.000
ver+0.000
Neg logit contributions
 habitat-0.000
 exp-0.000
 horizon-0.000
 glory-0.000
 sav-0.000
Token of
Token ID286
Feature activation+7.85e-01

Pos logit contributions
 habitat+0.011
 exp+0.010
 sav+0.010
 horizon+0.010
 oceans+0.010
Neg logit contributions
 yes-0.005
ggy-0.005
ver-0.004
ggie-0.004
 doll-0.004
Token adventures
Token ID17545
Feature activation+9.44e-01

Pos logit contributions
 habitat+0.021
 exp+0.019
 horizon+0.019
ky+0.018
 sav+0.018
Neg logit contributions
ggy-0.016
 yes-0.016
ggie-0.015
ver-0.014
 doll-0.014
Token in
Token ID287
Feature activation+2.13e+00

Pos logit contributions
 habitat+0.022
 exp+0.019
 oceans+0.019
 glory+0.019
 horizon+0.019
Neg logit contributions
 yes-0.022
ggy-0.022
ver-0.021
ggie-0.021
 doll-0.020
Token the
Token ID262
Feature activation+3.76e+00

Pos logit contributions
 habitat+0.058
 exp+0.052
 glory+0.051
 horizon+0.051
 oceans+0.051
Neg logit contributions
 yes-0.043
ggy-0.042
ggie-0.039
ver-0.039
 doll-0.037
Token vast
Token ID5909
Feature activation+8.25e+00

Pos logit contributions
 habitat+0.082
 habitats+0.072
 ago+0.069
iling+0.068
 glory+0.066
Neg logit contributions
 yes-0.090
 mom-0.086
 doll-0.085
 okay-0.084
ggy-0.083
Token ocean
Token ID9151
Feature activation+1.92e+00

Pos logit contributions
pill+0.179
iw+0.168
ips+0.167
oky+0.160
Fighting+0.160
Neg logit contributions
 friend-0.171
 mom-0.167
 shield-0.157
 doll-0.155
 little-0.146
Token.
Token ID13
Feature activation+1.39e+00

Pos logit contributions
 habitat+0.049
 exp+0.045
 horizon+0.043
 glory+0.043
 habitats+0.043
Neg logit contributions
 yes-0.041
ggy-0.041
ggie-0.037
ver-0.037
 doll-0.036
Token She
Token ID1375
Feature activation+1.94e+00

Pos logit contributions
 habitat+0.031
 glory+0.027
 oceans+0.027
 exp+0.027
ky+0.027
Neg logit contributions
 yes-0.034
ver-0.032
ggy-0.032
 doll-0.031
ggie-0.031
Token was
Token ID373
Feature activation+1.54e+00

Pos logit contributions
 habitat+0.058
 exp+0.052
 horizon+0.052
 glory+0.052
 oceans+0.051
Neg logit contributions
 yes-0.035
ggy-0.034
ver-0.032
ggie-0.031
 doll-0.029
Token happy
Token ID3772
Feature activation+2.09e+00

Pos logit contributions
 habitat+0.041
 exp+0.037
 oceans+0.036
 sav+0.036
 glory+0.036
Neg logit contributions
 yes-0.031
ggy-0.031
ver-0.029
ggie-0.029
 doll-0.027
Tokenam
Token ID321
Feature activation+4.36e-01

Pos logit contributions
 habitat+0.025
 exp+0.022
 horizon+0.022
 oceans+0.022
 glory+0.022
Neg logit contributions
ggy-0.028
 yes-0.027
ggie-0.026
ver-0.026
 doll-0.024
Token further
Token ID2252
Feature activation+3.19e+00

Pos logit contributions
 habitat+0.012
 exp+0.011
 glory+0.010
 habitats+0.010
 oceans+0.010
Neg logit contributions
 yes-0.009
ggy-0.009
ggie-0.008
ver-0.008
 doll-0.008
Token out
Token ID503
Feature activation+2.62e+00

Pos logit contributions
 habitat+0.090
 exp+0.082
 Now+0.081
 habitats+0.081
 horizon+0.078
Neg logit contributions
 yes-0.054
ggy-0.050
 doll-0.048
ver-0.047
 else-0.046
Token into
Token ID656
Feature activation+2.71e+00

Pos logit contributions
 habitat+0.077
 habitats+0.069
 exp+0.068
 glory+0.067
 sav+0.066
Neg logit contributions
 yes-0.049
ggy-0.044
ver-0.043
 doll-0.040
 else-0.040
Token the
Token ID262
Feature activation+5.10e+00

Pos logit contributions
 habitat+0.089
 habitats+0.081
 exp+0.078
 glory+0.077
 horizon+0.077
Neg logit contributions
 yes-0.038
ggy-0.037
 mom-0.036
 doll-0.035
 else-0.033
Token deep
Token ID2769
Feature activation+7.75e+00

Pos logit contributions
 habitat+0.107
 habitats+0.098
 ago+0.093
iling+0.093
 than+0.091
Neg logit contributions
 mom-0.113
 doll-0.112
ggy-0.112
 yes-0.111
 friend-0.109
Token ocean
Token ID9151
Feature activation+2.63e+00

Pos logit contributions
 habitats+0.167
 habitat+0.164
 sch+0.152
 MacDonald+0.151
ips+0.150
Neg logit contributions
 friend-0.140
 mom-0.132
 shield-0.131
 doll-0.129
 magnet-0.127
Token.
Token ID13
Feature activation+1.30e+00

Pos logit contributions
 habitat+0.074
 habitats+0.070
 exp+0.067
 glory+0.065
ky+0.064
Neg logit contributions
 yes-0.049
ggy-0.046
ggie-0.041
ver-0.041
 doll-0.040
Token Sure
Token ID10889
Feature activation+7.21e-01

Pos logit contributions
 habitat+0.031
 glory+0.028
 oceans+0.028
ky+0.027
 exp+0.027
Neg logit contributions
 yes-0.030
ver-0.029
ggy-0.028
ggie-0.026
 okay-0.026
Token enough
Token ID1576
Feature activation+5.80e-01

Pos logit contributions
 habitat+0.019
 horizon+0.018
 exp+0.017
 oceans+0.017
 habitats+0.017
Neg logit contributions
 yes-0.016
ggy-0.015
ggie-0.014
ver-0.014
 doll-0.013
Token,
Token ID11
Feature activation-5.06e-01

Pos logit contributions
 habitat+0.018
 habitats+0.016
 exp+0.016
ky+0.016
 horizon+0.016
Neg logit contributions
 yes-0.011
ggy-0.010
ver-0.010
ggie-0.009
 okay-0.009
Token.
Token ID13
Feature activation+6.61e-01

Pos logit contributions
 habitat+0.056
 exp+0.052
 horizon+0.050
 glory+0.050
 habitats+0.050
Neg logit contributions
 yes-0.039
ggy-0.037
ver-0.035
ggie-0.034
 doll-0.033
Token She
Token ID1375
Feature activation+8.18e-01

Pos logit contributions
 habitat+0.015
 glory+0.013
 exp+0.013
 oceans+0.013
 horizon+0.013
Neg logit contributions
 yes-0.016
ggy-0.016
ver-0.016
ggie-0.015
 doll-0.015
Token looked
Token ID3114
Feature activation+1.18e+00

Pos logit contributions
 habitat+0.022
 exp+0.020
 oceans+0.019
 glory+0.019
 sav+0.019
Neg logit contributions
 yes-0.017
ggy-0.017
ver-0.016
ggie-0.016
 doll-0.015
Token around
Token ID1088
Feature activation+3.08e+00

Pos logit contributions
 habitat+0.033
 exp+0.029
 glory+0.029
 oceans+0.029
 horizon+0.029
Neg logit contributions
 yes-0.024
ggy-0.023
ver-0.022
ggie-0.021
 doll-0.020
Token the
Token ID262
Feature activation+3.66e+00

Pos logit contributions
 habitat+0.083
 habitats+0.072
 exp+0.071
 glory+0.071
 sav+0.069
Neg logit contributions
 yes-0.070
 mom-0.059
 doll-0.057
 okay-0.056
ver-0.056
Token vast
Token ID5909
Feature activation+7.59e+00

Pos logit contributions
 habitat+0.060
iling+0.052
 habitats+0.050
rs+0.048
 glory+0.048
Neg logit contributions
 mom-0.103
 doll-0.099
 yes-0.098
 friend-0.095
 else-0.094
Token ocean
Token ID9151
Feature activation+2.79e+00

Pos logit contributions
 Now+0.136
ips+0.135
iling+0.130
brance+0.129
Now+0.128
Neg logit contributions
 mom-0.171
 friend-0.169
 doll-0.156
 shield-0.153
 necklace-0.145
Token and
Token ID290
Feature activation+2.22e+00

Pos logit contributions
 habitat+0.069
 exp+0.062
 habitats+0.061
 glory+0.059
 sav+0.057
Neg logit contributions
 yes-0.065
ggy-0.060
ver-0.057
ggie-0.056
 doll-0.056
Token didn
Token ID1422
Feature activation-1.89e+00

Pos logit contributions
 habitat+0.061
 exp+0.054
 glory+0.053
 habitats+0.052
 horizon+0.052
Neg logit contributions
 yes-0.045
ggy-0.042
ver-0.040
ggie-0.039
 doll-0.038
Token't
Token ID470
Feature activation-1.00e+00

Pos logit contributions
 yes+0.034
 doll+0.031
ggy+0.031
ggie+0.030
cher+0.029
Neg logit contributions
 habitat-0.050
 horizon-0.048
 exp-0.047
acks-0.046
 sav-0.045
Token see
Token ID766
Feature activation+7.11e-01

Pos logit contributions
 yes+0.022
ggy+0.022
ver+0.021
ggie+0.021
 doll+0.019
Neg logit contributions
 habitat-0.025
 exp-0.023
 oceans-0.022
 sav-0.022
 horizon-0.022
Token colourful
Token ID44799
Feature activation+1.29e+00

Pos logit contributions
 habitat+0.015
 exp+0.014
ky+0.013
 horizon+0.013
 glory+0.013
Neg logit contributions
 yes-0.014
ggy-0.013
 doll-0.012
ggie-0.012
ver-0.012
Token flowers
Token ID12734
Feature activation-6.67e-01

Pos logit contributions
 habitat+0.032
 horizon+0.029
iling+0.027
 sav+0.027
ky+0.027
Neg logit contributions
 yes-0.028
 doll-0.026
ggy-0.025
 mom-0.023
 friend-0.023
Token,
Token ID11
Feature activation+1.88e+00

Pos logit contributions
 yes+0.016
ggy+0.015
ver+0.014
ggie+0.014
 doll+0.014
Neg logit contributions
 habitat-0.016
 exp-0.014
 glory-0.014
 habitats-0.014
 sav-0.014
Token through
Token ID832
Feature activation+3.65e+00

Pos logit contributions
 habitat+0.043
 glory+0.037
 exp+0.037
 horizon+0.036
 habitats+0.036
Neg logit contributions
 yes-0.048
ggy-0.042
 doll-0.041
ver-0.040
ggie-0.040
Token the
Token ID262
Feature activation+3.77e+00

Pos logit contributions
 habitat+0.099
 exp+0.089
 glory+0.087
ky+0.086
acks+0.086
Neg logit contributions
 yes-0.071
ggy-0.064
 doll-0.063
 mom-0.061
ver-0.059
Token lush
Token ID37408
Feature activation+7.50e+00

Pos logit contributions
 habitat+0.081
iling+0.074
elly+0.071
 Now+0.071
az+0.070
Neg logit contributions
 doll-0.079
 crown-0.077
 mom-0.076
 yes-0.075
 friend-0.073
Token forests
Token ID17039
Feature activation+1.99e+00

Pos logit contributions
 habitat+0.179
Fighting+0.167
oky+0.166
iling+0.165
ulk+0.163
Neg logit contributions
 doll-0.121
 crown-0.120
 mom-0.111
 shield-0.107
 friend-0.105
Token deep
Token ID2769
Feature activation+7.08e+00

Pos logit contributions
 habitat+0.049
 exp+0.044
 habitats+0.042
 glory+0.042
 sav+0.041
Neg logit contributions
 yes-0.046
ggy-0.044
ver-0.043
ggie-0.041
 doll-0.040
Token in
Token ID287
Feature activation+4.61e+00

Pos logit contributions
Fighting+0.141
 habitat+0.137
 sch+0.136
istence+0.132
 venue+0.132
Neg logit contributions
 in-0.126
 out-0.126
 crown-0.123
 on-0.122
 doll-0.121
Token thought
Token ID1807
Feature activation+8.83e-02

Pos logit contributions
 habitat+0.161
 habitats+0.145
iling+0.144
icol+0.141
elly+0.139
Neg logit contributions
 mom-0.050
 doll-0.048
 yes-0.047
 nobody-0.040
 else-0.035
Token.
Token ID13
Feature activation+1.51e+00

Pos logit contributions
 habitat+0.002
 oceans+0.002
 exp+0.002
 glory+0.002
 horizon+0.002
Neg logit contributions
ggy-0.002
 yes-0.002
ver-0.002
ggie-0.002
 doll-0.002
Token many
Token ID867
Feature activation+1.94e+00

Pos logit contributions
 habitat+0.018
 oceans+0.016
 glory+0.016
 exp+0.016
 sav+0.015
Neg logit contributions
 yes-0.011
ggy-0.011
ver-0.010
ggie-0.010
 doll-0.010
Token dangers
Token ID16169
Feature activation+2.62e+00

Pos logit contributions
 habitat+0.056
 horizon+0.051
 exp+0.050
 sav+0.049
ky+0.048
Neg logit contributions
 yes-0.035
ggy-0.034
 else-0.034
 doll-0.031
ggie-0.030
Token lurking
Token ID36105
Feature activation+3.83e+00

Pos logit contributions
 habitat+0.081
 exp+0.074
 glory+0.073
 sav+0.072
 horizon+0.071
Neg logit contributions
 yes-0.044
ggy-0.042
ver-0.041
 else-0.040
ggie-0.038
Token in
Token ID287
Feature activation+3.04e+00

Pos logit contributions
 habitat+0.120
 glory+0.111
 exp+0.110
 horizon+0.109
 sav+0.108
Neg logit contributions
 yes-0.058
ggy-0.056
ver-0.053
ggie-0.051
 else-0.048
Token the
Token ID262
Feature activation+4.43e+00

Pos logit contributions
 habitat+0.093
 exp+0.086
 habitats+0.084
ky+0.083
 glory+0.083
Neg logit contributions
 yes-0.047
ggy-0.044
 mom-0.044
 doll-0.041
 nobody-0.040
Token deep
Token ID2769
Feature activation+7.42e+00

Pos logit contributions
 habitat+0.087
rs+0.084
 habitats+0.082
iling+0.078
 ago+0.077
Neg logit contributions
 mom-0.103
 else-0.094
 worse-0.089
 friend-0.089
 doll-0.089
Token blue
Token ID4171
Feature activation+5.14e+00

Pos logit contributions
pill+0.155
brance+0.152
istence+0.146
Fighting+0.142
Now+0.141
Neg logit contributions
 mom-0.134
 friend-0.133
 bear-0.129
 sword-0.122
ie-0.122
Token sea
Token ID5417
Feature activation+3.28e+00

Pos logit contributions
 habitats+0.097
iling+0.096
 sav+0.094
 habitat+0.094
icol+0.090
Neg logit contributions
 friend-0.117
 mom-0.108
 hammer-0.100
 doll-0.099
on-0.098
Token.
Token ID13
Feature activation+1.08e+00

Pos logit contributions
 habitat+0.086
 exp+0.078
 glory+0.076
 sav+0.076
 habitats+0.076
Neg logit contributions
 yes-0.066
ggy-0.061
ver-0.059
 else-0.058
 doll-0.057
Token But
Token ID887
Feature activation-2.02e-01

Pos logit contributions
ky+0.028
 habitat+0.027
 oceans+0.026
 horizon+0.026
 glory+0.026
Neg logit contributions
 yes-0.021
ver-0.020
 mom-0.020
 okay-0.019
ggy-0.019
Token he
Token ID339
Feature activation+8.46e-01

Pos logit contributions
 yes+0.003
ggy+0.003
ver+0.003
ggie+0.003
 doll+0.003
Neg logit contributions
 habitat-0.006
 exp-0.006
 oceans-0.006
 glory-0.006
 horizon-0.005
Token a
Token ID257
Feature activation+5.32e-01

Pos logit contributions
 habitat+0.058
 exp+0.052
 oceans+0.051
 glory+0.051
 horizon+0.051
Neg logit contributions
 yes-0.040
ggy-0.040
ver-0.038
ggie-0.037
 doll-0.035
Token lot
Token ID1256
Feature activation+2.30e+00

Pos logit contributions
 habitat+0.014
 exp+0.013
 sav+0.013
 horizon+0.013
 oceans+0.012
Neg logit contributions
ver-0.011
ggy-0.011
 yes-0.010
ggie-0.010
aches-0.009
Token safer
Token ID14178
Feature activation+3.54e+00

Pos logit contributions
 habitat+0.076
 exp+0.069
 sav+0.068
joy+0.068
 glory+0.067
Neg logit contributions
 yes-0.033
ggy-0.032
ver-0.030
 doll-0.029
ggie-0.029
Token in
Token ID287
Feature activation+4.45e+00

Pos logit contributions
 habitat+0.075
 exp+0.070
 horizon+0.068
 glory+0.067
 sav+0.066
Neg logit contributions
 yes-0.087
ggy-0.087
 doll-0.084
ggie-0.082
ver-0.080
Token the
Token ID262
Feature activation+5.16e+00

Pos logit contributions
 habitat+0.139
 habitats+0.130
 exp+0.128
 glory+0.128
icol+0.127
Neg logit contributions
 mom-0.062
 doll-0.059
ggy-0.056
 nobody-0.055
 anywhere-0.053
Token dark
Token ID3223
Feature activation+7.20e+00

Pos logit contributions
 habitat+0.116
iling+0.104
 habitats+0.104
acks+0.102
ky+0.098
Neg logit contributions
 doll-0.116
 yes-0.115
 mom-0.112
 okay-0.112
 doctor-0.109
Token".
Token ID1911
Feature activation+4.74e-01

Pos logit contributions
awks+0.178
pill+0.175
eals+0.170
 habitats+0.168
alks+0.167
Neg logit contributions
 doll-0.112
 lamp-0.105
 friend-0.100
 mom-0.099
 anywhere-0.098
Token The
Token ID383
Feature activation-6.73e-01

Pos logit contributions
 habitat+0.011
 habitats+0.010
 glory+0.010
 oceans+0.010
 horizon+0.010
Neg logit contributions
 yes-0.011
ver-0.011
ggy-0.011
 doll-0.010
 mom-0.010
Token boy
Token ID2933
Feature activation-8.95e-01

Pos logit contributions
ggy+0.014
 yes+0.013
ggie+0.013
ver+0.013
balls+0.011
Neg logit contributions
 habitat-0.018
 exp-0.017
 horizon-0.017
 oceans-0.017
 sav-0.016
Token nodded
Token ID14464
Feature activation+6.29e-01

Pos logit contributions
 yes+0.017
ggy+0.017
ver+0.017
ggie+0.016
 doll+0.015
Neg logit contributions
 habitat-0.024
 exp-0.022
 sav-0.022
 glory-0.021
ky-0.021
Token,
Token ID11
Feature activation+1.20e+00

Pos logit contributions
 habitat+0.011
 exp+0.010
 oceans+0.010
ky+0.009
 sav+0.009
Neg logit contributions
ggy-0.018
ver-0.017
ggie-0.017
 yes-0.017
 doll-0.016
Token the
Token ID262
Feature activation+9.46e-01

Pos logit contributions
 habitat+0.045
 exp+0.041
 glory+0.040
 oceans+0.040
 horizon+0.040
Neg logit contributions
 yes-0.030
ggy-0.029
ver-0.028
ggie-0.027
 doll-0.026
Token sun
Token ID4252
Feature activation+1.20e-01

Pos logit contributions
 habitat+0.022
 exp+0.020
 oceans+0.019
 glory+0.019
 sav+0.019
Neg logit contributions
 yes-0.023
ggy-0.022
ggie-0.021
ver-0.021
 doll-0.020
Token rises
Token ID16736
Feature activation+2.12e+00

Pos logit contributions
 habitat+0.003
 exp+0.003
 oceans+0.003
 glory+0.003
 horizon+0.003
Neg logit contributions
 yes-0.002
ggy-0.002
ver-0.002
ggie-0.002
 doll-0.002
Token in
Token ID287
Feature activation+3.76e+00

Pos logit contributions
 habitat+0.058
 habitats+0.050
 glory+0.049
joy+0.049
 exp+0.049
Neg logit contributions
 yes-0.044
ver-0.043
ggy-0.041
ggie-0.039
 doll-0.038
Token the
Token ID262
Feature activation+5.51e+00

Pos logit contributions
 habitat+0.133
 habitats+0.121
acks+0.121
elly+0.119
ashes+0.117
Neg logit contributions
 yes-0.046
 mom-0.044
 okay-0.039
 doll-0.038
 nobody-0.034
Token opposite
Token ID6697
Feature activation+7.18e+00

Pos logit contributions
 habitat+0.104
 habitats+0.087
iling+0.082
 than+0.078
joy+0.078
Neg logit contributions
 doll-0.151
 yes-0.149
tr-0.143
 mom-0.142
 okay-0.136
Token direction
Token ID4571
Feature activation+2.30e+00

Pos logit contributions
icol+0.164
 habitat+0.160
joy+0.157
 Now+0.145
 habitats+0.145
Neg logit contributions
 friend-0.138
 mom-0.132
 doll-0.129
 yes-0.124
ver-0.122
Token".
Token ID1911
Feature activation+3.09e-01

Pos logit contributions
 habitat+0.054
 sav+0.045
 exp+0.045
 glory+0.045
 habitats+0.045
Neg logit contributions
 yes-0.057
ggy-0.054
ver-0.054
 doll-0.051
ggie-0.051
Token Jack
Token ID3619
Feature activation-2.64e-01

Pos logit contributions
 habitat+0.009
 oceans+0.008
 horizon+0.008
 glory+0.008
 exp+0.008
Neg logit contributions
 yes-0.006
ggy-0.005
ver-0.005
ggie-0.005
 doll-0.005
Token thought
Token ID1807
Feature activation-9.18e-01

Pos logit contributions
 yes+0.006
ggy+0.006
ver+0.005
ggie+0.005
 doll+0.005
Neg logit contributions
 habitat-0.007
 exp-0.006
 sav-0.006
ky-0.006
 oceans-0.006
Token this
Token ID428
Feature activation-1.03e+00

Pos logit contributions
ggy+0.020
 yes+0.019
ggie+0.019
ver+0.019
 doll+0.018
Neg logit contributions
 habitat-0.021
 exp-0.019
 oceans-0.019
 glory-0.019
 horizon-0.019
Token,
Token ID11
Feature activation+1.88e+00

Pos logit contributions
 yes+0.016
ggy+0.015
ver+0.014
ggie+0.014
 doll+0.014
Neg logit contributions
 habitat-0.016
 exp-0.014
 glory-0.014
 habitats-0.014
 sav-0.014
Token through
Token ID832
Feature activation+3.65e+00

Pos logit contributions
 habitat+0.043
 glory+0.037
 exp+0.037
 horizon+0.036
 habitats+0.036
Neg logit contributions
 yes-0.048
ggy-0.042
 doll-0.041
ver-0.040
ggie-0.040
Token the
Token ID262
Feature activation+3.77e+00

Pos logit contributions
 habitat+0.099
 exp+0.089
 glory+0.087
ky+0.086
acks+0.086
Neg logit contributions
 yes-0.071
ggy-0.064
 doll-0.063
 mom-0.061
ver-0.059
Token lush
Token ID37408
Feature activation+7.50e+00

Pos logit contributions
 habitat+0.081
iling+0.074
elly+0.071
 Now+0.071
az+0.070
Neg logit contributions
 doll-0.079
 crown-0.077
 mom-0.076
 yes-0.075
 friend-0.073
Token forests
Token ID17039
Feature activation+1.99e+00

Pos logit contributions
 habitat+0.179
Fighting+0.167
oky+0.166
iling+0.165
ulk+0.163
Neg logit contributions
 doll-0.121
 crown-0.120
 mom-0.111
 shield-0.107
 friend-0.105
Token deep
Token ID2769
Feature activation+7.08e+00

Pos logit contributions
 habitat+0.049
 exp+0.044
 habitats+0.042
 glory+0.042
 sav+0.041
Neg logit contributions
 yes-0.046
ggy-0.044
ver-0.043
ggie-0.041
 doll-0.040
Token in
Token ID287
Feature activation+4.61e+00

Pos logit contributions
Fighting+0.141
 habitat+0.137
 sch+0.136
istence+0.132
 venue+0.132
Neg logit contributions
 in-0.126
 out-0.126
 crown-0.123
 on-0.122
 doll-0.121
Token thought
Token ID1807
Feature activation+8.83e-02

Pos logit contributions
 habitat+0.161
 habitats+0.145
iling+0.144
icol+0.141
elly+0.139
Neg logit contributions
 mom-0.050
 doll-0.048
 yes-0.047
 nobody-0.040
 else-0.035
Token.
Token ID13
Feature activation+1.51e+00

Pos logit contributions
 habitat+0.002
 oceans+0.002
 exp+0.002
 glory+0.002
 horizon+0.002
Neg logit contributions
ggy-0.002
 yes-0.002
ver-0.002
ggie-0.002
 doll-0.002
Token He
Token ID679
Feature activation+1.67e+00

Pos logit contributions
 habitat+0.035
 glory+0.032
 exp+0.031
 horizon+0.031
ky+0.031
Neg logit contributions
 yes-0.036
ver-0.034
ggy-0.033
ggie-0.032
 doll-0.031
Token admired
Token ID29382
Feature activation-2.80e-01

Pos logit contributions
 habitat+0.046
 exp+0.041
 glory+0.041
 horizon+0.040
 oceans+0.040
Neg logit contributions
 yes-0.034
ggy-0.033
ver-0.031
ggie-0.031
 doll-0.029
Token drove
Token ID10357
Feature activation+1.14e-01

Pos logit contributions
 habitat+0.051
 exp+0.046
 glory+0.046
 horizon+0.045
 habitats+0.045
Neg logit contributions
 yes-0.028
ggy-0.027
ver-0.026
ggie-0.025
 doll-0.024
Token the
Token ID262
Feature activation+7.38e-01

Pos logit contributions
 habitat+0.003
 exp+0.003
 glory+0.003
 oceans+0.003
 horizon+0.003
Neg logit contributions
 yes-0.002
ggy-0.002
ver-0.002
ggie-0.002
 doll-0.002
Token plane
Token ID6614
Feature activation-1.28e-01

Pos logit contributions
 habitat+0.024
 exp+0.022
 habitats+0.021
 glory+0.021
 sav+0.021
Neg logit contributions
 yes-0.011
ggy-0.011
ggie-0.010
 doll-0.010
ver-0.010
Token through
Token ID832
Feature activation+4.15e+00

Pos logit contributions
 yes+0.003
ggy+0.003
ggie+0.003
ver+0.003
 doll+0.003
Neg logit contributions
 habitat-0.003
 exp-0.003
 oceans-0.003
 glory-0.003
 horizon-0.003
Token the
Token ID262
Feature activation+4.23e+00

Pos logit contributions
 habitat+0.133
elly+0.122
ky+0.119
 exp+0.119
acks+0.119
Neg logit contributions
 yes-0.054
 mom-0.052
 doll-0.051
 nobody-0.051
ggy-0.049
Token deep
Token ID2769
Feature activation+7.03e+00

Pos logit contributions
 habitat+0.089
 ago+0.080
iling+0.079
joy+0.078
elly+0.076
Neg logit contributions
 doll-0.100
 mom-0.096
 friend-0.092
ggy-0.088
 doctor-0.088
Token blue
Token ID4171
Feature activation+4.52e+00

Pos logit contributions
brance+0.157
 vitamins+0.149
Fighting+0.147
 habitat+0.145
asks+0.143
Neg logit contributions
 doll-0.128
 mom-0.119
 lamp-0.115
 friend-0.114
ie-0.113
Token sky
Token ID6766
Feature activation+3.52e+00

Pos logit contributions
 habitat+0.079
iling+0.075
 sav+0.073
 habitats+0.069
ky+0.068
Neg logit contributions
 doll-0.120
 friend-0.111
 mom-0.109
 yes-0.107
man-0.103
Token until
Token ID1566
Feature activation+1.08e+00

Pos logit contributions
 habitat+0.100
 habitats+0.091
 exp+0.090
iling+0.086
 glory+0.085
Neg logit contributions
 yes-0.071
ggy-0.062
ver-0.062
ggie-0.058
 doll-0.056
Token it
Token ID340
Feature activation+8.92e-01

Pos logit contributions
 habitat+0.036
 exp+0.032
 glory+0.032
 habitats+0.032
ky+0.031
Neg logit contributions
 yes-0.016
ggy-0.016
ver-0.015
ggie-0.014
 doll-0.013
Token was
Token ID373
Feature activation+1.47e+00

Pos logit contributions
 habitat+0.027
 exp+0.025
 oceans+0.024
 glory+0.024
 horizon+0.024
Neg logit contributions
 yes-0.015
ggy-0.015
ver-0.014
ggie-0.014
 doll-0.013
Token It
Token ID632
Feature activation-4.11e-02

Pos logit contributions
 habitat+0.043
 glory+0.039
ky+0.039
 oceans+0.038
 horizon+0.038
Neg logit contributions
 yes-0.042
 okay-0.040
ver-0.038
 doll-0.036
 mom-0.036
Token will
Token ID481
Feature activation-3.27e-01

Pos logit contributions
 yes+0.001
ggy+0.001
ggie+0.001
ver+0.001
 doll+0.001
Neg logit contributions
 habitat-0.001
 exp-0.001
 oceans-0.001
 glory-0.001
 horizon-0.001
Token glow
Token ID19634
Feature activation+1.14e+00

Pos logit contributions
 yes+0.005
ggy+0.005
ver+0.005
ggie+0.004
 doll+0.004
Neg logit contributions
 habitat-0.010
 exp-0.009
 oceans-0.009
 habitats-0.009
 glory-0.009
Token in
Token ID287
Feature activation+3.07e+00

Pos logit contributions
 habitat+0.028
 exp+0.025
 glory+0.024
 sav+0.024
 horizon+0.024
Neg logit contributions
 yes-0.027
ggy-0.026
ver-0.025
ggie-0.024
 doll-0.024
Token the
Token ID262
Feature activation+4.00e+00

Pos logit contributions
 habitat+0.098
 habitats+0.087
acks+0.086
 exp+0.085
joy+0.084
Neg logit contributions
 yes-0.049
 mom-0.047
 doll-0.045
 okay-0.042
ggy-0.041
Token dark
Token ID3223
Feature activation+7.00e+00

Pos logit contributions
 habitat+0.086
 habitats+0.074
ky+0.069
joy+0.068
 exp+0.068
Neg logit contributions
 yes-0.103
 doll-0.100
ggy-0.093
 mom-0.093
 okay-0.091
Token and
Token ID290
Feature activation+1.80e+00

Pos logit contributions
 habitat+0.190
 habitats+0.183
pill+0.178
joy+0.177
awks+0.174
Neg logit contributions
 doll-0.119
 mom-0.115
 lamp-0.109
man-0.104
 friend-0.093
Token scare
Token ID19437
Feature activation+2.56e+00

Pos logit contributions
 habitat+0.051
 exp+0.045
 glory+0.045
 habitats+0.044
 oceans+0.044
Neg logit contributions
 yes-0.035
ggy-0.033
ver-0.031
ggie-0.031
 doll-0.030
Token away
Token ID1497
Feature activation+1.64e+00

Pos logit contributions
 habitat+0.063
 exp+0.055
 glory+0.054
 horizon+0.054
 sav+0.054
Neg logit contributions
 yes-0.058
ggy-0.058
ggie-0.054
ver-0.053
 doll-0.053
Token the
Token ID262
Feature activation+2.33e+00

Pos logit contributions
 habitat+0.033
 exp+0.029
 sav+0.028
 glory+0.028
 horizon+0.028
Neg logit contributions
 yes-0.044
ggy-0.043
ver-0.041
ggie-0.041
 doll-0.040
Token bad
Token ID2089
Feature activation+2.27e+00

Pos logit contributions
 habitat+0.055
 exp+0.049
 oceans+0.048
 glory+0.048
 horizon+0.047
Neg logit contributions
 yes-0.055
ggy-0.054
ver-0.052
ggie-0.051
 doll-0.049
Token good
Token ID922
Feature activation+2.42e+00

Pos logit contributions
 habitat+0.041
ky+0.038
 habitats+0.038
joy+0.037
 horizon+0.037
Neg logit contributions
ggy-0.013
 yes-0.012
 okay-0.012
 else-0.010
ver-0.010
Token to
Token ID284
Feature activation-4.27e-01

Pos logit contributions
 habitat+0.083
 exp+0.082
 horizon+0.079
 oceans+0.077
 sav+0.075
Neg logit contributions
ggy-0.035
 yes-0.034
ver-0.032
balls-0.030
ggie-0.030
Token roll
Token ID4836
Feature activation-7.97e-02

Pos logit contributions
 yes+0.009
ggy+0.009
ver+0.008
ggie+0.008
 doll+0.007
Neg logit contributions
 habitat-0.011
 exp-0.010
 sav-0.010
 glory-0.010
 horizon-0.010
Token in
Token ID287
Feature activation+1.95e+00

Pos logit contributions
 yes+0.002
ggy+0.002
ver+0.002
ggie+0.002
 doll+0.002
Neg logit contributions
 habitat-0.002
 exp-0.002
 oceans-0.002
 glory-0.002
 horizon-0.002
Token the
Token ID262
Feature activation+3.64e+00

Pos logit contributions
 habitat+0.053
 exp+0.048
 glory+0.047
 horizon+0.046
 habitats+0.046
Neg logit contributions
 yes-0.041
ggy-0.039
ggie-0.036
 doll-0.036
ver-0.036
Token lush
Token ID37408
Feature activation+6.89e+00

Pos logit contributions
 habitat+0.074
 ago+0.066
iling+0.065
 exp+0.064
 habitats+0.062
Neg logit contributions
 doll-0.086
 yes-0.084
 okay-0.083
 mom-0.082
ggy-0.082
Token green
Token ID4077
Feature activation+4.43e+00

Pos logit contributions
joy+0.158
Fighting+0.157
 habitat+0.156
ok+0.150
iling+0.150
Neg logit contributions
 doll-0.118
 shield-0.116
 friend-0.109
 mom-0.109
 cushion-0.105
Token grass
Token ID8701
Feature activation+1.32e+00

Pos logit contributions
joy+0.092
iling+0.088
icol+0.086
ishment+0.085
 habitat+0.085
Neg logit contributions
 doll-0.098
 friend-0.095
 shield-0.093
 bear-0.089
 scarf-0.087
Token and
Token ID290
Feature activation+1.37e+00

Pos logit contributions
 habitat+0.031
 exp+0.027
 glory+0.027
 oceans+0.026
 sav+0.026
Neg logit contributions
 yes-0.032
ggy-0.031
ver-0.030
ggie-0.030
 doll-0.028
Token jump
Token ID4391
Feature activation+5.94e-01

Pos logit contributions
 habitat+0.034
 exp+0.031
 oceans+0.031
 sav+0.030
 glory+0.030
Neg logit contributions
ggy-0.030
 yes-0.030
ver-0.029
ggie-0.029
 doll-0.027
Token high
Token ID1029
Feature activation+3.25e+00

Pos logit contributions
 habitat+0.014
 exp+0.013
 oceans+0.013
 horizon+0.012
 sav+0.012
Neg logit contributions
ggy-0.013
 yes-0.013
ggie-0.013
ver-0.013
 doll-0.012
Token repl
Token ID2186
Feature activation+1.20e+00

Pos logit contributions
 habitat+0.031
 exp+0.028
 glory+0.028
 oceans+0.028
 sav+0.028
Neg logit contributions
 yes-0.025
ggy-0.025
ver-0.024
ggie-0.024
 doll-0.022
Tokenanted
Token ID4126
Feature activation+1.60e+00

Pos logit contributions
 habitat+0.031
 glory+0.027
ky+0.027
 exp+0.027
 oceans+0.026
Neg logit contributions
 yes-0.027
ggy-0.026
 doll-0.024
ggie-0.024
ver-0.024
Token deeper
Token ID9211
Feature activation+4.98e+00

Pos logit contributions
 habitat+0.037
 exp+0.032
 oceans+0.032
 glory+0.032
 horizon+0.031
Neg logit contributions
 yes-0.039
ggy-0.038
ver-0.036
ggie-0.036
 doll-0.035
Token into
Token ID656
Feature activation+3.11e+00

Pos logit contributions
 habitat+0.116
 exp+0.109
 Now+0.108
 sav+0.105
 sch+0.105
Neg logit contributions
 yes-0.095
ggy-0.091
 doll-0.087
ggie-0.087
 friend-0.085
Token the
Token ID262
Feature activation+4.45e+00

Pos logit contributions
 habitat+0.093
 exp+0.084
 habitats+0.083
ky+0.081
 horizon+0.080
Neg logit contributions
 yes-0.049
ggy-0.048
 mom-0.046
 doll-0.044
ggie-0.043
Token dark
Token ID3223
Feature activation+6.88e+00

Pos logit contributions
 habitat+0.094
acks+0.081
 habitats+0.078
 exp+0.077
rs+0.076
Neg logit contributions
 yes-0.101
ggy-0.101
 mom-0.100
 doll-0.098
ggie-0.094
Token forest
Token ID8222
Feature activation+2.40e+00

Pos logit contributions
ips+0.178
eals+0.172
 habitat+0.172
ags+0.172
awks+0.170
Neg logit contributions
man-0.098
 mom-0.098
 doll-0.095
 friend-0.089
 bird-0.088
Token.
Token ID13
Feature activation+7.62e-01

Pos logit contributions
 habitat+0.061
 exp+0.055
 glory+0.053
 habitats+0.053
 horizon+0.052
Neg logit contributions
 yes-0.052
ggy-0.052
ggie-0.048
ver-0.048
 doll-0.045
Token<|endoftext|>
Token ID50256
Feature activation+2.35e+00

Pos logit contributions
 habitat+0.021
 exp+0.018
ky+0.018
 oceans+0.018
 glory+0.018
Neg logit contributions
 yes-0.016
ver-0.015
ggy-0.015
ggie-0.014
 doll-0.014
TokenM
Token ID44
Feature activation-1.24e+00

Pos logit contributions
 habitat+0.044
 exp+0.037
 glory+0.037
 horizon+0.036
 oceans+0.036
Neg logit contributions
ggy-0.067
 yes-0.067
ver-0.065
ggie-0.064
 doll-0.062
Tokenolly
Token ID5098
Feature activation+1.72e+00

Pos logit contributions
 yes+0.035
ver+0.034
ggy+0.034
 doll+0.033
ggie+0.033
Neg logit contributions
 habitat-0.022
 glory-0.019
 sav-0.019
 horizon-0.019
 exp-0.019
Token
Token ID198
Feature activation+9.63e-01

Pos logit contributions
 habitat+0.028
 glory+0.025
 exp+0.024
 horizon+0.024
 oceans+0.024
Neg logit contributions
ggy-0.025
 yes-0.025
ver-0.024
ggie-0.023
 doll-0.022
TokenHe
Token ID1544
Feature activation+1.19e+00

Pos logit contributions
 habitat+0.028
 glory+0.025
 exp+0.025
 horizon+0.025
 oceans+0.025
Neg logit contributions
ggy-0.018
 yes-0.018
ggie-0.017
ver-0.017
 doll-0.015
Token soared
Token ID35292
Feature activation+1.38e+00

Pos logit contributions
 habitat+0.034
 exp+0.031
 glory+0.030
 horizon+0.030
 oceans+0.030
Neg logit contributions
 yes-0.022
ggy-0.022
ver-0.021
ggie-0.020
 doll-0.019
Token through
Token ID832
Feature activation+3.56e+00

Pos logit contributions
 habitat+0.038
 exp+0.034
 glory+0.033
 habitats+0.033
 sav+0.033
Neg logit contributions
 yes-0.028
ggy-0.027
ver-0.026
ggie-0.025
 doll-0.024
Token the
Token ID262
Feature activation+4.55e+00

Pos logit contributions
 habitat+0.113
ky+0.100
 exp+0.100
 habitats+0.100
 glory+0.100
Neg logit contributions
 yes-0.051
 doll-0.049
 mom-0.046
ggy-0.046
 nobody-0.043
Token dark
Token ID3223
Feature activation+6.84e+00

Pos logit contributions
 habitat+0.093
iling+0.082
 habitats+0.081
rs+0.078
 than+0.077
Neg logit contributions
 doll-0.113
 mom-0.110
 hammer-0.108
 friend-0.105
 doctor-0.103
Token night
Token ID1755
Feature activation+6.73e+00

Pos logit contributions
 habitat+0.150
brance+0.147
ishment+0.142
 habitats+0.139
awks+0.139
Neg logit contributions
 doll-0.132
 mom-0.121
 lamp-0.119
 bird-0.110
man-0.110
Token!
Token ID0
Feature activation+1.47e+00

Pos logit contributions
 habitat+0.173
 habitats+0.162
iling+0.142
ishment+0.135
 vitamins+0.132
Neg logit contributions
 mom-0.135
 doll-0.135
ggy-0.132
man-0.123
on-0.119
Token He
Token ID679
Feature activation+2.12e+00

Pos logit contributions
 habitat+0.036
ky+0.033
 glory+0.033
 oceans+0.032
 habitats+0.032
Neg logit contributions
 yes-0.032
ver-0.030
ggy-0.030
ggie-0.028
 doll-0.028
Token felt
Token ID2936
Feature activation+1.73e+00

Pos logit contributions
 habitat+0.069
 habitats+0.062
 exp+0.061
 glory+0.061
 horizon+0.060
Neg logit contributions
 yes-0.032
ggy-0.031
ver-0.029
ggie-0.027
 else-0.026
Token happy
Token ID3772
Feature activation+2.10e+00

Pos logit contributions
 habitat+0.057
 habitats+0.054
ky+0.050
 glory+0.049
elly+0.048
Neg logit contributions
 yes-0.030
 okay-0.026
ggy-0.026
ver-0.025
 else-0.024
Token lay
Token ID3830
Feature activation+1.26e+00

Pos logit contributions
 sav+0.018
 habitat+0.018
 exp+0.018
 oceans+0.017
 hills+0.017
Neg logit contributions
ggy-0.021
ver-0.020
ggie-0.020
 yes-0.019
ves-0.017
Token it
Token ID340
Feature activation-2.93e-01

Pos logit contributions
 habitat+0.038
 exp+0.034
 glory+0.033
 horizon+0.033
 oceans+0.033
Neg logit contributions
 yes-0.023
ggy-0.022
ver-0.020
ggie-0.020
 doll-0.020
Token down
Token ID866
Feature activation+2.42e+00

Pos logit contributions
ggy+0.006
 yes+0.005
ggie+0.005
ver+0.005
 doll+0.005
Neg logit contributions
 habitat-0.008
 exp-0.007
 oceans-0.007
 sav-0.007
ky-0.007
Token in
Token ID287
Feature activation+2.27e+00

Pos logit contributions
 habitat+0.088
 habitats+0.080
 exp+0.076
 glory+0.076
 horizon+0.073
Neg logit contributions
 yes-0.034
ver-0.029
 doll-0.027
 okay-0.025
 mom-0.024
Token the
Token ID262
Feature activation+4.09e+00

Pos logit contributions
 habitat+0.073
 habitats+0.065
 exp+0.064
 horizon+0.063
 glory+0.063
Neg logit contributions
 yes-0.036
 doll-0.036
 mom-0.033
ggy-0.033
ggie-0.030
Token deep
Token ID2769
Feature activation+6.80e+00

Pos logit contributions
 habitat+0.094
 ago+0.084
 habitats+0.084
joy+0.081
iling+0.079
Neg logit contributions
 doll-0.096
ggy-0.090
 mom-0.087
tr-0.086
 yes-0.084
Token,
Token ID11
Feature activation+2.83e+00

Pos logit contributions
joy+0.175
pill+0.173
Fighting+0.170
 MacDonald+0.166
 habitats+0.166
Neg logit contributions
 doll-0.117
 mom-0.106
 friend-0.098
 bear-0.097
 lamp-0.094
Token green
Token ID4077
Feature activation+3.34e+00

Pos logit contributions
 habitat+0.080
 habitats+0.070
 glory+0.068
 exp+0.067
iling+0.066
Neg logit contributions
 yes-0.059
 doll-0.054
ggy-0.051
 okay-0.049
 mom-0.048
Token grass
Token ID8701
Feature activation+6.26e-01

Pos logit contributions
 habitat+0.065
joy+0.056
 habitats+0.055
 glory+0.055
iling+0.054
Neg logit contributions
 doll-0.089
 yes-0.081
ggy-0.079
 mom-0.078
man-0.077
Token.
Token ID13
Feature activation+8.80e-01

Pos logit contributions
 habitat+0.015
 exp+0.013
 glory+0.013
 oceans+0.013
 horizon+0.013
Neg logit contributions
 yes-0.015
ggy-0.014
ver-0.014
ggie-0.013
 doll-0.013
Token
Token ID198
Feature activation-2.09e-01

Pos logit contributions
 habitat+0.020
 exp+0.018
 oceans+0.017
 glory+0.017
 horizon+0.017
Neg logit contributions
 yes-0.022
ggy-0.021
ver-0.020
ggie-0.020
 doll-0.019
Token water
Token ID1660
Feature activation+6.82e-01

Pos logit contributions
 habitat+0.041
 exp+0.036
 oceans+0.035
 glory+0.035
 horizon+0.035
Neg logit contributions
 yes-0.047
ggy-0.046
ver-0.044
ggie-0.044
 doll-0.042
Token and
Token ID290
Feature activation+1.03e+00

Pos logit contributions
 habitat+0.016
 exp+0.014
 oceans+0.014
 glory+0.014
 habitats+0.014
Neg logit contributions
 yes-0.016
ggy-0.016
ver-0.015
ggie-0.015
 doll-0.014
Token disappeared
Token ID12120
Feature activation+2.38e+00

Pos logit contributions
 habitat+0.027
 sav+0.024
 oceans+0.024
 exp+0.024
 glory+0.024
Neg logit contributions
ggy-0.022
 yes-0.022
ver-0.021
ggie-0.021
 doll-0.019
Token into
Token ID656
Feature activation+2.53e+00

Pos logit contributions
 habitat+0.061
 exp+0.055
 habitats+0.054
 sav+0.053
 oceans+0.052
Neg logit contributions
 yes-0.051
ggy-0.049
ggie-0.045
ver-0.045
 doll-0.045
Token the
Token ID262
Feature activation+3.92e+00

Pos logit contributions
 habitat+0.074
 exp+0.068
 habitats+0.066
ky+0.066
 horizon+0.065
Neg logit contributions
ggy-0.043
 yes-0.043
 mom-0.040
ggie-0.039
 doll-0.039
Token deep
Token ID2769
Feature activation+6.80e+00

Pos logit contributions
 habitat+0.069
 habitats+0.057
 exp+0.055
 glory+0.053
ky+0.052
Neg logit contributions
 yes-0.110
ggy-0.107
 doll-0.106
ggie-0.102
 mom-0.102
Token blue
Token ID4171
Feature activation+3.94e+00

Pos logit contributions
 habitat+0.134
 habitats+0.131
brance+0.123
 sch+0.118
 MacDonald+0.116
Neg logit contributions
 doll-0.143
 mom-0.141
 friend-0.135
 hammer-0.128
 magnet-0.126
Token sea
Token ID5417
Feature activation+1.21e+00

Pos logit contributions
 habitat+0.075
 habitats+0.064
 exp+0.062
 sav+0.061
 oceans+0.061
Neg logit contributions
 doll-0.105
 yes-0.101
ggy-0.100
 mom-0.097
 hammer-0.096
Token.
Token ID13
Feature activation+7.26e-01

Pos logit contributions
 habitat+0.029
 exp+0.025
 glory+0.025
 oceans+0.024
 horizon+0.024
Neg logit contributions
 yes-0.029
ggy-0.028
ggie-0.027
ver-0.026
 doll-0.026
Token<|endoftext|>
Token ID50256
Feature activation+2.38e+00

Pos logit contributions
 habitat+0.021
 oceans+0.018
ky+0.018
 exp+0.018
 glory+0.018
Neg logit contributions
 yes-0.014
ggy-0.014
ver-0.013
ggie-0.013
 doll-0.012
TokenM
Token ID44
Feature activation-1.13e+00

Pos logit contributions
 habitat+0.048
 glory+0.041
 exp+0.040
 habitats+0.039
 horizon+0.039
Neg logit contributions
ggy-0.065
 yes-0.064
ver-0.063
ggie-0.062
 doll-0.060
Token big
Token ID1263
Feature activation+2.85e+00

Pos logit contributions
 habitat+0.033
ky+0.029
 exp+0.029
 glory+0.028
 habitats+0.028
Neg logit contributions
 yes-0.032
ggy-0.031
ggie-0.029
 doll-0.029
 mom-0.028
Token creatures
Token ID8109
Feature activation-1.86e-01

Pos logit contributions
 habitat+0.093
 habitats+0.086
 Now+0.084
ky+0.084
Now+0.083
Neg logit contributions
 mom-0.037
 doll-0.035
 yes-0.035
 friend-0.033
 hammer-0.031
Token lurking
Token ID36105
Feature activation+2.98e+00

Pos logit contributions
ggy+0.004
 yes+0.004
ggie+0.004
ver+0.004
 doll+0.004
Neg logit contributions
 habitat-0.004
 exp-0.004
 oceans-0.004
 horizon-0.004
 sav-0.004
Token in
Token ID287
Feature activation+2.54e+00

Pos logit contributions
 habitat+0.085
 exp+0.077
 glory+0.076
 horizon+0.075
 oceans+0.075
Neg logit contributions
ggy-0.056
 yes-0.055
ggie-0.052
ver-0.051
 doll-0.048
Token the
Token ID262
Feature activation+4.33e+00

Pos logit contributions
 habitat+0.071
 exp+0.064
 glory+0.063
 horizon+0.062
 habitats+0.062
Neg logit contributions
ggy-0.048
 yes-0.048
ggie-0.044
 doll-0.043
ver-0.042
Token deep
Token ID2769
Feature activation+6.79e+00

Pos logit contributions
 habitat+0.093
joy+0.086
iling+0.084
 habitats+0.084
 ago+0.083
Neg logit contributions
ggy-0.094
 doll-0.091
 mom-0.091
 yes-0.089
 else-0.085
Token dark
Token ID3223
Feature activation+6.50e+00

Pos logit contributions
brance+0.152
istence+0.152
joy+0.148
 MacDonald+0.146
Now+0.146
Neg logit contributions
 friend-0.118
 mom-0.110
 bear-0.108
 doll-0.106
ie-0.102
Token waters
Token ID10150
Feature activation+2.14e+00

Pos logit contributions
istence+0.196
joy+0.196
icol+0.194
brance+0.193
awks+0.187
Neg logit contributions
 mom-0.059
man-0.058
 friend-0.057
 doll-0.056
ggy-0.051
Token.
Token ID13
Feature activation+1.18e+00

Pos logit contributions
 habitat+0.052
 exp+0.046
 glory+0.045
 oceans+0.045
 sav+0.045
Neg logit contributions
 yes-0.049
ggy-0.048
ver-0.046
ggie-0.046
 doll-0.044
Token
Token ID220
Feature activation+1.37e-01

Pos logit contributions
 habitat+0.026
 exp+0.023
 oceans+0.023
 glory+0.023
 horizon+0.023
Neg logit contributions
 yes-0.029
ggy-0.029
ver-0.028
ggie-0.028
 doll-0.026
Token
Token ID198
Feature activation+3.93e-01

Pos logit contributions
 habitat+0.002
 oceans+0.002
 exp+0.002
 horizon+0.002
 sav+0.002
Neg logit contributions
 yes-0.004
ggy-0.004
ggie-0.004
 doll-0.004
ver-0.004
Token She
Token ID1375
Feature activation+2.23e-02

Pos logit contributions
 habitat+0.006
 glory+0.005
ky+0.005
 horizon+0.005
 habitats+0.005
Neg logit contributions
 yes-0.006
ggy-0.005
 doll-0.005
ver-0.005
ggie-0.005
Token loved
Token ID6151
Feature activation+7.07e-02

Pos logit contributions
 habitat+0.001
 horizon+0.001
 exp+0.001
 glory+0.001
 oceans+0.001
Neg logit contributions
ggy-0.000
 yes-0.000
ggie-0.000
ver-0.000
 doll-0.000
Token swimming
Token ID14899
Feature activation+1.77e-01

Pos logit contributions
 habitat+0.002
 horizon+0.002
 glory+0.002
ky+0.002
 exp+0.002
Neg logit contributions
 yes-0.001
ggy-0.001
ggie-0.001
 doll-0.001
 mom-0.001
Token in
Token ID287
Feature activation+2.63e+00

Pos logit contributions
 habitat+0.006
 horizon+0.005
 glory+0.005
 exp+0.005
 ago+0.005
Neg logit contributions
 yes-0.003
ggy-0.003
ggie-0.002
 doll-0.002
ver-0.002
Token the
Token ID262
Feature activation+3.43e+00

Pos logit contributions
 habitat+0.090
 habitats+0.080
 glory+0.080
 horizon+0.078
ky+0.078
Neg logit contributions
 doll-0.036
 mom-0.035
 yes-0.035
ggy-0.032
ggie-0.027
Token deep
Token ID2769
Feature activation+6.76e+00

Pos logit contributions
 habitat+0.066
 ago+0.056
 habitats+0.055
joy+0.054
 glory+0.054
Neg logit contributions
ggy-0.089
 mom-0.089
 doll-0.088
 yes-0.087
 friend-0.084
Token,
Token ID11
Feature activation+1.93e+00

Pos logit contributions
joy+0.175
Fighting+0.170
istence+0.168
brance+0.166
 MacDonald+0.165
Neg logit contributions
 friend-0.110
 mom-0.106
 doll-0.103
ie-0.098
 bird-0.095
Token blue
Token ID4171
Feature activation+3.69e+00

Pos logit contributions
 habitat+0.054
 glory+0.048
 habitats+0.047
 exp+0.046
 horizon+0.045
Neg logit contributions
 yes-0.041
ggy-0.037
 doll-0.036
ver-0.034
 okay-0.034
Token sea
Token ID5417
Feature activation+6.40e-01

Pos logit contributions
icol+0.074
istence+0.073
 habitat+0.071
iling+0.069
 olds+0.067
Neg logit contributions
 friend-0.089
 mom-0.085
 doll-0.081
man-0.077
 bird-0.074
Token.
Token ID13
Feature activation+1.17e+00

Pos logit contributions
 habitat+0.017
 exp+0.016
 horizon+0.015
 glory+0.015
 habitats+0.015
Neg logit contributions
ggy-0.013
 yes-0.013
ggie-0.012
 doll-0.012
ver-0.012
Token Everywhere
Token ID48201
Feature activation+1.30e-01

Pos logit contributions
 habitat+0.029
 glory+0.025
ky+0.025
 oceans+0.025
 horizon+0.025
Neg logit contributions
 yes-0.027
ggy-0.025
ver-0.025
 doll-0.025
ggie-0.024
Token was
Token ID373
Feature activation+1.12e+00

Pos logit contributions
 yes+0.004
ggy+0.004
ver+0.004
ggie+0.004
 doll+0.004
Neg logit contributions
 habitat-0.009
 exp-0.008
 oceans-0.008
 glory-0.008
 horizon-0.008
Token all
Token ID477
Feature activation+1.48e+00

Pos logit contributions
 habitat+0.036
 exp+0.033
 horizon+0.033
 oceans+0.032
 glory+0.032
Neg logit contributions
 yes-0.017
ggy-0.016
ggie-0.015
ver-0.015
 doll-0.014
Token alone
Token ID3436
Feature activation+2.32e+00

Pos logit contributions
 habitat+0.037
 exp+0.033
 horizon+0.033
 glory+0.032
 oceans+0.032
Neg logit contributions
 yes-0.032
ggy-0.031
 doll-0.030
ver-0.030
ggie-0.029
Token in
Token ID287
Feature activation+3.33e+00

Pos logit contributions
 habitat+0.069
 exp+0.065
 horizon+0.064
 sav+0.062
 glory+0.062
Neg logit contributions
 yes-0.041
ver-0.039
ggy-0.039
 doll-0.035
ggie-0.035
Token the
Token ID262
Feature activation+3.78e+00

Pos logit contributions
 habitat+0.104
ky+0.100
icol+0.098
 habitats+0.097
 glory+0.096
Neg logit contributions
 mom-0.046
 nobody-0.044
 yes-0.043
ggy-0.042
 doll-0.039
Token deep
Token ID2769
Feature activation+6.75e+00

Pos logit contributions
 habitat+0.067
 Now+0.061
 habitats+0.060
icol+0.060
ky+0.059
Neg logit contributions
 yes-0.097
 mom-0.095
 nobody-0.092
 friend-0.090
 else-0.090
Token,
Token ID11
Feature activation+2.94e+00

Pos logit contributions
brance+0.133
Now+0.132
pill+0.132
 Now+0.130
Fighting+0.130
Neg logit contributions
 friend-0.137
 mom-0.129
 shield-0.127
ie-0.125
 doll-0.124
Token dark
Token ID3223
Feature activation+5.72e+00

Pos logit contributions
 habitat+0.079
 glory+0.070
 habitats+0.070
iling+0.069
acks+0.069
Neg logit contributions
 yes-0.060
 doll-0.053
 okay-0.052
ggy-0.051
 nobody-0.051
Token blue
Token ID4171
Feature activation+4.24e+00

Pos logit contributions
awks+0.132
brance+0.131
istence+0.129
 habitat+0.126
 habitats+0.126
Neg logit contributions
 mom-0.095
 friend-0.094
 doll-0.092
 anywhere-0.091
man-0.088
Token water
Token ID1660
Feature activation+1.08e+00

Pos logit contributions
icol+0.070
 sav+0.068
 habitat+0.067
 Now+0.067
ky+0.066
Neg logit contributions
 yes-0.109
 friend-0.107
 mom-0.103
 doll-0.100
 nobody-0.096
Token.
Token ID13
Feature activation+8.41e-01

Pos logit contributions
 habitat+0.029
 exp+0.027
 glory+0.026
 oceans+0.026
 horizon+0.026
Neg logit contributions
 yes-0.021
ggy-0.021
ggie-0.019
ver-0.019
 doll-0.019
Token.
Token ID13
Feature activation+1.08e-01

Pos logit contributions
 yes+0.029
ggy+0.028
ver+0.027
ggie+0.026
 doll+0.024
Neg logit contributions
 habitat-0.038
 exp-0.034
 sav-0.034
 oceans-0.034
ky-0.033
Token He
Token ID679
Feature activation-8.71e-02

Pos logit contributions
 habitat+0.003
 glory+0.003
 horizon+0.003
iling+0.003
ky+0.002
Neg logit contributions
 yes-0.002
 mom-0.002
ggy-0.002
 doll-0.002
ggie-0.002
Token lived
Token ID5615
Feature activation-5.31e-01

Pos logit contributions
ggy+0.002
 yes+0.002
ggie+0.001
ver+0.001
 doll+0.001
Neg logit contributions
 habitat-0.003
 exp-0.002
 horizon-0.002
 oceans-0.002
 glory-0.002
Token in
Token ID287
Feature activation+1.89e+00

Pos logit contributions
 yes+0.009
ggy+0.009
ver+0.008
ggie+0.008
 doll+0.008
Neg logit contributions
 habitat-0.016
 exp-0.014
 oceans-0.014
 glory-0.014
 sav-0.014
Token the
Token ID262
Feature activation+3.25e+00

Pos logit contributions
 habitat+0.066
 exp+0.061
 glory+0.060
 horizon+0.060
 habitats+0.059
Neg logit contributions
ggy-0.024
 yes-0.024
ggie-0.022
ver-0.020
 doll-0.020
Token deep
Token ID2769
Feature activation+6.74e+00

Pos logit contributions
 habitat+0.059
 glory+0.052
 habitats+0.051
 ago+0.051
 than+0.050
Neg logit contributions
ggy-0.090
ggie-0.085
 doll-0.085
 mom-0.085
 yes-0.084
Token,
Token ID11
Feature activation+2.72e+00

Pos logit contributions
brance+0.162
 MacDonald+0.159
Fighting+0.157
Ag+0.153
istence+0.152
Neg logit contributions
 friend-0.121
 mom-0.118
 bear-0.118
 shield-0.107
 doll-0.106
Token blue
Token ID4171
Feature activation+3.73e+00

Pos logit contributions
 habitat+0.080
 habitats+0.070
 glory+0.070
 exp+0.069
 oceans+0.066
Neg logit contributions
 yes-0.052
ggy-0.048
 doll-0.048
 okay-0.044
ggie-0.044
Token sea
Token ID5417
Feature activation+1.02e+00

Pos logit contributions
icol+0.073
ky+0.069
istence+0.067
 glory+0.065
 habitat+0.065
Neg logit contributions
 friend-0.095
 mom-0.091
 doll-0.087
 doctor-0.085
 hammer-0.078
Token.
Token ID13
Feature activation+1.15e+00

Pos logit contributions
 habitat+0.029
 exp+0.027
 horizon+0.026
 glory+0.026
 habitats+0.025
Neg logit contributions
ggy-0.020
 yes-0.019
ggie-0.018
ver-0.018
 doll-0.017
Token He
Token ID679
Feature activation+1.00e+00

Pos logit contributions
 habitat+0.029
ky+0.026
 glory+0.026
 exp+0.025
 horizon+0.025
Neg logit contributions
 yes-0.025
ggy-0.024
 doll-0.023
ver-0.023
ggie-0.023
Token forest
Token ID8222
Feature activation+2.05e+00

Pos logit contributions
 habitat+0.079
 exp+0.072
 habitats+0.069
iling+0.069
acks+0.068
Neg logit contributions
ggy-0.077
 doll-0.076
 mom-0.075
 yes-0.074
ggie-0.071
Token and
Token ID290
Feature activation+8.11e-01

Pos logit contributions
 habitat+0.048
 exp+0.043
 glory+0.041
 oceans+0.041
 sav+0.041
Neg logit contributions
 yes-0.048
ggy-0.048
ver-0.045
ggie-0.045
 doll-0.043
Token fallen
Token ID9292
Feature activation+1.61e+00

Pos logit contributions
 habitat+0.023
 exp+0.021
 oceans+0.021
 glory+0.021
 horizon+0.020
Neg logit contributions
 yes-0.015
ggy-0.015
ver-0.014
ggie-0.014
 doll-0.013
Token into
Token ID656
Feature activation+2.16e+00

Pos logit contributions
 habitat+0.043
 exp+0.039
 glory+0.038
 habitats+0.038
 sav+0.038
Neg logit contributions
 yes-0.031
ggy-0.031
 doll-0.029
ver-0.028
ggie-0.028
Token the
Token ID262
Feature activation+3.94e+00

Pos logit contributions
 habitat+0.059
 exp+0.054
 horizon+0.052
 glory+0.052
 sav+0.051
Neg logit contributions
ggy-0.042
 yes-0.042
ggie-0.039
ver-0.038
 doll-0.038
Token deep
Token ID2769
Feature activation+6.73e+00

Pos logit contributions
 habitat+0.078
 exp+0.069
 habitats+0.067
iling+0.065
joy+0.065
Neg logit contributions
ggy-0.097
 doll-0.096
 yes-0.094
 mom-0.091
ggie-0.089
Token hole
Token ID7604
Feature activation+1.05e+00

Pos logit contributions
 habitat+0.139
 habitats+0.137
joy+0.134
Now+0.133
brance+0.133
Neg logit contributions
 doll-0.130
 mom-0.121
 friend-0.120
 bear-0.115
 shield-0.112
Token.
Token ID13
Feature activation+1.04e+00

Pos logit contributions
 habitat+0.025
 exp+0.022
 oceans+0.021
 glory+0.021
 horizon+0.021
Neg logit contributions
 yes-0.025
ggy-0.025
ver-0.023
ggie-0.023
 doll-0.022
Token They
Token ID1119
Feature activation-4.06e-01

Pos logit contributions
 habitat+0.028
 oceans+0.026
ky+0.026
 exp+0.026
 glory+0.026
Neg logit contributions
 yes-0.021
ver-0.020
ggy-0.020
ggie-0.019
 mom-0.018
Token were
Token ID547
Feature activation+2.15e-01

Pos logit contributions
ggy+0.009
ggie+0.008
 yes+0.008
ver+0.008
 doll+0.008
Neg logit contributions
 habitat-0.010
 exp-0.009
 sav-0.009
 oceans-0.009
 glory-0.009
Token heart
Token ID2612
Feature activation+1.05e+00

Pos logit contributions
 habitat+0.006
 oceans+0.005
 sav+0.005
 glory+0.005
 horizon+0.005
Neg logit contributions
 yes-0.004
ggy-0.004
ver-0.004
ggie-0.004
 doll-0.004
Token and
Token ID290
Feature activation-2.02e-02

Pos logit contributions
 habitat+0.020
 exp+0.018
 oceans+0.018
 habitats+0.018
 glory+0.018
Neg logit contributions
 yes-0.023
ggy-0.021
ver-0.021
ggie-0.020
 doll-0.020
Token decided
Token ID3066
Feature activation-4.70e-02

Pos logit contributions
ggy+0.000
 yes+0.000
ver+0.000
ggie+0.000
 doll+0.000
Neg logit contributions
 habitat-0.001
 exp-0.000
 sav-0.000
 glory-0.000
 oceans-0.000
Token to
Token ID284
Feature activation-1.70e+00

Pos logit contributions
ggy+0.001
ver+0.001
 yes+0.001
ggie+0.001
 doll+0.001
Neg logit contributions
 habitat-0.001
 exp-0.001
 sav-0.001
 oceans-0.001
 glory-0.001
Token give
Token ID1577
Feature activation-2.34e+00

Pos logit contributions
ver+0.034
ggy+0.034
 yes+0.034
ggie+0.032
balls+0.029
Neg logit contributions
 habitat-0.044
 sav-0.042
 exp-0.042
 glory-0.039
 waters-0.039
Token the
Token ID262
Feature activation-1.48e+00

Pos logit contributions
ggy+0.070
ver+0.068
ggie+0.067
 yes+0.067
keys+0.063
Neg logit contributions
 air-0.035
ky-0.033
 hills-0.033
 oceans-0.033
 Now-0.033
Token hat
Token ID6877
Feature activation-7.43e+00

Pos logit contributions
ggy+0.023
ver+0.023
 yes+0.022
ggie+0.022
 doll+0.018
Neg logit contributions
 habitat-0.045
 exp-0.043
 oceans-0.042
 sav-0.042
 glory-0.042
Token to
Token ID284
Feature activation-1.64e+00

Pos logit contributions
ggy+0.220
ggie+0.213
ver+0.204
keys+0.191
 yes+0.187
Neg logit contributions
 habitat-0.111
 than-0.107
 exp-0.097
 air-0.096
 oceans-0.095
Token Sarah
Token ID10490
Feature activation-3.95e+00

Pos logit contributions
ggy+0.038
ver+0.038
ggie+0.036
ery+0.034
balls+0.034
Neg logit contributions
 habitat-0.034
 sav-0.033
 glory-0.033
 exp-0.032
ky-0.031
Token as
Token ID355
Feature activation-5.89e-01

Pos logit contributions
ggy+0.112
 yes+0.108
ggie+0.106
ver+0.105
balls+0.095
Neg logit contributions
 habitat-0.073
 exp-0.065
ky-0.064
 sav-0.063
 glory-0.062
Token a
Token ID257
Feature activation-2.52e+00

Pos logit contributions
ggy+0.012
ver+0.011
 yes+0.011
man+0.011
ggie+0.011
Neg logit contributions
 habitat-0.013
joy-0.012
 oceans-0.012
 habitats-0.012
 exp-0.012
Token gift
Token ID6979
Feature activation-3.01e+00

Pos logit contributions
ver+0.060
ggy+0.053
bled+0.052
ggie+0.051
aches+0.050
Neg logit contributions
 sav-0.056
 exp-0.054
 habitat-0.054
joy-0.053
 glory-0.049
Token are
Token ID389
Feature activation-9.50e-01

Pos logit contributions
ggy+0.001
 yes+0.001
ggie+0.001
ver+0.001
 doll+0.001
Neg logit contributions
 habitat-0.002
 exp-0.002
 sav-0.002
 glory-0.002
 habitats-0.002
Token sorry
Token ID7926
Feature activation-1.01e+00

Pos logit contributions
ver+0.020
 yes+0.019
ggy+0.018
ggie+0.018
ves+0.016
Neg logit contributions
 habitat-0.023
 sav-0.022
 ago-0.021
 than-0.021
 oceans-0.021
Token and
Token ID290
Feature activation-1.28e+00

Pos logit contributions
 yes+0.024
ggy+0.024
ver+0.023
ggie+0.023
 doll+0.022
Neg logit contributions
 habitat-0.024
 exp-0.021
 oceans-0.021
 glory-0.021
 horizon-0.020
Token give
Token ID1577
Feature activation-2.31e+00

Pos logit contributions
ggy+0.025
 yes+0.025
ggie+0.024
ver+0.024
 doll+0.021
Neg logit contributions
 habitat-0.035
 exp-0.032
 sav-0.031
 oceans-0.031
 glory-0.030
Token the
Token ID262
Feature activation-1.32e+00

Pos logit contributions
ver+0.061
 yes+0.060
ggy+0.058
ggie+0.055
isy+0.053
Neg logit contributions
 habitat-0.047
 air-0.043
 sav-0.043
 oceans-0.042
ky-0.040
Token hat
Token ID6877
Feature activation-7.39e+00

Pos logit contributions
ggy+0.026
ver+0.025
 yes+0.025
ggie+0.024
 doll+0.021
Neg logit contributions
 habitat-0.036
 exp-0.033
 oceans-0.033
 sav-0.033
 horizon-0.032
Token back
Token ID736
Feature activation-2.06e+00

Pos logit contributions
ggie+0.199
ggy+0.198
ver+0.189
 yes+0.176
isy+0.175
Neg logit contributions
 habitat-0.126
 than-0.122
 air-0.106
 waters-0.106
 exp-0.104
Token to
Token ID284
Feature activation-8.48e-01

Pos logit contributions
 yes+0.053
ggy+0.053
ggie+0.051
ver+0.051
 doll+0.047
Neg logit contributions
 habitat-0.044
 exp-0.037
 oceans-0.037
 glory-0.037
 habitats-0.036
Token the
Token ID262
Feature activation+1.39e+00

Pos logit contributions
ggy+0.017
 yes+0.017
ver+0.016
ggie+0.016
 doll+0.015
Neg logit contributions
 habitat-0.023
 exp-0.020
 sav-0.020
 oceans-0.020
 glory-0.020
Token bald
Token ID28273
Feature activation+1.32e+00

Pos logit contributions
 habitat+0.037
 exp+0.033
 oceans+0.033
 horizon+0.033
 sav+0.032
Neg logit contributions
 yes-0.029
ggy-0.029
ver-0.028
ggie-0.027
 doll-0.025
Token man
Token ID582
Feature activation-1.90e+00

Pos logit contributions
 habitat+0.042
 exp+0.039
 oceans+0.039
 glory+0.038
 horizon+0.037
Neg logit contributions
ggy-0.021
 yes-0.020
 doll-0.018
ggie-0.018
ver-0.017
Token
Token ID198
Feature activation-1.87e+00

Pos logit contributions
 yes+0.013
ggy+0.013
ver+0.012
ggie+0.012
 doll+0.012
Neg logit contributions
 habitat-0.015
 exp-0.013
 glory-0.013
 oceans-0.013
ky-0.013
Token
Token ID198
Feature activation-1.62e+00

Pos logit contributions
 yes+0.053
ggy+0.050
ver+0.050
ggie+0.049
 doll+0.046
Neg logit contributions
 habitat-0.036
 exp-0.030
 sav-0.030
 oceans-0.030
 horizon-0.029
TokenThey
Token ID2990
Feature activation-6.11e-01

Pos logit contributions
 yes+0.037
ggy+0.035
ver+0.035
ggie+0.034
 doll+0.032
Neg logit contributions
 habitat-0.040
 exp-0.036
 sav-0.036
 oceans-0.035
 glory-0.035
Token gave
Token ID2921
Feature activation-3.17e+00

Pos logit contributions
ggy+0.014
ggie+0.013
ver+0.013
 yes+0.013
balls+0.012
Neg logit contributions
 habitat-0.014
 sav-0.014
 exp-0.013
ky-0.013
 waters-0.012
Token the
Token ID262
Feature activation-2.52e+00

Pos logit contributions
ggy+0.092
ver+0.090
 yes+0.089
ggie+0.086
cher+0.083
Neg logit contributions
 habitat-0.060
 oceans-0.054
 air-0.053
 sav-0.053
 hills-0.051
Token hat
Token ID6877
Feature activation-7.31e+00

Pos logit contributions
ver+0.054
ggy+0.052
ggie+0.052
 yes+0.048
gh+0.043
Neg logit contributions
 habitat-0.066
 hills-0.059
 air-0.058
 exp-0.058
 horizon-0.058
Token back
Token ID736
Feature activation-1.71e+00

Pos logit contributions
ggy+0.215
ggie+0.215
ver+0.205
 yes+0.194
cher+0.189
Neg logit contributions
 habitat-0.113
 than-0.103
 air-0.097
 waters-0.097
 hills-0.092
Token to
Token ID284
Feature activation-1.63e+00

Pos logit contributions
 yes+0.043
ggy+0.043
ggie+0.041
ver+0.041
 doll+0.038
Neg logit contributions
 habitat-0.038
 exp-0.033
 oceans-0.033
 glory-0.032
 habitats-0.032
Token Mama
Token ID40084
Feature activation-2.43e+00

Pos logit contributions
ggy+0.038
 yes+0.037
ver+0.037
ggie+0.036
cher+0.032
Neg logit contributions
 habitat-0.037
 sav-0.035
 exp-0.034
 oceans-0.033
 horizon-0.033
Token Bird
Token ID14506
Feature activation-3.12e+00

Pos logit contributions
ggy+0.088
ggie+0.086
ver+0.084
 yes+0.084
gh+0.079
Neg logit contributions
 habitat-0.024
ky-0.020
 exp-0.020
 waters-0.019
 oceans-0.019
Token and
Token ID290
Feature activation-1.62e+00

Pos logit contributions
ggy+0.104
ggie+0.100
 yes+0.099
ver+0.098
cher+0.091
Neg logit contributions
 habitat-0.043
ky-0.037
 exp-0.034
 oceans-0.034
 than-0.033
Token,
Token ID11
Feature activation+1.45e+00

Pos logit contributions
 habitat+0.028
 exp+0.024
 oceans+0.024
 horizon+0.023
 glory+0.023
Neg logit contributions
ggy-0.038
 yes-0.038
ggie-0.037
ver-0.036
 doll-0.034
Token but
Token ID475
Feature activation-5.60e-01

Pos logit contributions
 habitat+0.039
 exp+0.035
 glory+0.034
 habitats+0.034
 oceans+0.034
Neg logit contributions
 yes-0.032
ggy-0.029
ver-0.028
ggie-0.027
 doll-0.027
Token reluctantly
Token ID35462
Feature activation+1.67e-01

Pos logit contributions
ggy+0.012
ggie+0.011
 yes+0.011
 doll+0.010
ver+0.010
Neg logit contributions
 habitat-0.013
 sav-0.013
 oceans-0.013
 horizon-0.013
 exp-0.013
Token gave
Token ID2921
Feature activation-1.81e+00

Pos logit contributions
 habitat+0.005
 oceans+0.004
 exp+0.004
 horizon+0.004
 habitats+0.004
Neg logit contributions
 yes-0.003
ggy-0.003
ver-0.003
ggie-0.003
 doll-0.003
Token the
Token ID262
Feature activation-1.65e+00

Pos logit contributions
ggy+0.050
 yes+0.049
ggie+0.046
ver+0.045
tr+0.044
Neg logit contributions
 oceans-0.034
 habitat-0.033
ky-0.032
 exp-0.032
 sav-0.031
Token hat
Token ID6877
Feature activation-7.29e+00

Pos logit contributions
ggy+0.030
ver+0.029
 yes+0.029
ggie+0.029
 nobody+0.024
Neg logit contributions
 habitat-0.045
 exp-0.043
 sav-0.042
 oceans-0.042
 glory-0.041
Token back
Token ID736
Feature activation-8.68e-01

Pos logit contributions
ggy+0.199
ggie+0.194
keys+0.190
ver+0.183
isy+0.179
Neg logit contributions
 than-0.115
 habitat-0.114
 air-0.104
 waters-0.095
joy-0.095
Token to
Token ID284
Feature activation-5.59e-01

Pos logit contributions
ggy+0.022
 yes+0.022
ggie+0.021
ver+0.021
 doll+0.020
Neg logit contributions
 habitat-0.019
 exp-0.016
 glory-0.016
 oceans-0.016
 sav-0.016
Token the
Token ID262
Feature activation+4.38e-01

Pos logit contributions
ggy+0.013
 yes+0.012
ggie+0.012
ver+0.012
 doll+0.011
Neg logit contributions
 habitat-0.014
 exp-0.012
 oceans-0.012
 horizon-0.012
 glory-0.012
Token man
Token ID582
Feature activation-2.09e+00

Pos logit contributions
 habitat+0.012
 exp+0.011
 oceans+0.011
 horizon+0.011
 sav+0.011
Neg logit contributions
 yes-0.008
ggy-0.008
ver-0.008
ggie-0.008
 doll-0.007
Token.
Token ID13
Feature activation+3.11e-01

Pos logit contributions
ggy+0.063
 yes+0.061
ggie+0.061
ver+0.061
Over+0.057
Neg logit contributions
 habitat-0.031
 sav-0.026
ky-0.025
 ago-0.025
 exp-0.024
Token laughs
Token ID22051
Feature activation+1.16e+00

Pos logit contributions
 habitat+0.040
 glory+0.035
 horizon+0.034
 oceans+0.034
 exp+0.034
Neg logit contributions
 yes-0.043
ggy-0.042
 doll-0.040
ver-0.040
ggie-0.040
Token.
Token ID13
Feature activation-5.26e-01

Pos logit contributions
 habitat+0.029
 glory+0.025
 exp+0.025
 habitats+0.025
 horizon+0.025
Neg logit contributions
 yes-0.028
ggy-0.026
ver-0.025
ggie-0.025
 doll-0.025
Token She
Token ID1375
Feature activation+2.16e+00

Pos logit contributions
 yes+0.010
ggy+0.010
ver+0.010
ggie+0.009
 doll+0.009
Neg logit contributions
 habitat-0.015
 glory-0.013
 exp-0.013
 oceans-0.013
 horizon-0.013
Token gives
Token ID3607
Feature activation-2.12e+00

Pos logit contributions
 habitat+0.049
 horizon+0.043
 oceans+0.043
 glory+0.043
 exp+0.042
Neg logit contributions
 yes-0.054
ggy-0.053
 doll-0.051
ggie-0.050
ver-0.050
Token the
Token ID262
Feature activation-1.14e+00

Pos logit contributions
ggy+0.060
ver+0.059
 yes+0.058
ggie+0.057
keys+0.055
Neg logit contributions
 oceans-0.037
 air-0.037
ky-0.036
 hills-0.035
 habitat-0.034
Token hat
Token ID6877
Feature activation-7.21e+00

Pos logit contributions
ver+0.021
ggy+0.020
ggie+0.019
 yes+0.018
 nobody+0.016
Neg logit contributions
 habitat-0.032
 exp-0.031
 oceans-0.031
 sav-0.030
 glory-0.030
Token back
Token ID736
Feature activation-1.38e+00

Pos logit contributions
ggy+0.216
ggie+0.214
ver+0.210
keys+0.199
cher+0.194
Neg logit contributions
 than-0.101
 habitat-0.089
 air-0.087
 sav-0.079
ky-0.077
Token to
Token ID284
Feature activation-7.84e-01

Pos logit contributions
 yes+0.032
ggy+0.031
ver+0.030
ggie+0.030
 doll+0.028
Neg logit contributions
 habitat-0.034
 exp-0.030
 oceans-0.029
 glory-0.029
 horizon-0.029
Token Sam
Token ID3409
Feature activation-2.30e+00

Pos logit contributions
ggy+0.019
ver+0.019
 yes+0.019
ggie+0.018
cher+0.017
Neg logit contributions
 habitat-0.016
 sav-0.015
ky-0.014
 horizon-0.014
 exp-0.014
Token.
Token ID13
Feature activation-1.32e-01

Pos logit contributions
 yes+0.058
ggy+0.058
ver+0.055
ggie+0.055
 doll+0.052
Neg logit contributions
 habitat-0.050
 exp-0.044
 oceans-0.043
 glory-0.043
 sav-0.043
Token "
Token ID366
Feature activation+1.23e-01

Pos logit contributions
 yes+0.003
ggy+0.003
ver+0.003
ggie+0.003
 doll+0.003
Neg logit contributions
 habitat-0.003
 glory-0.003
 exp-0.003
 oceans-0.003
 horizon-0.003
Token.
Token ID13
Feature activation-1.15e+00

Pos logit contributions
ggy+0.087
ggie+0.085
 yes+0.082
ver+0.082
aches+0.077
Neg logit contributions
 habitat-0.041
joy-0.038
 exp-0.038
ky-0.037
 oceans-0.036
Token She
Token ID1375
Feature activation+8.68e-01

Pos logit contributions
 yes+0.023
ggy+0.022
 doll+0.021
ver+0.021
 mom+0.021
Neg logit contributions
 habitat-0.034
 glory-0.030
 exp-0.030
 oceans-0.029
 habitats-0.029
Token gives
Token ID3607
Feature activation-2.54e+00

Pos logit contributions
 habitat+0.019
 glory+0.017
 exp+0.017
 oceans+0.017
 horizon+0.017
Neg logit contributions
 yes-0.022
ggy-0.022
ver-0.020
 doll-0.020
ggie-0.020
Token him
Token ID683
Feature activation-6.07e+00

Pos logit contributions
ggy+0.078
ver+0.075
 yes+0.075
ggie+0.074
keys+0.069
Neg logit contributions
 air-0.041
 oceans-0.039
 sav-0.038
 hills-0.037
ky-0.036
Token the
Token ID262
Feature activation-1.84e+00

Pos logit contributions
ggy+0.171
ggie+0.164
ver+0.164
 yes+0.161
cher+0.147
Neg logit contributions
 habitat-0.107
 oceans-0.100
 exp-0.099
 sav-0.098
 waters-0.097
Token cap
Token ID1451
Feature activation-7.20e+00

Pos logit contributions
ggy+0.041
ver+0.041
ggie+0.040
 yes+0.036
keys+0.034
Neg logit contributions
 habitat-0.044
 sav-0.042
 air-0.041
 exp-0.041
 glory-0.040
Token.
Token ID13
Feature activation-7.44e-01

Pos logit contributions
ggy+0.218
ggie+0.218
ver+0.206
 yes+0.201
keys+0.198
Neg logit contributions
 than-0.096
 habitat-0.081
 air-0.080
elly-0.076
 waters-0.075
Token
Token ID198
Feature activation-6.15e-01

Pos logit contributions
 yes+0.016
ggy+0.015
ver+0.015
 doll+0.014
 mom+0.014
Neg logit contributions
 habitat-0.021
 glory-0.018
 exp-0.018
 oceans-0.018
 horizon-0.018
Token
Token ID198
Feature activation-4.70e-01

Pos logit contributions
ggy+0.014
 yes+0.013
ver+0.013
ggie+0.013
 doll+0.012
Neg logit contributions
 habitat-0.016
 exp-0.014
 glory-0.014
 oceans-0.014
 horizon-0.014
TokenTom
Token ID13787
Feature activation+2.98e-01

Pos logit contributions
ggy+0.008
ggie+0.007
 yes+0.007
 doll+0.006
ver+0.006
Neg logit contributions
 habitat-0.016
 glory-0.014
 exp-0.014
 horizon-0.014
 habitats-0.014
Token takes
Token ID2753
Feature activation-1.64e+00

Pos logit contributions
 habitat+0.007
 glory+0.006
 horizon+0.006
 oceans+0.006
 exp+0.006
Neg logit contributions
 yes-0.007
ggy-0.007
 doll-0.007
ver-0.007
ggie-0.007
Token felt
Token ID2936
Feature activation-2.00e-01

Pos logit contributions
 habitat+0.007
 oceans+0.006
 glory+0.006
 horizon+0.006
 exp+0.006
Neg logit contributions
 yes-0.004
ggy-0.004
ggie-0.004
ver-0.004
 doll-0.004
Token ashamed
Token ID22461
Feature activation+5.33e-01

Pos logit contributions
ggy+0.003
 yes+0.003
ver+0.003
ggie+0.003
 doll+0.003
Neg logit contributions
 habitat-0.006
 sav-0.005
 exp-0.005
 glory-0.005
 horizon-0.005
Token and
Token ID290
Feature activation-7.31e-01

Pos logit contributions
 habitat+0.011
 exp+0.010
 oceans+0.010
 glory+0.010
 horizon+0.009
Neg logit contributions
 yes-0.014
ggy-0.014
ver-0.013
ggie-0.013
 doll-0.013
Token gave
Token ID2921
Feature activation-3.07e+00

Pos logit contributions
ggy+0.016
ver+0.016
ggie+0.016
 yes+0.015
 doll+0.014
Neg logit contributions
 habitat-0.017
 sav-0.016
 exp-0.016
 glory-0.015
 air-0.015
Token the
Token ID262
Feature activation-2.21e+00

Pos logit contributions
ggy+0.095
keys+0.090
ggie+0.089
 yes+0.087
ver+0.086
Neg logit contributions
 air-0.049
ky-0.045
 oceans-0.042
 sav-0.042
 habitat-0.042
Token doll
Token ID3654
Feature activation-7.18e+00

Pos logit contributions
ver+0.053
ggy+0.051
ggie+0.050
 yes+0.044
gh+0.044
Neg logit contributions
 habitat-0.047
 air-0.047
 horizon-0.046
 exp-0.046
joy-0.045
Token back
Token ID736
Feature activation-1.80e+00

Pos logit contributions
ggy+0.188
ver+0.187
ggie+0.183
 yes+0.175
ves+0.171
Neg logit contributions
 habitat-0.136
 than-0.117
ky-0.114
 air-0.112
joy-0.112
Token.
Token ID13
Feature activation+1.66e-01

Pos logit contributions
 yes+0.046
ggy+0.046
ggie+0.044
ver+0.044
 doll+0.040
Neg logit contributions
 habitat-0.039
 exp-0.033
 glory-0.033
 oceans-0.032
 sav-0.032
Token
Token ID198
Feature activation-4.01e-01

Pos logit contributions
 habitat+0.004
 oceans+0.004
 glory+0.004
 horizon+0.004
 exp+0.004
Neg logit contributions
 yes-0.004
ggy-0.004
ver-0.003
 doll-0.003
 mom-0.003
Token
Token ID198
Feature activation-1.65e-01

Pos logit contributions
 yes+0.010
ggy+0.010
ver+0.010
ggie+0.010
 doll+0.009
Neg logit contributions
 habitat-0.008
 exp-0.007
 oceans-0.007
 sav-0.007
 glory-0.007
TokenWhen
Token ID2215
Feature activation-2.27e+00

Pos logit contributions
 yes+0.003
ggy+0.003
ver+0.003
ggie+0.003
 doll+0.003
Neg logit contributions
 habitat-0.004
 exp-0.004
 oceans-0.004
 glory-0.004
 sav-0.004
Token the
Token ID262
Feature activation+8.15e-01

Pos logit contributions
 habitat+0.006
 habitats+0.005
 exp+0.005
 glory+0.005
 oceans+0.005
Neg logit contributions
 yes-0.004
ggy-0.004
ver-0.003
ggie-0.003
 doll-0.003
Token swing
Token ID9628
Feature activation-1.91e+00

Pos logit contributions
 habitat+0.023
 horizon+0.021
 sav+0.021
 exp+0.021
 glory+0.021
Neg logit contributions
ver-0.015
ggy-0.015
 yes-0.015
ggie-0.014
cher-0.012
Token and
Token ID290
Feature activation+5.75e-02

Pos logit contributions
 yes+0.051
ggy+0.051
ver+0.049
ggie+0.049
 doll+0.046
Neg logit contributions
 habitat-0.038
 exp-0.033
 oceans-0.033
 glory-0.032
 horizon-0.032
Token gave
Token ID2921
Feature activation-2.36e+00

Pos logit contributions
 habitat+0.001
 sav+0.001
 exp+0.001
 oceans+0.001
 glory+0.001
Neg logit contributions
ggy-0.001
 yes-0.001
ver-0.001
ggie-0.001
 okay-0.001
Token his
Token ID465
Feature activation-3.54e+00

Pos logit contributions
ver+0.057
ggy+0.056
 yes+0.055
keys+0.053
tr+0.052
Neg logit contributions
 habitat-0.050
 sav-0.048
 glory-0.047
 oceans-0.047
joy-0.046
Token doll
Token ID3654
Feature activation-7.18e+00

Pos logit contributions
ver+0.064
ggy+0.061
ggie+0.060
 yes+0.054
keys+0.050
Neg logit contributions
 habitat-0.099
 exp-0.095
joy-0.095
 glory-0.092
 sav-0.092
Token a
Token ID257
Feature activation-3.01e+00

Pos logit contributions
ver+0.161
ggy+0.154
 yes+0.147
ggie+0.146
keys+0.135
Neg logit contributions
 habitat-0.170
 oceans-0.153
joy-0.152
 exp-0.152
ky-0.151
Token big
Token ID1263
Feature activation-2.13e+00

Pos logit contributions
ggy+0.067
ver+0.065
ggie+0.064
keys+0.060
aches+0.060
Neg logit contributions
 exp-0.064
 sav-0.062
joy-0.060
 habitat-0.059
 air-0.058
Token hug
Token ID16225
Feature activation-1.44e+00

Pos logit contributions
 yes+0.037
ggy+0.035
ver+0.033
ggie+0.032
 doll+0.031
Neg logit contributions
 habitat-0.065
 exp-0.058
 oceans-0.058
 glory-0.058
 horizon-0.057
Token.
Token ID13
Feature activation+3.95e-02

Pos logit contributions
ggy+0.038
 yes+0.037
ver+0.036
ggie+0.036
 doll+0.034
Neg logit contributions
 habitat-0.028
 exp-0.025
 glory-0.024
 horizon-0.024
ky-0.024
Token He
Token ID679
Feature activation+5.34e-01

Pos logit contributions
 habitat+0.001
 exp+0.001
 oceans+0.001
 glory+0.001
 horizon+0.001
Neg logit contributions
 yes-0.001
ggy-0.001
ver-0.001
ggie-0.001
 doll-0.001
Token nods
Token ID34833
Feature activation+1.04e+00

Pos logit contributions
 habitat+0.036
 glory+0.033
 horizon+0.031
 habitats+0.031
 oceans+0.031
Neg logit contributions
 doll-0.032
 yes-0.032
ggy-0.030
ver-0.029
 mom-0.029
Token.
Token ID13
Feature activation+3.59e-03

Pos logit contributions
 habitat+0.027
 glory+0.024
 horizon+0.024
 exp+0.024
 oceans+0.023
Neg logit contributions
 yes-0.024
ggy-0.022
ggie-0.021
 doll-0.021
ver-0.021
Token She
Token ID1375
Feature activation+1.67e+00

Pos logit contributions
 habitat+0.000
 glory+0.000
ky+0.000
 oceans+0.000
iling+0.000
Neg logit contributions
 yes-0.000
 mom-0.000
ver-0.000
 doll-0.000
ggy-0.000
Token gives
Token ID3607
Feature activation-1.57e+00

Pos logit contributions
 habitat+0.040
 glory+0.034
 oceans+0.034
 horizon+0.034
 exp+0.033
Neg logit contributions
 yes-0.041
ggy-0.039
 doll-0.039
ver-0.037
ggie-0.037
Token the
Token ID262
Feature activation-1.81e+00

Pos logit contributions
ggy+0.041
 yes+0.039
ver+0.039
ggie+0.038
cher+0.034
Neg logit contributions
 habitat-0.033
 oceans-0.031
 sav-0.031
 exp-0.030
ky-0.029
Token hat
Token ID6877
Feature activation-7.11e+00

Pos logit contributions
ver+0.030
ggy+0.030
ggie+0.028
 yes+0.028
 okay+0.023
Neg logit contributions
 habitat-0.053
 exp-0.051
 oceans-0.050
 horizon-0.049
 glory-0.049
Token to
Token ID284
Feature activation-1.83e+00

Pos logit contributions
ggy+0.203
ggie+0.199
ver+0.194
keys+0.183
cher+0.178
Neg logit contributions
 than-0.112
 habitat-0.108
 air-0.101
 waters-0.100
 exp-0.096
Token Ben
Token ID3932
Feature activation-2.91e+00

Pos logit contributions
ggy+0.047
ver+0.047
 yes+0.046
ggie+0.045
cher+0.041
Neg logit contributions
 habitat-0.037
 sav-0.035
 exp-0.033
 horizon-0.032
 oceans-0.032
Token.
Token ID13
Feature activation-1.68e-01

Pos logit contributions
ggy+0.078
 yes+0.077
ggie+0.075
ver+0.075
 doll+0.068
Neg logit contributions
 habitat-0.057
 exp-0.050
 sav-0.049
ky-0.049
 oceans-0.048
Token He
Token ID679
Feature activation+9.25e-01

Pos logit contributions
 yes+0.004
ver+0.003
 mom+0.003
ggy+0.003
 doll+0.003
Neg logit contributions
 habitat-0.005
 glory-0.004
iling-0.004
 horizon-0.004
ky-0.004
Token puts
Token ID7584
Feature activation-1.25e+00

Pos logit contributions
 habitat+0.020
 exp+0.017
 oceans+0.017
 glory+0.017
 horizon+0.017
Neg logit contributions
 yes-0.025
ggy-0.024
ver-0.023
ggie-0.023
 doll-0.022
Token
Token ID198
Feature activation-8.23e-01

Pos logit contributions
 habitat+0.003
 glory+0.003
 exp+0.003
 oceans+0.003
 horizon+0.003
Neg logit contributions
 yes-0.003
ggy-0.003
ver-0.003
ggie-0.003
 doll-0.003
Token
Token ID198
Feature activation-5.65e-01

Pos logit contributions
 yes+0.021
ggy+0.021
ver+0.020
ggie+0.020
 doll+0.019
Neg logit contributions
 habitat-0.018
 exp-0.016
 oceans-0.015
 glory-0.015
 sav-0.015
TokenShe
Token ID3347
Feature activation+6.47e-01

Pos logit contributions
ggy+0.012
 yes+0.012
ggie+0.011
ver+0.011
 doll+0.010
Neg logit contributions
 habitat-0.015
 exp-0.014
 oceans-0.013
 glory-0.013
 horizon-0.013
Token gave
Token ID2921
Feature activation-2.68e+00

Pos logit contributions
 habitat+0.018
 exp+0.016
 sav+0.016
 oceans+0.016
 glory+0.016
Neg logit contributions
ggy-0.012
 yes-0.012
ggie-0.012
ver-0.012
 doll-0.011
Token the
Token ID262
Feature activation-2.01e+00

Pos logit contributions
ggy+0.081
ver+0.081
 yes+0.077
ggie+0.076
keys+0.076
Neg logit contributions
 air-0.042
ky-0.040
 oceans-0.040
 sav-0.039
 hills-0.039
Token scarf
Token ID36953
Feature activation-7.09e+00

Pos logit contributions
ver+0.034
ggy+0.032
ggie+0.031
 yes+0.028
keys+0.025
Neg logit contributions
 air-0.056
 habitat-0.055
 sav-0.055
 oceans-0.055
 glory-0.054
Token to
Token ID284
Feature activation-2.67e+00

Pos logit contributions
ggy+0.216
ggie+0.213
ver+0.204
keys+0.193
cher+0.189
Neg logit contributions
 air-0.093
 than-0.089
 waters-0.086
 habitat-0.083
 hills-0.082
Token Tom
Token ID4186
Feature activation-3.00e+00

Pos logit contributions
ver+0.075
ggy+0.071
ery+0.069
ggie+0.068
cher+0.067
Neg logit contributions
 sav-0.047
 habitat-0.040
ky-0.040
 air-0.039
 horizon-0.038
Token the
Token ID262
Feature activation-5.07e-01

Pos logit contributions
ggy+0.095
ggie+0.092
 yes+0.092
ver+0.089
 nobody+0.083
Neg logit contributions
 habitat-0.042
ky-0.038
 exp-0.037
 sav-0.036
 glory-0.034
Token next
Token ID1306
Feature activation+1.38e+00

Pos logit contributions
ver+0.011
ggy+0.010
ggie+0.010
 yes+0.009
aches+0.008
Neg logit contributions
 habitat-0.013
 sav-0.013
 oceans-0.012
 horizon-0.012
 exp-0.012
Token day
Token ID1110
Feature activation+2.26e+00

Pos logit contributions
 habitat+0.035
 exp+0.031
 glory+0.030
 oceans+0.030
 horizon+0.030
Neg logit contributions
 yes-0.031
ggy-0.031
ggie-0.029
 doll-0.028
ver-0.028
Token asked
Token ID1965
Feature activation-1.22e+00

Pos logit contributions
 habitat+0.019
 sav+0.018
 exp+0.017
 oceans+0.016
 air+0.016
Neg logit contributions
ver-0.020
ggy-0.019
 yes-0.019
ggie-0.019
 doll-0.017
Token Tom
Token ID4186
Feature activation-4.04e+00

Pos logit contributions
ggy+0.033
ggie+0.031
ver+0.031
cher+0.030
tr+0.030
Neg logit contributions
joy-0.020
 habitat-0.019
 hills-0.019
 than-0.019
 oceans-0.019
Token to
Token ID284
Feature activation-2.03e+00

Pos logit contributions
ggy+0.129
ggie+0.129
kin+0.122
ves+0.121
fs+0.121
Neg logit contributions
joy-0.040
 than-0.039
 habitat-0.037
 wonders-0.036
 ago-0.035
Token give
Token ID1577
Feature activation-2.78e+00

Pos logit contributions
ver+0.043
ves+0.042
ggy+0.041
balls+0.041
ery+0.040
Neg logit contributions
 sav-0.046
 habitat-0.044
 exp-0.043
 waters-0.039
 glory-0.038
Token her
Token ID607
Feature activation-4.41e+00

Pos logit contributions
ver+0.076
tr+0.073
ggy+0.073
 yes+0.072
keys+0.070
Neg logit contributions
 sav-0.046
 air-0.045
 oceans-0.044
 hills-0.043
ky-0.042
Token lamp
Token ID20450
Feature activation-7.04e+00

Pos logit contributions
ggy+0.107
ggie+0.103
 yes+0.098
ver+0.096
keys+0.093
Neg logit contributions
 air-0.091
 oceans-0.086
 habitat-0.085
 exp-0.085
 glory-0.084
Token back
Token ID736
Feature activation-1.66e+00

Pos logit contributions
ggy+0.196
ggie+0.191
keys+0.188
ver+0.186
ves+0.181
Neg logit contributions
 than-0.099
 habitat-0.097
 air-0.093
ky-0.092
 waters-0.084
Token.
Token ID13
Feature activation+6.40e-01

Pos logit contributions
ggy+0.049
 yes+0.049
ggie+0.047
ver+0.046
balls+0.043
Neg logit contributions
 habitat-0.027
 than-0.023
 glory-0.023
ky-0.022
 sav-0.022
Token
Token ID198
Feature activation+2.62e-02

Pos logit contributions
 habitat+0.021
 glory+0.020
 oceans+0.019
 horizon+0.019
 exp+0.019
Neg logit contributions
ggy-0.010
 yes-0.010
ggie-0.009
ver-0.009
 doll-0.009
Token
Token ID198
Feature activation+3.47e-01

Pos logit contributions
 habitat+0.001
 exp+0.001
 oceans+0.000
 glory+0.000
 horizon+0.000
Neg logit contributions
 yes-0.001
ggy-0.001
ver-0.001
ggie-0.001
 doll-0.001
TokenTom
Token ID13787
Feature activation-3.94e-02

Pos logit contributions
 habitat+0.010
 exp+0.009
 oceans+0.009
 glory+0.009
 horizon+0.009
Neg logit contributions
ggy-0.007
 yes-0.006
ggie-0.006
ver-0.006
 doll-0.006
Token and
Token ID290
Feature activation-2.29e-02

Pos logit contributions
 habitat+0.059
 exp+0.053
 glory+0.052
 oceans+0.052
 horizon+0.051
Neg logit contributions
 yes-0.043
ggy-0.042
ggie-0.040
ver-0.039
 doll-0.037
Token he
Token ID339
Feature activation-6.30e-02

Pos logit contributions
ver+0.000
ggy+0.000
 yes+0.000
ggie+0.000
 doll+0.000
Neg logit contributions
 habitat-0.001
 sav-0.001
 exp-0.001
 glory-0.001
 horizon-0.001
Token quickly
Token ID2952
Feature activation+3.91e-01

Pos logit contributions
 yes+0.001
ggy+0.001
ver+0.001
ggie+0.001
 doll+0.001
Neg logit contributions
 habitat-0.002
 sav-0.001
 exp-0.001
 glory-0.001
 oceans-0.001
Token handed
Token ID10158
Feature activation-3.50e+00

Pos logit contributions
 habitat+0.011
 oceans+0.010
 horizon+0.010
 exp+0.010
 glory+0.010
Neg logit contributions
 yes-0.007
ggy-0.007
ggie-0.007
ver-0.006
 doll-0.006
Token the
Token ID262
Feature activation-2.39e+00

Pos logit contributions
ggy+0.114
ggie+0.107
tr+0.105
keys+0.104
thy+0.101
Neg logit contributions
 air-0.044
 sav-0.043
joy-0.042
ky-0.042
 Now-0.041
Token bracelet
Token ID42893
Feature activation-7.03e+00

Pos logit contributions
ggy+0.048
ggie+0.045
ver+0.045
balls+0.044
 yes+0.042
Neg logit contributions
 habitat-0.059
 horizon-0.058
 exp-0.056
 sav-0.056
joy-0.056
Token back
Token ID736
Feature activation-1.69e+00

Pos logit contributions
ggy+0.181
 yes+0.176
ver+0.175
ggie+0.175
keys+0.160
Neg logit contributions
 than-0.127
 habitat-0.122
ky-0.112
 sav-0.108
 horizon-0.107
Token to
Token ID284
Feature activation-2.30e+00

Pos logit contributions
 yes+0.046
ggy+0.045
ggie+0.043
ver+0.043
 okay+0.039
Neg logit contributions
 habitat-0.034
 exp-0.029
 glory-0.028
ky-0.028
 sav-0.028
Token the
Token ID262
Feature activation-2.81e-01

Pos logit contributions
ggy+0.063
ver+0.061
ggie+0.060
tr+0.060
 yes+0.056
Neg logit contributions
 sav-0.040
 exp-0.039
 habitat-0.039
joy-0.038
 horizon-0.037
Token woman
Token ID2415
Feature activation-2.55e+00

Pos logit contributions
ver+0.006
 yes+0.006
ggy+0.006
ggie+0.006
cher+0.005
Neg logit contributions
 habitat-0.007
 horizon-0.006
 sav-0.006
 exp-0.006
 glory-0.006
Token.
Token ID13
Feature activation-4.48e-02

Pos logit contributions
ggy+0.077
ver+0.076
ggie+0.075
 yes+0.075
balls+0.069
Neg logit contributions
 habitat-0.036
 sav-0.033
 exp-0.032
ky-0.031
 ago-0.031
Token down
Token ID866
Feature activation+2.51e+00

Pos logit contributions
 habitat+0.010
 exp+0.009
 oceans+0.009
 horizon+0.009
 sav+0.009
Neg logit contributions
ggy-0.009
 yes-0.009
ggie-0.009
ver-0.009
 doll-0.008
Token and
Token ID290
Feature activation+2.38e+00

Pos logit contributions
 habitat+0.079
 glory+0.070
 habitats+0.069
 exp+0.066
iling+0.066
Neg logit contributions
 yes-0.049
ver-0.042
 doll-0.042
 mom-0.041
ggy-0.040
Token gave
Token ID2921
Feature activation-2.23e+00

Pos logit contributions
 habitat+0.078
 habitats+0.071
 glory+0.070
 horizon+0.068
 ago+0.067
Neg logit contributions
 yes-0.042
ggy-0.034
 doll-0.034
ver-0.034
 else-0.033
Token Lily
Token ID20037
Feature activation-5.93e+00

Pos logit contributions
ggy+0.061
keys+0.058
ver+0.058
ggie+0.056
 yes+0.055
Neg logit contributions
 air-0.043
 oceans-0.043
 habitat-0.042
 waters-0.042
ky-0.041
Token the
Token ID262
Feature activation-2.34e+00

Pos logit contributions
ver+0.120
 yes+0.120
ggy+0.120
ggie+0.112
cher+0.101
Neg logit contributions
 habitat-0.152
 oceans-0.138
 sav-0.136
 exp-0.133
ky-0.132
Token necklace
Token ID38987
Feature activation-7.02e+00

Pos logit contributions
ggy+0.040
ver+0.039
ggie+0.039
 yes+0.033
balls+0.030
Neg logit contributions
 habitat-0.069
 oceans-0.066
 glory-0.065
 exp-0.064
 air-0.064
Token.
Token ID13
Feature activation-3.09e-02

Pos logit contributions
ver+0.209
ggy+0.207
ggie+0.203
 yes+0.203
keys+0.188
Neg logit contributions
 than-0.097
 habitat-0.095
 waters-0.078
 sav-0.077
 air-0.077
Token She
Token ID1375
Feature activation+8.88e-01

Pos logit contributions
 yes+0.001
ggy+0.001
ver+0.001
ggie+0.001
 doll+0.001
Neg logit contributions
 habitat-0.001
 exp-0.001
 glory-0.001
 oceans-0.001
 horizon-0.001
Token put
Token ID1234
Feature activation-1.58e+00

Pos logit contributions
 habitat+0.024
 exp+0.022
 sav+0.021
 oceans+0.021
 glory+0.021
Neg logit contributions
 yes-0.018
ggy-0.017
ggie-0.016
ver-0.016
 doll-0.015
Token it
Token ID340
Feature activation-2.79e+00

Pos logit contributions
ggy+0.040
ggie+0.038
ver+0.038
 yes+0.035
keys+0.034
Neg logit contributions
 oceans-0.034
 air-0.033
 sav-0.032
ky-0.032
 habitat-0.031
Token around
Token ID1088
Feature activation+9.81e-01

Pos logit contributions
ggy+0.062
ggie+0.059
ver+0.055
 yes+0.053
keys+0.049
Neg logit contributions
 oceans-0.067
 habitat-0.066
 hills-0.064
 exp-0.060
 than-0.060
Token,
Token ID11
Feature activation+9.26e-01

Pos logit contributions
 habitat+0.022
 exp+0.019
 oceans+0.019
 horizon+0.019
 glory+0.019
Neg logit contributions
 yes-0.020
ggy-0.020
ggie-0.019
ver-0.019
 doll-0.018
Token so
Token ID523
Feature activation-1.49e+00

Pos logit contributions
 habitat+0.024
 exp+0.021
 glory+0.021
 oceans+0.021
 habitats+0.021
Neg logit contributions
 yes-0.021
ggy-0.020
ver-0.019
ggie-0.018
 doll-0.018
Token she
Token ID673
Feature activation+2.26e-01

Pos logit contributions
ver+0.032
ggie+0.032
ggy+0.031
 yes+0.030
ery+0.030
Neg logit contributions
 sav-0.034
 habitat-0.033
 glory-0.031
 air-0.031
 oceans-0.030
Token gave
Token ID2921
Feature activation-2.61e+00

Pos logit contributions
 habitat+0.005
 sav+0.005
 exp+0.004
ky+0.004
 waters+0.004
Neg logit contributions
ver-0.005
ggy-0.005
 yes-0.005
ggie-0.005
 doll-0.005
Token the
Token ID262
Feature activation-2.05e+00

Pos logit contributions
ggy+0.091
ggie+0.086
keys+0.084
ver+0.084
 yes+0.083
Neg logit contributions
 air-0.032
 sav-0.031
ky-0.030
 oceans-0.029
 hills-0.027
Token chain
Token ID6333
Feature activation-7.02e+00

Pos logit contributions
ggy+0.039
ggie+0.038
 yes+0.038
ver+0.037
balls+0.032
Neg logit contributions
 habitat-0.055
 exp-0.052
 sav-0.051
 oceans-0.051
 glory-0.050
Token back
Token ID736
Feature activation-1.35e+00

Pos logit contributions
ggy+0.186
ggie+0.184
ver+0.177
keys+0.176
 yes+0.174
Neg logit contributions
 habitat-0.118
 than-0.117
 air-0.101
 sav-0.099
ky-0.097
Token to
Token ID284
Feature activation-1.32e+00

Pos logit contributions
 yes+0.030
ggy+0.030
ver+0.029
ggie+0.028
 doll+0.027
Neg logit contributions
 habitat-0.034
 exp-0.030
 oceans-0.030
 horizon-0.029
 glory-0.029
Token the
Token ID262
Feature activation+2.99e-01

Pos logit contributions
ggy+0.030
ver+0.029
ggie+0.028
 yes+0.028
tr+0.024
Neg logit contributions
 habitat-0.031
 sav-0.030
 exp-0.029
 glory-0.028
 horizon-0.028
Token boy
Token ID2933
Feature activation-2.18e+00

Pos logit contributions
 habitat+0.007
 exp+0.007
 sav+0.007
 horizon+0.007
 oceans+0.006
Neg logit contributions
ver-0.007
ggy-0.007
 yes-0.007
ggie-0.007
ves-0.006
Token.
Token ID13
Feature activation+7.07e-01

Pos logit contributions
ggy+0.063
 yes+0.062
ggie+0.062
ver+0.061
Over+0.056
Neg logit contributions
 habitat-0.037
 sav-0.031
ky-0.030
 exp-0.030
 ago-0.029
TokenTom
Token ID13787
Feature activation+4.75e-01

Pos logit contributions
 yes+0.023
ggy+0.023
ggie+0.022
ver+0.022
 doll+0.021
Neg logit contributions
 habitat-0.030
 exp-0.027
 oceans-0.027
 glory-0.026
 horizon-0.026
Token nods
Token ID34833
Feature activation+9.20e-01

Pos logit contributions
 habitat+0.011
 glory+0.009
 oceans+0.009
 horizon+0.009
 exp+0.009
Neg logit contributions
 yes-0.012
ggy-0.012
 doll-0.011
ver-0.011
ggie-0.011
Token and
Token ID290
Feature activation+7.99e-01

Pos logit contributions
 habitat+0.019
 exp+0.016
 oceans+0.016
 glory+0.016
 horizon+0.016
Neg logit contributions
 yes-0.025
ggy-0.025
ver-0.024
ggie-0.024
 doll-0.023
Token gives
Token ID3607
Feature activation-2.54e+00

Pos logit contributions
 habitat+0.016
 exp+0.014
 glory+0.013
 oceans+0.013
 horizon+0.013
Neg logit contributions
 yes-0.022
ggy-0.022
ver-0.021
ggie-0.021
 doll-0.020
Token the
Token ID262
Feature activation-1.58e+00

Pos logit contributions
 yes+0.065
ver+0.064
ggy+0.063
keys+0.063
thy+0.061
Neg logit contributions
 air-0.049
 sav-0.048
 habitat-0.047
 oceans-0.044
 hills-0.043
Token stone
Token ID7815
Feature activation-7.01e+00

Pos logit contributions
ggy+0.036
 yes+0.035
ggie+0.034
ver+0.034
 doll+0.031
Neg logit contributions
 habitat-0.038
 exp-0.035
 oceans-0.035
 horizon-0.034
 glory-0.034
Token to
Token ID284
Feature activation-3.24e+00

Pos logit contributions
ver+0.214
ggy+0.213
ggie+0.211
 yes+0.198
thy+0.193
Neg logit contributions
 habitat-0.097
 than-0.095
 waters-0.092
 exp-0.084
 oceans-0.083
Token Sue
Token ID26089
Feature activation-4.17e+00

Pos logit contributions
ver+0.087
cher+0.082
keys+0.079
ache+0.076
ggy+0.076
Neg logit contributions
 sav-0.063
 air-0.052
 Now-0.051
 habitat-0.050
 than-0.050
Token.
Token ID13
Feature activation-1.04e+00

Pos logit contributions
ggy+0.136
ggie+0.132
 yes+0.131
ver+0.126
cher+0.121
Neg logit contributions
 habitat-0.056
 exp-0.048
 sav-0.048
ky-0.048
 than-0.046
Token Sue
Token ID26089
Feature activation-1.10e-01

Pos logit contributions
 yes+0.025
ggy+0.024
ver+0.023
ggie+0.023
 doll+0.022
Neg logit contributions
 habitat-0.025
 glory-0.022
 oceans-0.022
 exp-0.022
ky-0.022
Token holds
Token ID6622
Feature activation-1.80e+00

Pos logit contributions
 yes+0.003
ggy+0.003
ver+0.003
ggie+0.003
 doll+0.003
Neg logit contributions
 habitat-0.002
 exp-0.002
 glory-0.002
 oceans-0.002
 horizon-0.002
Token
Token ID198
Feature activation-1.08e+00

Pos logit contributions
 yes+0.037
ggy+0.036
ver+0.035
ggie+0.035
 doll+0.033
Neg logit contributions
 habitat-0.028
 exp-0.024
 sav-0.024
 glory-0.023
 horizon-0.023
TokenTim
Token ID14967
Feature activation-8.65e-01

Pos logit contributions
 yes+0.021
ggy+0.020
ver+0.019
ggie+0.019
 doll+0.018
Neg logit contributions
 habitat-0.031
 exp-0.028
 glory-0.027
 oceans-0.027
 sav-0.027
Tokenmy
Token ID1820
Feature activation-2.23e-03

Pos logit contributions
ggy+0.015
 yes+0.015
ggie+0.013
ver+0.013
balls+0.012
Neg logit contributions
 habitat-0.026
ky-0.024
 sav-0.024
 exp-0.024
 glory-0.023
Token gave
Token ID2921
Feature activation-2.76e+00

Pos logit contributions
 yes+0.000
ggy+0.000
ver+0.000
ggie+0.000
 doll+0.000
Neg logit contributions
 habitat-0.000
 exp-0.000
 sav-0.000
ky-0.000
 glory-0.000
Token the
Token ID262
Feature activation-2.48e+00

Pos logit contributions
ggy+0.078
 yes+0.075
ggie+0.074
keys+0.072
ver+0.072
Neg logit contributions
ky-0.049
 air-0.047
 oceans-0.047
 habitat-0.047
 exp-0.045
Token hat
Token ID6877
Feature activation-6.99e+00

Pos logit contributions
ggy+0.052
ver+0.051
ggie+0.050
 yes+0.047
 okay+0.042
Neg logit contributions
 habitat-0.064
 exp-0.060
 oceans-0.058
 horizon-0.057
 sav-0.057
Token back
Token ID736
Feature activation-6.08e-01

Pos logit contributions
ggy+0.198
ggie+0.191
ver+0.177
keys+0.173
ves+0.170
Neg logit contributions
 habitat-0.114
 than-0.109
 air-0.104
 horizon-0.102
 exp-0.101
Token and
Token ID290
Feature activation-4.38e-01

Pos logit contributions
ggy+0.016
 yes+0.016
ggie+0.015
ver+0.015
 doll+0.014
Neg logit contributions
 habitat-0.013
 exp-0.011
 oceans-0.011
 glory-0.011
 horizon-0.011
Token apologized
Token ID22893
Feature activation-1.40e+00

Pos logit contributions
ggy+0.010
ggie+0.010
ver+0.010
 yes+0.010
gh+0.009
Neg logit contributions
 habitat-0.010
 sav-0.009
 exp-0.009
 oceans-0.009
 glory-0.009
Token again
Token ID757
Feature activation+1.92e+00

Pos logit contributions
 yes+0.032
ggy+0.032
ver+0.030
ggie+0.030
 doll+0.028
Neg logit contributions
 habitat-0.035
 exp-0.031
 oceans-0.030
 glory-0.030
 horizon-0.030
Token.
Token ID13
Feature activation+1.93e-02

Pos logit contributions
 habitat+0.054
 oceans+0.049
 exp+0.049
 horizon+0.049
 habitats+0.047
Neg logit contributions
 yes-0.040
ggy-0.039
ver-0.035
ggie-0.035
 okay-0.034
Tokenara
Token ID3301
Feature activation+9.42e-01

Pos logit contributions
 habitat+0.031
 oceans+0.027
 horizon+0.026
 habitats+0.025
 exp+0.025
Neg logit contributions
ggy-0.031
 yes-0.030
ggie-0.029
ver-0.029
 doll-0.028
Token smiles
Token ID21845
Feature activation+1.43e+00

Pos logit contributions
 habitat+0.022
 glory+0.019
 oceans+0.019
 horizon+0.019
 habitats+0.018
Neg logit contributions
 yes-0.023
ggy-0.023
 doll-0.022
ver-0.021
ggie-0.021
Token and
Token ID290
Feature activation+1.35e+00

Pos logit contributions
 habitat+0.043
 glory+0.039
 habitats+0.038
 horizon+0.038
 exp+0.037
Neg logit contributions
 yes-0.029
 okay-0.026
 doll-0.025
ver-0.025
 mom-0.024
Token gives
Token ID3607
Feature activation-2.24e+00

Pos logit contributions
 habitat+0.032
 glory+0.028
 horizon+0.027
 habitats+0.027
 oceans+0.027
Neg logit contributions
 yes-0.034
ggy-0.032
 doll-0.031
ver-0.030
ggie-0.030
Token the
Token ID262
Feature activation-9.77e-01

Pos logit contributions
ggy+0.057
 yes+0.055
ver+0.055
ggie+0.053
tr+0.048
Neg logit contributions
 habitat-0.047
 oceans-0.045
 sav-0.044
ky-0.043
 exp-0.042
Token snail
Token ID47374
Feature activation-6.96e+00

Pos logit contributions
ggy+0.020
 yes+0.020
ggie+0.019
 doll+0.018
ver+0.018
Neg logit contributions
 habitat-0.027
 glory-0.024
 exp-0.023
 oceans-0.023
 habitats-0.023
Token to
Token ID284
Feature activation-2.16e+00

Pos logit contributions
ver+0.158
ggy+0.156
 yes+0.152
ggie+0.151
keys+0.134
Neg logit contributions
 habitat-0.162
 exp-0.142
ky-0.141
 oceans-0.141
 sav-0.141
Token Ben
Token ID3932
Feature activation-3.39e+00

Pos logit contributions
ggy+0.055
ver+0.054
 yes+0.054
ggie+0.052
 doll+0.048
Neg logit contributions
 habitat-0.045
 sav-0.041
 exp-0.040
 horizon-0.039
 oceans-0.039
Token.
Token ID13
Feature activation-3.37e-01

Pos logit contributions
ggy+0.095
 yes+0.094
ggie+0.091
ver+0.091
 doll+0.082
Neg logit contributions
 habitat-0.062
 exp-0.054
ky-0.053
 sav-0.052
 glory-0.051
Token Ben
Token ID3932
Feature activation-5.88e-03

Pos logit contributions
 yes+0.007
ver+0.007
 doll+0.006
 mom+0.006
ggy+0.006
Neg logit contributions
 habitat-0.009
 glory-0.008
iling-0.008
 horizon-0.008
 oceans-0.008
Token holds
Token ID6622
Feature activation-1.57e+00

Pos logit contributions
 yes+0.000
ggy+0.000
ver+0.000
ggie+0.000
 doll+0.000
Neg logit contributions
 habitat-0.000
 glory-0.000
 exp-0.000
 oceans-0.000
 horizon-0.000
Token felt
Token ID2936
Feature activation+8.84e-01

Pos logit contributions
 habitat+0.023
 exp+0.020
 oceans+0.020
 glory+0.020
 horizon+0.020
Neg logit contributions
 yes-0.015
ggy-0.015
ggie-0.014
ver-0.014
 doll-0.013
Token bad
Token ID2089
Feature activation+9.34e-01

Pos logit contributions
 habitat+0.027
 exp+0.024
 sav+0.024
 glory+0.024
 oceans+0.024
Neg logit contributions
 yes-0.015
ggy-0.015
ver-0.014
ggie-0.014
 doll-0.013
Token and
Token ID290
Feature activation-6.88e-01

Pos logit contributions
 habitat+0.023
 exp+0.020
 oceans+0.020
 horizon+0.020
 glory+0.020
Neg logit contributions
 yes-0.022
ggy-0.022
ver-0.021
ggie-0.021
 doll-0.020
Token gave
Token ID2921
Feature activation-1.99e+00

Pos logit contributions
ver+0.016
ggy+0.015
ggie+0.015
 yes+0.015
tr+0.014
Neg logit contributions
 habitat-0.016
 sav-0.016
 glory-0.014
 exp-0.014
 air-0.014
Token the
Token ID262
Feature activation-2.05e+00

Pos logit contributions
ggy+0.052
 yes+0.051
ver+0.049
keys+0.049
tr+0.047
Neg logit contributions
 habitat-0.039
 sav-0.038
ky-0.035
 glory-0.035
joy-0.035
Token jewel
Token ID16927
Feature activation-6.96e+00

Pos logit contributions
ggy+0.043
ver+0.043
ggie+0.041
 yes+0.038
balls+0.037
Neg logit contributions
 habitat-0.053
 sav-0.050
 glory-0.049
 horizon-0.048
 oceans-0.048
Token back
Token ID736
Feature activation-1.48e+00

Pos logit contributions
ggy+0.177
ggie+0.172
ver+0.169
 yes+0.162
ves+0.159
Neg logit contributions
 habitat-0.131
 than-0.123
 waters-0.112
 air-0.112
 sav-0.111
Token to
Token ID284
Feature activation-1.29e+00

Pos logit contributions
 yes+0.038
ggy+0.038
ver+0.036
ggie+0.036
 doll+0.034
Neg logit contributions
 habitat-0.032
 glory-0.026
 exp-0.026
ky-0.026
 oceans-0.026
Token his
Token ID465
Feature activation-2.71e+00

Pos logit contributions
ggy+0.027
ver+0.027
 yes+0.027
ggie+0.025
tr+0.023
Neg logit contributions
 habitat-0.032
 sav-0.030
 exp-0.029
 glory-0.028
 horizon-0.028
Token friend
Token ID1545
Feature activation-3.06e+00

Pos logit contributions
ver+0.054
 yes+0.043
cher+0.042
ggie+0.042
ggy+0.040
Neg logit contributions
 habitat-0.084
 glory-0.076
 sav-0.074
 wonders-0.072
 habitats-0.071
Token.
Token ID13
Feature activation-2.64e-01

Pos logit contributions
ggy+0.089
 yes+0.087
ver+0.087
ggie+0.087
Over+0.079
Neg logit contributions
 habitat-0.049
 sav-0.042
ky-0.041
 glory-0.041
 exp-0.041
Token Ben
Token ID3932
Feature activation-2.83e+00

Pos logit contributions
ggy+0.025
ver+0.025
 yes+0.024
ggie+0.023
cher+0.022
Neg logit contributions
 habitat-0.026
 exp-0.024
 oceans-0.024
ky-0.024
 sav-0.023
Token and
Token ID290
Feature activation-1.97e-01

Pos logit contributions
ggy+0.090
 yes+0.089
ggie+0.087
ver+0.086
 doll+0.080
Neg logit contributions
 habitat-0.042
 exp-0.035
 sav-0.035
 oceans-0.034
 glory-0.033
Token Lily
Token ID20037
Feature activation-1.84e+00

Pos logit contributions
ggy+0.005
 yes+0.005
ver+0.005
ggie+0.005
 doll+0.004
Neg logit contributions
 habitat-0.004
 exp-0.004
 sav-0.004
 oceans-0.004
 glory-0.004
Token and
Token ID290
Feature activation-7.23e-01

Pos logit contributions
 yes+0.045
ggy+0.042
ver+0.041
 doll+0.041
ggie+0.039
Neg logit contributions
 habitat-0.044
 habitats-0.038
 oceans-0.038
 glory-0.038
 exp-0.038
Token gives
Token ID3607
Feature activation-2.85e+00

Pos logit contributions
ggy+0.017
 yes+0.017
ggie+0.017
ver+0.016
 okay+0.014
Neg logit contributions
 habitat-0.017
 sav-0.015
 exp-0.015
 glory-0.015
 oceans-0.015
Token them
Token ID606
Feature activation-6.96e+00

Pos logit contributions
ggy+0.082
ver+0.080
 yes+0.075
ggie+0.075
keys+0.073
Neg logit contributions
 oceans-0.050
ky-0.050
 habitat-0.048
 sav-0.047
 air-0.047
Token a
Token ID257
Feature activation-3.27e+00

Pos logit contributions
ggy+0.143
 yes+0.139
ver+0.135
ggie+0.134
 doll+0.118
Neg logit contributions
 habitat-0.184
 exp-0.167
 oceans-0.165
 glory-0.162
 sav-0.162
Token kiss
Token ID9245
Feature activation-3.11e+00

Pos logit contributions
ggy+0.071
ggie+0.069
ver+0.067
 yes+0.065
 nobody+0.063
Neg logit contributions
 exp-0.074
 habitat-0.071
 air-0.068
 sav-0.067
joy-0.067
Token.
Token ID13
Feature activation-4.24e-01

Pos logit contributions
ggy+0.086
 yes+0.082
ver+0.082
ggie+0.082
aches+0.075
Neg logit contributions
 habitat-0.055
 exp-0.048
ky-0.048
 oceans-0.047
 horizon-0.047
Token Then
Token ID3244
Feature activation-9.64e-01

Pos logit contributions
 yes+0.009
 mom+0.008
 okay+0.007
 doll+0.007
ver+0.007
Neg logit contributions
 habitat-0.012
iling-0.011
 glory-0.011
ky-0.011
 oceans-0.011
Token they
Token ID484
Feature activation+2.66e-02

Pos logit contributions
ggy+0.019
ggie+0.019
ver+0.018
 yes+0.017
isy+0.016
Neg logit contributions
 habitat-0.024
 exp-0.024
 sav-0.023
 oceans-0.023
 glory-0.022
Token ever
Token ID1683
Feature activation+2.45e+00

Pos logit contributions
 habitat+0.037
 exp+0.035
 horizon+0.034
 glory+0.033
 sav+0.033
Neg logit contributions
 yes-0.026
ggy-0.026
ver-0.024
ggie-0.024
 doll-0.022
Token after
Token ID706
Feature activation+2.18e-01

Pos logit contributions
 habitat+0.053
 exp+0.052
 Now+0.051
 horizon+0.050
acks+0.050
Neg logit contributions
 yes-0.054
ggy-0.050
 okay-0.049
ggie-0.048
 else-0.048
Token."
Token ID526
Feature activation-9.24e-01

Pos logit contributions
 habitat+0.006
 exp+0.005
ky+0.005
 oceans+0.005
 horizon+0.005
Neg logit contributions
ggy-0.005
 yes-0.005
ggie-0.004
ver-0.004
 doll-0.004
Token They
Token ID1119
Feature activation-1.03e+00

Pos logit contributions
 yes+0.022
ggy+0.022
ver+0.021
ggie+0.021
 doll+0.020
Neg logit contributions
 habitat-0.021
 exp-0.019
 oceans-0.018
 sav-0.018
 glory-0.018
Token gave
Token ID2921
Feature activation-3.61e+00

Pos logit contributions
ggy+0.022
ggie+0.020
ver+0.020
 yes+0.020
balls+0.018
Neg logit contributions
 habitat-0.026
 sav-0.025
 exp-0.025
ky-0.023
 glory-0.023
Token them
Token ID606
Feature activation-6.94e+00

Pos logit contributions
ver+0.105
ggy+0.103
 yes+0.102
ggie+0.096
isy+0.094
Neg logit contributions
 habitat-0.060
 air-0.054
 sav-0.054
ky-0.054
 oceans-0.053
Token some
Token ID617
Feature activation-2.82e+00

Pos logit contributions
ggy+0.150
ver+0.145
 yes+0.144
ggie+0.140
cher+0.125
Neg logit contributions
 habitat-0.174
 exp-0.156
 oceans-0.155
 sav-0.152
 glory-0.150
Token cake
Token ID12187
Feature activation-4.64e+00

Pos logit contributions
ggy+0.057
ver+0.057
 yes+0.055
ggie+0.055
cher+0.047
Neg logit contributions
 habitat-0.074
 glory-0.067
 exp-0.066
 sav-0.066
 oceans-0.065
Token and
Token ID290
Feature activation-1.50e+00

Pos logit contributions
ggy+0.139
 yes+0.136
ggie+0.135
ver+0.134
 okay+0.122
Neg logit contributions
 habitat-0.077
 glory-0.063
 horizon-0.062
 exp-0.061
 sav-0.061
Token juice
Token ID13135
Feature activation-4.59e+00

Pos logit contributions
ver+0.035
ggy+0.034
ggie+0.033
 yes+0.033
 okay+0.029
Neg logit contributions
 habitat-0.035
 sav-0.033
 glory-0.032
 exp-0.031
 oceans-0.030
Token and
Token ID290
Feature activation-1.23e+00

Pos logit contributions
 yes+0.117
ggy+0.117
ver+0.111
ggie+0.111
 doll+0.105
Neg logit contributions
 habitat-0.099
 exp-0.086
 oceans-0.084
 glory-0.084
 horizon-0.083
Tokenwork
Token ID1818
Feature activation-2.56e-01

Pos logit contributions
 habitat+0.011
 exp+0.010
 oceans+0.010
 horizon+0.010
 glory+0.010
Neg logit contributions
ggy-0.010
 yes-0.010
ggie-0.009
ver-0.009
 doll-0.008
Token shot
Token ID2823
Feature activation+9.67e-02

Pos logit contributions
 yes+0.005
ggy+0.005
ver+0.005
ggie+0.005
 doll+0.005
Neg logit contributions
 habitat-0.007
 exp-0.006
 oceans-0.006
 glory-0.006
 horizon-0.006
Token up
Token ID510
Feature activation+2.31e+00

Pos logit contributions
 habitat+0.003
 oceans+0.002
 exp+0.002
ky+0.002
 horizon+0.002
Neg logit contributions
ggy-0.002
 yes-0.002
ver-0.002
ggie-0.002
 doll-0.002
Token high
Token ID1029
Feature activation+4.04e+00

Pos logit contributions
 habitat+0.060
 exp+0.052
 habitats+0.051
 glory+0.051
 sav+0.051
Neg logit contributions
 yes-0.051
ggy-0.049
ver-0.047
ggie-0.046
 doll-0.044
Token in
Token ID287
Feature activation+3.12e+00

Pos logit contributions
 habitat+0.114
joy+0.102
 habitats+0.102
 exp+0.099
 glory+0.099
Neg logit contributions
 yes-0.071
ggy-0.067
 doll-0.065
ggie-0.065
man-0.062
Token the
Token ID262
Feature activation+4.52e+00

Pos logit contributions
 habitat+0.100
 habitats+0.089
 exp+0.087
elly+0.086
acks+0.086
Neg logit contributions
 yes-0.045
 mom-0.045
 doll-0.043
ggy-0.040
 nobody-0.037
Token sky
Token ID6766
Feature activation+3.28e+00

Pos logit contributions
 habitat+0.084
 habitats+0.072
joy+0.072
iling+0.062
ky+0.061
Neg logit contributions
 doll-0.126
man-0.118
 mom-0.118
tr-0.115
 yes-0.115
Token.
Token ID13
Feature activation+1.51e+00

Pos logit contributions
 habitat+0.085
 exp+0.076
 habitats+0.075
 sav+0.073
 oceans+0.072
Neg logit contributions
 yes-0.071
ggy-0.068
ver-0.064
ggie-0.063
 doll-0.062
Token They
Token ID1119
Feature activation+1.52e-01

Pos logit contributions
 habitat+0.034
 glory+0.030
ky+0.030
 exp+0.030
 oceans+0.030
Neg logit contributions
 yes-0.036
ggy-0.034
ver-0.034
ggie-0.033
 doll-0.032
Token burst
Token ID11173
Feature activation+2.33e+00

Pos logit contributions
 habitat+0.004
 oceans+0.004
 exp+0.004
 sav+0.003
 horizon+0.003
Neg logit contributions
ggy-0.003
 yes-0.003
ggie-0.003
ver-0.003
 doll-0.003
Token open
Token ID1280
Feature activation+2.63e+00

Pos logit contributions
 habitat+0.061
 habitats+0.054
 sav+0.054
 exp+0.053
 glory+0.053
Neg logit contributions
 yes-0.048
ggy-0.045
ver-0.044
 doll-0.043
ggie-0.042
Token that
Token ID326
Feature activation-9.68e-01

Pos logit contributions
ver+0.052
ggy+0.052
ggie+0.050
 yes+0.049
cher+0.049
Neg logit contributions
 habitat-0.043
 exp-0.043
 oceans-0.041
 horizon-0.038
 hills-0.038
Token everyone
Token ID2506
Feature activation-1.25e+00

Pos logit contributions
ggy+0.019
 yes+0.019
ggie+0.018
ver+0.018
 doll+0.017
Neg logit contributions
 habitat-0.026
 exp-0.023
 oceans-0.023
 sav-0.023
 glory-0.023
Token should
Token ID815
Feature activation-2.32e+00

Pos logit contributions
 yes+0.026
ggy+0.024
ver+0.024
ggie+0.023
 okay+0.021
Neg logit contributions
 habitat-0.032
 exp-0.029
 than-0.028
 oceans-0.028
 sav-0.028
Token sleep
Token ID3993
Feature activation+1.42e+00

Pos logit contributions
 yes+0.039
ggy+0.039
ver+0.037
ggie+0.036
 doll+0.033
Neg logit contributions
 habitat-0.070
 exp-0.064
 glory-0.063
 oceans-0.063
 horizon-0.062
Token at
Token ID379
Feature activation+1.19e+00

Pos logit contributions
 habitat+0.040
 exp+0.036
 horizon+0.035
 oceans+0.035
 glory+0.035
Neg logit contributions
 yes-0.030
ggy-0.029
ggie-0.027
ver-0.027
 doll-0.025
Token night
Token ID1755
Feature activation+4.59e+00

Pos logit contributions
 habitat+0.030
ky+0.027
 exp+0.027
 glory+0.026
 habitats+0.026
Neg logit contributions
ggy-0.025
 yes-0.024
 doll-0.024
 mom-0.024
ggie-0.023
Token.
Token ID13
Feature activation+7.77e-01

Pos logit contributions
 habitat+0.134
 exp+0.126
 habitats+0.124
joy+0.123
 glory+0.123
Neg logit contributions
ggy-0.079
ggie-0.074
 yes-0.071
 doll-0.066
ver-0.064
Token Every
Token ID3887
Feature activation-2.10e-01

Pos logit contributions
 habitat+0.018
 glory+0.016
ky+0.016
 horizon+0.016
 exp+0.016
Neg logit contributions
 yes-0.019
ggy-0.018
 doll-0.017
ver-0.017
ggie-0.017
Token night
Token ID1755
Feature activation+1.56e+00

Pos logit contributions
 yes+0.005
ggy+0.005
ggie+0.005
ver+0.005
 doll+0.005
Neg logit contributions
 habitat-0.005
 exp-0.004
 glory-0.004
 oceans-0.004
 horizon-0.004
Token people
Token ID661
Feature activation-8.58e-01

Pos logit contributions
 habitat+0.039
 exp+0.035
 oceans+0.034
 glory+0.034
 horizon+0.034
Neg logit contributions
 yes-0.035
ggy-0.034
ver-0.033
ggie-0.032
 doll-0.031
Token all
Token ID477
Feature activation+8.19e-01

Pos logit contributions
ggy+0.016
 yes+0.015
ggie+0.015
ver+0.014
 doll+0.013
Neg logit contributions
 habitat-0.024
 exp-0.023
 oceans-0.022
ky-0.022
 sav-0.022
Token saw
Token ID2497
Feature activation-1.62e-01

Pos logit contributions
 habitat+0.021
 sav+0.019
 exp+0.019
ky+0.018
 oceans+0.018
Neg logit contributions
 yes-0.023
ggy-0.023
ver-0.022
ggie-0.022
 doll-0.021
Token a
Token ID257
Feature activation-6.64e-01

Pos logit contributions
ver+0.004
ggy+0.004
ggie+0.004
 yes+0.004
cher+0.004
Neg logit contributions
 habitat-0.004
 oceans-0.004
 hills-0.003
 mountains-0.003
 air-0.003
Token jet
Token ID12644
Feature activation-5.88e-01

Pos logit contributions
ver+0.017
 yes+0.015
ggy+0.015
ggie+0.015
owed+0.014
Neg logit contributions
 exp-0.014
 sav-0.014
 habitat-0.013
 horizon-0.013
 hills-0.013
Token in
Token ID287
Feature activation+2.85e+00

Pos logit contributions
 yes+0.013
ggy+0.013
ver+0.012
ggie+0.012
 doll+0.011
Neg logit contributions
 habitat-0.015
 exp-0.013
 oceans-0.013
 horizon-0.013
 glory-0.013
Token the
Token ID262
Feature activation+4.49e+00

Pos logit contributions
 habitat+0.089
 exp+0.079
 habitats+0.078
 glory+0.078
 horizon+0.076
Neg logit contributions
 yes-0.046
ggy-0.046
 doll-0.044
ggie-0.042
 mom-0.042
Token deep
Token ID2769
Feature activation+6.72e+00

Pos logit contributions
 habitat+0.096
 habitats+0.084
joy+0.083
iling+0.080
acks+0.080
Neg logit contributions
 doll-0.116
ggy-0.107
 yes-0.106
 mom-0.105
tr-0.103
Token sky
Token ID6766
Feature activation+3.35e+00

Pos logit contributions
 habitats+0.169
joy+0.165
 habitat+0.161
pill+0.159
 MacDonald+0.155
Neg logit contributions
 doll-0.128
 friend-0.108
 mom-0.105
 bird-0.104
 necklace-0.100
Token.
Token ID13
Feature activation+1.40e+00

Pos logit contributions
 habitat+0.100
 habitats+0.092
 exp+0.091
icol+0.089
 oceans+0.087
Neg logit contributions
 yes-0.055
ggy-0.053
ggie-0.048
 doll-0.047
ver-0.047
Token The
Token ID383
Feature activation-7.10e-01

Pos logit contributions
 habitat+0.037
 glory+0.033
ky+0.032
 habitats+0.032
iling+0.032
Neg logit contributions
 yes-0.030
ggy-0.028
ver-0.028
 doll-0.027
 mom-0.027
Token little
Token ID1310
Feature activation+7.52e-01

Pos logit contributions
ggy+0.014
 yes+0.014
ggie+0.013
ver+0.013
 doll+0.012
Neg logit contributions
 habitat-0.019
 exp-0.018
 oceans-0.018
 horizon-0.018
 glory-0.017
Token boy
Token ID2933
Feature activation-4.87e-01

Pos logit contributions
 habitat+0.023
 exp+0.021
 glory+0.021
 oceans+0.021
 horizon+0.021
Neg logit contributions
 yes-0.012
ggy-0.012
ver-0.011
ggie-0.011
 doll-0.010
Token got
Token ID1392
Feature activation+2.36e-01

Pos logit contributions
 yes+0.004
ggy+0.004
ver+0.004
ggie+0.004
 doll+0.004
Neg logit contributions
 habitat-0.006
 exp-0.005
 oceans-0.005
 glory-0.005
 horizon-0.005
Token them
Token ID606
Feature activation-2.05e+00

Pos logit contributions
 habitat+0.006
 oceans+0.006
 exp+0.006
 sav+0.006
 glory+0.005
Neg logit contributions
ggy-0.005
 yes-0.005
ver-0.005
ggie-0.005
 doll-0.004
Token from
Token ID422
Feature activation+2.00e+00

Pos logit contributions
ggy+0.046
 yes+0.044
ggie+0.044
ver+0.042
 doll+0.039
Neg logit contributions
 habitat-0.050
 exp-0.045
 oceans-0.045
 horizon-0.044
ky-0.044
Token flying
Token ID7348
Feature activation+1.45e+00

Pos logit contributions
 habitat+0.051
 exp+0.046
 glory+0.044
 horizon+0.044
 oceans+0.044
Neg logit contributions
 yes-0.044
ggy-0.043
ggie-0.040
 doll-0.040
ver-0.039
Token in
Token ID287
Feature activation+3.82e+00

Pos logit contributions
 habitat+0.038
 glory+0.035
 exp+0.034
 horizon+0.034
joy+0.034
Neg logit contributions
 yes-0.028
ggy-0.028
 doll-0.027
ggie-0.026
ver-0.025
Token the
Token ID262
Feature activation+4.63e+00

Pos logit contributions
 habitat+0.126
 habitats+0.116
 exp+0.114
icol+0.114
acks+0.112
Neg logit contributions
 doll-0.050
 mom-0.047
 yes-0.046
ggy-0.045
 nobody-0.040
Token sky
Token ID6766
Feature activation+2.84e+00

Pos logit contributions
 habitat+0.094
 habitats+0.083
 ago+0.082
iling+0.082
joy+0.080
Neg logit contributions
 doll-0.113
ggy-0.111
 mom-0.106
 friend-0.105
 nobody-0.103
Token and
Token ID290
Feature activation+1.87e+00

Pos logit contributions
 habitat+0.069
 exp+0.064
 glory+0.062
 horizon+0.062
 habitats+0.062
Neg logit contributions
 yes-0.061
ggy-0.059
ver-0.058
 doll-0.056
ggie-0.056
Token collecting
Token ID13157
Feature activation+6.13e-01

Pos logit contributions
 habitat+0.049
 exp+0.044
 oceans+0.043
 glory+0.043
 horizon+0.043
Neg logit contributions
 yes-0.039
ggy-0.039
ver-0.036
ggie-0.036
 doll-0.034
Token things
Token ID1243
Feature activation-4.86e-01

Pos logit contributions
 habitat+0.016
 horizon+0.015
 exp+0.014
 habitats+0.014
joy+0.014
Neg logit contributions
 yes-0.013
ggy-0.012
 doll-0.012
aches-0.011
 else-0.011
Token along
Token ID1863
Feature activation+2.24e+00

Pos logit contributions
 yes+0.009
ggy+0.009
ver+0.009
 else+0.008
 doll+0.008
Neg logit contributions
 habitat-0.014
 exp-0.013
 habitats-0.013
 glory-0.013
joy-0.013
Token I
Token ID314
Feature activation+5.28e-02

Pos logit contributions
 habitat+0.045
 horizon+0.041
 glory+0.040
 oceans+0.040
 exp+0.039
Neg logit contributions
 yes-0.052
ggy-0.050
ver-0.049
ggie-0.047
 okay-0.047
Token will
Token ID481
Feature activation+1.28e-01

Pos logit contributions
 habitat+0.001
 sav+0.001
 exp+0.001
 habitats+0.001
 glory+0.001
Neg logit contributions
 yes-0.001
ggy-0.001
ggie-0.001
ver-0.001
 doll-0.001
Token not
Token ID407
Feature activation-3.25e-01

Pos logit contributions
 habitat+0.004
 exp+0.004
 oceans+0.004
 glory+0.004
 horizon+0.004
Neg logit contributions
 yes-0.002
ggy-0.002
ggie-0.002
ver-0.002
 doll-0.002
Token touch
Token ID3638
Feature activation+1.40e+00

Pos logit contributions
 yes+0.006
ver+0.006
ggy+0.006
ggie+0.006
 doll+0.005
Neg logit contributions
 habitat-0.009
 sav-0.008
 exp-0.008
 glory-0.008
 horizon-0.008
Token it
Token ID340
Feature activation+2.47e-01

Pos logit contributions
 habitat+0.033
 oceans+0.029
 exp+0.029
 glory+0.028
 horizon+0.028
Neg logit contributions
 yes-0.033
ggy-0.033
ver-0.031
ggie-0.031
 doll-0.029
Token again
Token ID757
Feature activation+4.36e+00

Pos logit contributions
 habitat+0.006
 exp+0.005
 oceans+0.005
 horizon+0.005
 glory+0.005
Neg logit contributions
ggy-0.006
 yes-0.006
ggie-0.005
ver-0.005
 doll-0.005
Token."
Token ID526
Feature activation-1.35e-01

Pos logit contributions
 habitat+0.113
icol+0.107
 exp+0.106
 horizon+0.102
 habitats+0.100
Neg logit contributions
 okay-0.089
ggy-0.088
 yes-0.086
 mom-0.083
 else-0.081
Token
Token ID198
Feature activation-1.22e+00

Pos logit contributions
 yes+0.003
ggy+0.003
ver+0.003
ggie+0.003
 doll+0.003
Neg logit contributions
 habitat-0.003
 exp-0.003
 glory-0.003
 horizon-0.003
ky-0.003
Token
Token ID198
Feature activation-7.47e-01

Pos logit contributions
 yes+0.033
ggy+0.032
ver+0.031
ggie+0.031
 doll+0.029
Neg logit contributions
 habitat-0.024
 exp-0.021
 oceans-0.021
 sav-0.021
 glory-0.021
TokenThe
Token ID464
Feature activation-1.14e+00

Pos logit contributions
ggy+0.015
 yes+0.015
ver+0.014
ggie+0.014
 doll+0.013
Neg logit contributions
 habitat-0.021
 exp-0.019
 glory-0.019
 horizon-0.018
 oceans-0.018
Token mouse
Token ID10211
Feature activation-1.71e-01

Pos logit contributions
ver+0.023
 yes+0.022
ggy+0.021
ggie+0.021
aches+0.020
Neg logit contributions
 habitat-0.029
 horizon-0.028
 sav-0.028
 air-0.028
 oceans-0.028
Token was
Token ID373
Feature activation+4.45e-01

Pos logit contributions
 habitat+0.001
 exp+0.001
 oceans+0.001
 glory+0.001
 horizon+0.001
Neg logit contributions
 yes-0.001
ggy-0.001
ver-0.001
ggie-0.001
 doll-0.001
Token there
Token ID612
Feature activation+1.18e+00

Pos logit contributions
 habitat+0.012
 sav+0.010
 glory+0.010
 exp+0.010
 oceans+0.010
Neg logit contributions
 yes-0.009
ggy-0.009
ver-0.009
ggie-0.008
 doll-0.008
Token to
Token ID284
Feature activation-4.27e-01

Pos logit contributions
 habitat+0.027
 exp+0.024
 oceans+0.023
 glory+0.023
 horizon+0.023
Neg logit contributions
 yes-0.028
ggy-0.028
ver-0.027
ggie-0.027
 doll-0.025
Token keep
Token ID1394
Feature activation+4.55e-01

Pos logit contributions
ggy+0.008
ver+0.008
 yes+0.008
ggie+0.008
 doll+0.007
Neg logit contributions
 habitat-0.012
 sav-0.011
 exp-0.011
 glory-0.010
 oceans-0.010
Token her
Token ID607
Feature activation-2.03e+00

Pos logit contributions
 habitat+0.012
 sav+0.011
 glory+0.011
 oceans+0.010
 exp+0.010
Neg logit contributions
 yes-0.009
ggy-0.009
ver-0.009
ggie-0.009
 doll-0.008
Token safe
Token ID3338
Feature activation+1.01e+00

Pos logit contributions
ver+0.044
ggy+0.043
ggie+0.041
 yes+0.040
cher+0.037
Neg logit contributions
 habitat-0.051
 glory-0.046
 sav-0.045
 horizon-0.044
 exp-0.044
Token and
Token ID290
Feature activation-4.95e-01

Pos logit contributions
 habitat+0.023
 exp+0.020
 oceans+0.019
 glory+0.019
 horizon+0.019
Neg logit contributions
 yes-0.025
ggy-0.025
ver-0.024
ggie-0.024
 doll-0.023
Token happy
Token ID3772
Feature activation+1.08e+00

Pos logit contributions
ggy+0.010
 yes+0.010
ver+0.009
ggie+0.009
 doll+0.008
Neg logit contributions
 habitat-0.014
 sav-0.012
 glory-0.012
 exp-0.012
 oceans-0.012
Token.
Token ID13
Feature activation+1.08e+00

Pos logit contributions
 habitat+0.025
 exp+0.022
 oceans+0.022
 glory+0.022
 horizon+0.022
Neg logit contributions
 yes-0.026
ggy-0.025
ver-0.024
ggie-0.024
 doll-0.023
Token
Token ID220
Feature activation-4.16e-01

Pos logit contributions
 habitat+0.025
 glory+0.023
 oceans+0.023
 exp+0.022
 horizon+0.022
Neg logit contributions
 yes-0.025
ggy-0.024
ver-0.024
 doll-0.023
ggie-0.023
Token
Token ID198
Feature activation+3.52e-01

Pos logit contributions
 yes+0.012
ggy+0.012
ggie+0.012
 doll+0.011
ver+0.011
Neg logit contributions
 habitat-0.007
 exp-0.006
 Now-0.006
 horizon-0.006
 glory-0.006
Token This
Token ID770
Feature activation-8.50e-01

Pos logit contributions
 habitat+0.024
 exp+0.022
 horizon+0.022
 oceans+0.022
 glory+0.022
Neg logit contributions
 yes-0.019
ggy-0.018
ver-0.018
 doll-0.016
ggie-0.016
Token made
Token ID925
Feature activation-2.26e+00

Pos logit contributions
 yes+0.017
ggy+0.016
ver+0.015
ggie+0.015
 doll+0.014
Neg logit contributions
 habitat-0.024
 exp-0.021
 oceans-0.021
 glory-0.021
 horizon-0.021
Token the
Token ID262
Feature activation-6.65e-01

Pos logit contributions
ver+0.058
 yes+0.058
cher+0.057
ggy+0.055
ggie+0.053
Neg logit contributions
 habitat-0.046
 air-0.042
 glory-0.042
 oceans-0.042
 sav-0.041
Token kids
Token ID3988
Feature activation-2.89e+00

Pos logit contributions
 yes+0.013
ggy+0.012
ggie+0.012
ver+0.012
 doll+0.011
Neg logit contributions
 habitat-0.019
 exp-0.017
 oceans-0.017
 glory-0.017
 horizon-0.017
Token sad
Token ID6507
Feature activation+8.25e-01

Pos logit contributions
ggy+0.059
ggie+0.057
ver+0.055
 yes+0.054
tr+0.054
Neg logit contributions
 habitat-0.063
 than-0.062
 exp-0.059
 air-0.059
 waters-0.057
Token.
Token ID13
Feature activation+1.03e+00

Pos logit contributions
 habitat+0.019
 exp+0.017
 oceans+0.017
 glory+0.017
 horizon+0.017
Neg logit contributions
 yes-0.020
ggy-0.020
ggie-0.019
ver-0.019
 doll-0.018
Token They
Token ID1119
Feature activation-4.13e-01

Pos logit contributions
 habitat+0.029
 exp+0.026
 horizon+0.026
 oceans+0.026
 glory+0.025
Neg logit contributions
 yes-0.020
ggy-0.020
ver-0.019
ggie-0.018
 doll-0.018
Token did
Token ID750
Feature activation-8.67e-01

Pos logit contributions
ggy+0.009
ggie+0.009
 yes+0.009
ver+0.008
 doll+0.008
Neg logit contributions
 habitat-0.010
 exp-0.009
 sav-0.009
 habitats-0.009
ky-0.009
Token not
Token ID407
Feature activation-9.94e-01

Pos logit contributions
 yes+0.010
ver+0.009
ggy+0.009
cher+0.009
ggie+0.008
Neg logit contributions
 habitat-0.030
 sav-0.028
 exp-0.027
 glory-0.027
 habitats-0.027
Token know
Token ID760
Feature activation-1.07e-01

Pos logit contributions
 yes+0.022
ggy+0.021
ver+0.020
ggie+0.020
 doll+0.019
Neg logit contributions
 habitat-0.025
 exp-0.023
 glory-0.022
 sav-0.022
 oceans-0.022
Token what
Token ID644
Feature activation-8.12e-01

Pos logit contributions
ggy+0.002
ggie+0.002
ver+0.002
 yes+0.002
cher+0.002
Neg logit contributions
 habitat-0.003
 oceans-0.003
 hills-0.003
 exp-0.002
 glory-0.002
Token€
Token ID26391
Feature activation+8.61e-01

Pos logit contributions
 habitat+0.099
 oceans+0.090
 habitats+0.087
joy+0.087
 hills+0.085
Neg logit contributions
ggy-0.073
ggie-0.069
 yes-0.063
ver-0.062
isy-0.056
Token
Token ID198
Feature activation+5.38e-01

Pos logit contributions
 habitat+0.022
 glory+0.021
 horizon+0.020
 exp+0.020
 oceans+0.020
Neg logit contributions
ggy-0.020
ver-0.018
 yes-0.018
ggie-0.018
 doll-0.016
Token
Token ID198
Feature activation+5.99e-01

Pos logit contributions
 habitat+0.013
 exp+0.011
 sav+0.011
 oceans+0.011
 glory+0.011
Neg logit contributions
 yes-0.013
ggy-0.012
ver-0.012
ggie-0.012
 doll-0.011
TokenThe
Token ID464
Feature activation-1.21e+00

Pos logit contributions
 habitat+0.016
 exp+0.014
 glory+0.014
 oceans+0.014
 horizon+0.014
Neg logit contributions
ggy-0.013
 yes-0.013
ggie-0.012
ver-0.012
 doll-0.011
Token animals
Token ID4695
Feature activation-5.79e-01

Pos logit contributions
ver+0.026
 yes+0.023
ggy+0.023
ggie+0.023
balls+0.020
Neg logit contributions
 habitat-0.031
 oceans-0.029
 horizon-0.029
 sav-0.029
 air-0.028
Token laughed
Token ID13818
Feature activation+1.54e+00

Pos logit contributions
ggy+0.012
 yes+0.011
ggie+0.011
ver+0.011
 doll+0.010
Neg logit contributions
 habitat-0.015
 exp-0.014
 oceans-0.014
 sav-0.014
 glory-0.014
Token at
Token ID379
Feature activation+3.85e-01

Pos logit contributions
 habitat+0.030
 exp+0.026
 oceans+0.025
 glory+0.025
 horizon+0.025
Neg logit contributions
 yes-0.043
ggy-0.042
ver-0.040
ggie-0.040
 doll-0.038
Token her
Token ID607
Feature activation-1.60e+00

Pos logit contributions
 habitat+0.010
 exp+0.008
 oceans+0.008
 glory+0.008
 sav+0.008
Neg logit contributions
ggy-0.009
 yes-0.008
ver-0.008
ggie-0.008
 doll-0.007
Token.
Token ID13
Feature activation+1.67e+00

Pos logit contributions
ver+0.042
ggy+0.042
 yes+0.041
ggie+0.040
 doll+0.037
Neg logit contributions
 habitat-0.033
 exp-0.028
 glory-0.028
 horizon-0.027
 sav-0.027
Token They
Token ID1119
Feature activation+4.23e-02

Pos logit contributions
 habitat+0.037
 glory+0.035
 oceans+0.033
ky+0.033
 horizon+0.033
Neg logit contributions
 yes-0.041
ver-0.038
ggy-0.036
 doll-0.036
 okay-0.035
Token all
Token ID477
Feature activation+6.87e-01

Pos logit contributions
 habitat+0.001
 exp+0.001
 sav+0.001
 oceans+0.001
 glory+0.001
Neg logit contributions
ggy-0.001
 yes-0.001
ggie-0.001
ver-0.001
 doll-0.001
Token and
Token ID290
Feature activation+9.15e-01

Pos logit contributions
ggy+0.044
 yes+0.043
ggie+0.042
ver+0.042
 doll+0.039
Neg logit contributions
 habitat-0.033
 oceans-0.029
 exp-0.028
 horizon-0.028
 glory-0.028
Token shades
Token ID23787
Feature activation-1.71e+00

Pos logit contributions
 habitat+0.020
 exp+0.017
 oceans+0.017
 horizon+0.017
 glory+0.017
Neg logit contributions
 yes-0.023
ggy-0.023
ggie-0.022
ver-0.022
 doll-0.021
Token of
Token ID286
Feature activation+3.13e-01

Pos logit contributions
 yes+0.034
ggy+0.033
ver+0.031
ggie+0.031
 doll+0.029
Neg logit contributions
 habitat-0.047
 exp-0.042
 oceans-0.042
 glory-0.041
 horizon-0.041
Token colors
Token ID7577
Feature activation-9.49e-01

Pos logit contributions
 habitat+0.008
 exp+0.007
ky+0.007
 horizon+0.006
 sav+0.006
Neg logit contributions
 yes-0.007
 doll-0.007
ggy-0.006
ggie-0.006
 mom-0.006
Token.
Token ID13
Feature activation+4.28e-01

Pos logit contributions
 yes+0.024
ggy+0.024
ver+0.022
ggie+0.022
 doll+0.021
Neg logit contributions
 habitat-0.021
 exp-0.018
 oceans-0.018
 glory-0.018
 horizon-0.018
Token She
Token ID1375
Feature activation+1.68e+00

Pos logit contributions
 habitat+0.009
 exp+0.007
 glory+0.007
 oceans+0.007
 horizon+0.007
Neg logit contributions
 yes-0.012
ggy-0.011
ver-0.011
ggie-0.011
 doll-0.010
Token liked
Token ID8288
Feature activation+5.54e-02

Pos logit contributions
 habitat+0.044
 exp+0.039
 oceans+0.039
 glory+0.039
 horizon+0.038
Neg logit contributions
 yes-0.036
ggy-0.035
ver-0.033
ggie-0.033
 doll-0.031
Token it
Token ID340
Feature activation-1.03e+00

Pos logit contributions
 habitat+0.001
 oceans+0.001
 exp+0.001
 glory+0.001
 sav+0.001
Neg logit contributions
ggy-0.001
 yes-0.001
ver-0.001
ggie-0.001
 doll-0.001
Token.
Token ID13
Feature activation+3.94e-01

Pos logit contributions
ggy+0.027
ver+0.026
ggie+0.026
 yes+0.025
cher+0.024
Neg logit contributions
 habitat-0.019
 than-0.019
 glory-0.017
 oceans-0.017
 sav-0.017
Token She
Token ID1375
Feature activation+1.62e+00

Pos logit contributions
 habitat+0.008
 exp+0.007
 glory+0.007
 oceans+0.007
 horizon+0.007
Neg logit contributions
 yes-0.011
ggy-0.011
ver-0.010
ggie-0.010
 doll-0.010
Token smiled
Token ID13541
Feature activation+2.04e+00

Pos logit contributions
 habitat+0.044
 exp+0.039
 oceans+0.039
 horizon+0.039
 glory+0.039
Neg logit contributions
 yes-0.034
ggy-0.033
ver-0.031
ggie-0.031
 doll-0.030
Token heard
Token ID2982
Feature activation+6.55e-02

Pos logit contributions
 habitat+0.042
 exp+0.038
 sav+0.037
 oceans+0.037
 glory+0.037
Neg logit contributions
ggy-0.039
 yes-0.039
ver-0.037
ggie-0.037
 doll-0.034
Token the
Token ID262
Feature activation-4.49e-01

Pos logit contributions
 habitat+0.002
 oceans+0.001
 exp+0.001
 hills+0.001
 air+0.001
Neg logit contributions
ver-0.002
ggy-0.001
 yes-0.001
ggie-0.001
cher-0.001
Token birds
Token ID10087
Feature activation-4.13e-01

Pos logit contributions
 yes+0.010
ggy+0.010
ver+0.010
ggie+0.009
 doll+0.009
Neg logit contributions
 habitat-0.011
 exp-0.010
 horizon-0.010
 oceans-0.010
 glory-0.010
Token singing
Token ID13777
Feature activation+4.24e-05

Pos logit contributions
ggy+0.010
 yes+0.009
ver+0.009
ggie+0.009
 doll+0.008
Neg logit contributions
 habitat-0.010
 exp-0.009
 oceans-0.009
 horizon-0.009
 sav-0.008
Token again
Token ID757
Feature activation+3.23e+00

Pos logit contributions
 habitat+0.000
 oceans+0.000
 exp+0.000
ky+0.000
 horizon+0.000
Neg logit contributions
ggy-0.000
 yes-0.000
ver-0.000
ggie-0.000
 doll-0.000
Token.
Token ID13
Feature activation+1.18e+00

Pos logit contributions
 habitat+0.099
 exp+0.088
 habitats+0.087
 oceans+0.085
 sav+0.083
Neg logit contributions
 yes-0.056
ggy-0.056
 mom-0.053
 doll-0.051
ggie-0.050
Token She
Token ID1375
Feature activation+1.50e+00

Pos logit contributions
 habitat+0.029
 oceans+0.026
 glory+0.026
 horizon+0.025
ky+0.025
Neg logit contributions
 yes-0.027
 doll-0.025
ggy-0.025
ver-0.024
 mom-0.024
Token took
Token ID1718
Feature activation-9.20e-01

Pos logit contributions
 habitat+0.039
 exp+0.036
 oceans+0.035
 sav+0.035
 glory+0.035
Neg logit contributions
 yes-0.031
ggy-0.031
ver-0.029
ggie-0.029
 doll-0.027
Token a
Token ID257
Feature activation-1.62e+00

Pos logit contributions
ggy+0.021
ver+0.020
 yes+0.020
ggie+0.019
cher+0.019
Neg logit contributions
 air-0.021
 oceans-0.020
 habitat-0.020
 hills-0.020
 valleys-0.019
Token deep
Token ID2769
Feature activation+1.27e+00

Pos logit contributions
ver+0.041
ggy+0.041
 yes+0.040
ggie+0.040
 nobody+0.039
Neg logit contributions
 exp-0.030
 hills-0.027
 formation-0.026
 air-0.026
 horizon-0.026
Token breath
Token ID8033
Feature activation+9.48e-01

Pos logit contributions
 habitat+0.033
 habitats+0.029
 glory+0.029
 horizon+0.028
 oceans+0.028
Neg logit contributions
ggy-0.029
 yes-0.028
ggie-0.027
 doll-0.026
ver-0.025
Token under
Token ID739
Feature activation+2.65e+00

Pos logit contributions
 habitat+0.068
 exp+0.061
 oceans+0.061
 glory+0.060
 horizon+0.060
Neg logit contributions
 yes-0.042
ggy-0.041
ver-0.039
ggie-0.038
 doll-0.036
Token the
Token ID262
Feature activation+1.55e+00

Pos logit contributions
 habitat+0.078
 glory+0.070
 exp+0.069
 habitats+0.069
ky+0.069
Neg logit contributions
 yes-0.049
ggy-0.046
 doll-0.043
ggie-0.041
 mom-0.041
Token oak
Token ID26210
Feature activation+3.24e+00

Pos logit contributions
 habitat+0.040
 exp+0.035
 glory+0.034
 oceans+0.034
 habitats+0.034
Neg logit contributions
 yes-0.033
ggy-0.033
 doll-0.031
ggie-0.030
ver-0.030
Token tree
Token ID5509
Feature activation+2.03e+00

Pos logit contributions
 habitat+0.111
icol+0.106
joy+0.105
 exp+0.101
 habitats+0.101
Neg logit contributions
 doll-0.039
ggy-0.036
 yes-0.031
 else-0.030
ver-0.029
Token and
Token ID290
Feature activation+4.96e-01

Pos logit contributions
 habitat+0.050
 exp+0.046
 glory+0.044
 oceans+0.044
 horizon+0.044
Neg logit contributions
 yes-0.045
ggy-0.044
ver-0.042
ggie-0.041
 doll-0.041
Token talk
Token ID1561
Feature activation-2.83e-01

Pos logit contributions
 habitat+0.014
 exp+0.013
 sav+0.013
 oceans+0.013
 horizon+0.013
Neg logit contributions
ggy-0.009
 yes-0.009
ver-0.009
ggie-0.009
 doll-0.008
Token.
Token ID13
Feature activation+1.02e+00

Pos logit contributions
ggy+0.007
 yes+0.007
ver+0.006
ggie+0.006
 doll+0.006
Neg logit contributions
 habitat-0.007
 exp-0.006
 oceans-0.006
 glory-0.006
 horizon-0.006
Token
Token ID198
Feature activation+2.40e-01

Pos logit contributions
 habitat+0.027
ky+0.027
 glory+0.026
 exp+0.025
 oceans+0.025
Neg logit contributions
 yes-0.019
ggy-0.018
 mom-0.018
ver-0.018
 doll-0.018
Token
Token ID198
Feature activation+6.81e-01

Pos logit contributions
 habitat+0.005
 exp+0.005
 oceans+0.005
 glory+0.005
 horizon+0.005
Neg logit contributions
 yes-0.006
ggy-0.006
ver-0.006
ggie-0.006
 doll-0.005
TokenOne
Token ID3198
Feature activation+4.50e-01

Pos logit contributions
 habitat+0.020
 glory+0.018
 exp+0.018
 horizon+0.018
 oceans+0.018
Neg logit contributions
ggy-0.013
 yes-0.013
ggie-0.012
ver-0.012
 doll-0.011
Token day
Token ID1110
Feature activation-6.03e-01

Pos logit contributions
 habitat+0.010
 exp+0.009
 glory+0.009
 horizon+0.009
 oceans+0.009
Neg logit contributions
 yes-0.011
ggy-0.011
ver-0.011
ggie-0.011
 doll-0.010
Token held
Token ID2714
Feature activation-1.15e+00

Pos logit contributions
 habitat+0.016
 oceans+0.014
 horizon+0.014
 glory+0.014
 exp+0.014
Neg logit contributions
 yes-0.010
ggy-0.010
ggie-0.009
ver-0.009
 doll-0.009
Token the
Token ID262
Feature activation-1.67e+00

Pos logit contributions
ggy+0.032
 yes+0.031
ggie+0.030
ver+0.030
tr+0.030
Neg logit contributions
 exp-0.018
 sav-0.018
 Now-0.018
joy-0.018
ky-0.017
Token wrap
Token ID14441
Feature activation-3.12e+00

Pos logit contributions
ver+0.039
ggy+0.037
ggie+0.035
 yes+0.033
keys+0.030
Neg logit contributions
 habitat-0.041
 horizon-0.039
 air-0.038
 exp-0.038
 sav-0.037
Token all
Token ID477
Feature activation-2.30e-01

Pos logit contributions
ggy+0.083
 yes+0.078
ver+0.078
ggie+0.077
 okay+0.072
Neg logit contributions
 habitat-0.059
ky-0.055
 horizon-0.055
 exp-0.053
 oceans-0.053
Token the
Token ID262
Feature activation+1.83e-02

Pos logit contributions
 yes+0.004
ggy+0.004
ver+0.004
ggie+0.004
 doll+0.004
Neg logit contributions
 habitat-0.007
 exp-0.006
 oceans-0.006
 glory-0.006
 horizon-0.006
Token way
Token ID835
Feature activation-4.85e-01

Pos logit contributions
 habitat+0.000
 glory+0.000
 exp+0.000
 oceans+0.000
 horizon+0.000
Neg logit contributions
ggy-0.000
 yes-0.000
ver-0.000
ggie-0.000
 doll-0.000
Token home
Token ID1363
Feature activation-7.52e-02

Pos logit contributions
ggy+0.012
 yes+0.011
ggie+0.011
ver+0.011
 doll+0.010
Neg logit contributions
 habitat-0.011
 horizon-0.010
 exp-0.010
 oceans-0.010
 glory-0.010
Token,
Token ID11
Feature activation+1.37e+00

Pos logit contributions
ggy+0.002
 yes+0.002
ggie+0.002
ver+0.002
 doll+0.002
Neg logit contributions
 habitat-0.002
 glory-0.001
 horizon-0.001
 exp-0.001
 oceans-0.001
Token not
Token ID407
Feature activation-7.11e-01

Pos logit contributions
 habitat+0.034
 exp+0.030
 oceans+0.029
 glory+0.029
 habitats+0.029
Neg logit contributions
 yes-0.033
ggy-0.031
ver-0.029
ggie-0.029
 doll-0.028
Token wanting
Token ID10291
Feature activation-4.10e-01

Pos logit contributions
ggy+0.017
ver+0.017
 yes+0.017
ggie+0.016
 doll+0.015
Neg logit contributions
 habitat-0.017
 sav-0.015
 oceans-0.014
 exp-0.014
 horizon-0.014
Token to
Token ID284
Feature activation-9.85e-01

Pos logit contributions
ggy+0.010
 yes+0.010
ver+0.009
ggie+0.009
 doll+0.009
Neg logit contributions
 habitat-0.009
 exp-0.008
 oceans-0.008
 glory-0.008
 horizon-0.008
Token ball
Token ID2613
Feature activation-9.15e-01

Pos logit contributions
 habitat+0.054
 exp+0.049
 glory+0.048
 oceans+0.048
 horizon+0.048
Neg logit contributions
 yes-0.036
ggy-0.035
ggie-0.032
ver-0.032
 doll-0.031
Token.
Token ID13
Feature activation+1.61e+00

Pos logit contributions
 yes+0.024
ggy+0.024
ver+0.023
ggie+0.023
 doll+0.022
Neg logit contributions
 habitat-0.019
 exp-0.017
 oceans-0.016
 glory-0.016
 horizon-0.016
Token Do
Token ID2141
Feature activation-2.34e+00

Pos logit contributions
 habitat+0.033
 exp+0.029
 glory+0.029
 horizon+0.028
 oceans+0.028
Neg logit contributions
 yes-0.043
ggy-0.042
ver-0.040
ggie-0.040
 doll-0.039
Token you
Token ID345
Feature activation+2.06e-01

Pos logit contributions
ver+0.070
 yes+0.067
ggy+0.067
ggie+0.066
 doll+0.064
Neg logit contributions
 habitat-0.037
 sav-0.031
 oceans-0.031
 exp-0.031
 glory-0.029
Token want
Token ID765
Feature activation-1.04e+00

Pos logit contributions
 habitat+0.005
 oceans+0.004
 exp+0.004
 horizon+0.004
 glory+0.004
Neg logit contributions
 yes-0.005
ggy-0.005
ver-0.005
ggie-0.005
 doll-0.004
Token to
Token ID284
Feature activation-1.52e+00

Pos logit contributions
 yes+0.022
ggy+0.022
ggie+0.020
ver+0.020
 doll+0.020
Neg logit contributions
 habitat-0.028
 exp-0.025
 glory-0.024
 horizon-0.024
 oceans-0.024
Token play
Token ID711
Feature activation-7.84e-01

Pos logit contributions
 yes+0.032
ggy+0.032
ver+0.031
ggie+0.030
 doll+0.028
Neg logit contributions
 habitat-0.040
 exp-0.036
 oceans-0.035
 sav-0.035
 glory-0.035
Token with
Token ID351
Feature activation+3.45e-01

Pos logit contributions
 yes+0.017
ggy+0.017
ver+0.016
ggie+0.016
 doll+0.015
Neg logit contributions
 habitat-0.020
 exp-0.018
 oceans-0.018
 glory-0.017
 sav-0.017
Token me
Token ID502
Feature activation-1.03e+00

Pos logit contributions
 habitat+0.006
 exp+0.005
 oceans+0.005
 glory+0.005
 horizon+0.005
Neg logit contributions
 yes-0.011
ggy-0.011
ggie-0.010
ver-0.010
 doll-0.010
Token?"
Token ID1701
Feature activation-2.80e-01

Pos logit contributions
 yes+0.022
ggy+0.022
ver+0.021
ggie+0.020
 doll+0.020
Neg logit contributions
 habitat-0.027
 exp-0.024
 horizon-0.024
 glory-0.024
 oceans-0.024
Token
Token ID198
Feature activation-1.49e+00

Pos logit contributions
 yes+0.007
ggy+0.007
ver+0.007
ggie+0.007
 doll+0.006
Neg logit contributions
 habitat-0.006
 exp-0.006
 oceans-0.005
 glory-0.005
 horizon-0.005
Token high
Token ID1029
Feature activation+2.95e+00

Pos logit contributions
 habitat+0.014
 exp+0.012
 oceans+0.012
 glory+0.012
 horizon+0.012
Neg logit contributions
 yes-0.011
ggy-0.010
ver-0.010
ggie-0.010
 doll-0.009
Token,
Token ID11
Feature activation+2.25e+00

Pos logit contributions
 habitat+0.083
 habitats+0.075
 glory+0.074
 exp+0.073
 oceans+0.071
Neg logit contributions
 yes-0.056
ggy-0.053
ggie-0.051
ver-0.050
 doll-0.049
Token and
Token ID290
Feature activation+6.45e-01

Pos logit contributions
 habitat+0.058
 habitats+0.050
 glory+0.050
 exp+0.050
iling+0.047
Neg logit contributions
 yes-0.053
ggy-0.046
 doll-0.045
ver-0.044
ggie-0.043
Token Joey
Token ID26154
Feature activation-2.78e-01

Pos logit contributions
 habitat+0.016
 sav+0.015
 oceans+0.015
 exp+0.015
 glory+0.014
Neg logit contributions
ggy-0.014
 yes-0.014
ggie-0.013
ver-0.013
 doll-0.012
Token reached
Token ID4251
Feature activation+4.68e-01

Pos logit contributions
 yes+0.005
ggy+0.005
ggie+0.005
ver+0.004
 doll+0.004
Neg logit contributions
 habitat-0.008
 exp-0.007
 sav-0.007
 oceans-0.007
 glory-0.007
Token out
Token ID503
Feature activation+9.93e-02

Pos logit contributions
 habitat+0.012
 oceans+0.011
 exp+0.011
 glory+0.011
 sav+0.011
Neg logit contributions
ggy-0.010
 yes-0.010
ver-0.009
ggie-0.009
 doll-0.008
Token to
Token ID284
Feature activation+4.33e-01

Pos logit contributions
 habitat+0.002
 oceans+0.002
 exp+0.002
 glory+0.002
joy+0.002
Neg logit contributions
ggy-0.002
ggie-0.002
ver-0.002
 yes-0.002
 doll-0.002
Token grab
Token ID5552
Feature activation-5.82e-01

Pos logit contributions
 habitat+0.011
 exp+0.010
 sav+0.010
 oceans+0.010
 glory+0.010
Neg logit contributions
ggy-0.009
 yes-0.009
ver-0.009
ggie-0.009
 doll-0.008
Token the
Token ID262
Feature activation-8.72e-01

Pos logit contributions
ggy+0.013
ver+0.013
 yes+0.013
ggie+0.012
 doll+0.011
Neg logit contributions
 habitat-0.014
 oceans-0.013
 sav-0.013
ky-0.013
 exp-0.012
Token bird
Token ID6512
Feature activation-3.03e+00

Pos logit contributions
ver+0.018
ggy+0.017
 yes+0.017
ggie+0.016
 okay+0.014
Neg logit contributions
 habitat-0.023
 oceans-0.021
 horizon-0.021
 exp-0.021
 glory-0.021
Token.
Token ID13
Feature activation+3.64e-01

Pos logit contributions
 yes+0.087
ver+0.086
ggy+0.082
ggie+0.081
bled+0.076
Neg logit contributions
 habitat-0.049
 than-0.045
ky-0.044
 sav-0.041
 oceans-0.039
Token sw
Token ID1509
Feature activation+1.21e+00

Pos logit contributions
 habitat+0.033
 glory+0.031
 horizon+0.031
 oceans+0.030
 habitats+0.030
Neg logit contributions
 yes-0.017
ggy-0.017
ver-0.015
ggie-0.015
 else-0.014
Tokenam
Token ID321
Feature activation+7.70e-01

Pos logit contributions
 habitat+0.028
 horizon+0.026
 exp+0.026
 sav+0.026
 oceans+0.026
Neg logit contributions
ggy-0.028
 yes-0.027
ggie-0.026
ver-0.025
 doll-0.024
Token and
Token ID290
Feature activation+1.25e+00

Pos logit contributions
 habitat+0.018
 exp+0.016
 glory+0.016
 oceans+0.016
 horizon+0.016
Neg logit contributions
 yes-0.018
ggy-0.018
ver-0.017
ggie-0.017
 doll-0.016
Token sw
Token ID1509
Feature activation+1.08e+00

Pos logit contributions
 habitat+0.034
 horizon+0.031
 glory+0.031
 exp+0.030
 habitats+0.029
Neg logit contributions
 yes-0.026
ggy-0.024
ver-0.023
ggie-0.022
 doll-0.022
Tokenam
Token ID321
Feature activation+8.95e-01

Pos logit contributions
 habitat+0.025
 horizon+0.023
 exp+0.023
 oceans+0.022
 sav+0.022
Neg logit contributions
ggy-0.026
 yes-0.025
ggie-0.024
ver-0.023
 doll-0.022
Token until
Token ID1566
Feature activation+2.35e-01

Pos logit contributions
 habitat+0.023
 exp+0.021
 glory+0.020
 habitats+0.020
 horizon+0.020
Neg logit contributions
 yes-0.020
ggy-0.019
ggie-0.018
ver-0.018
 doll-0.017
Token she
Token ID673
Feature activation+3.85e-01

Pos logit contributions
 habitat+0.008
 exp+0.008
 glory+0.007
 oceans+0.007
 horizon+0.007
Neg logit contributions
 yes-0.003
ggy-0.003
ver-0.003
ggie-0.003
 doll-0.002
Token saw
Token ID2497
Feature activation-2.00e-01

Pos logit contributions
 habitat+0.012
 exp+0.010
 glory+0.010
 oceans+0.010
 horizon+0.010
Neg logit contributions
 yes-0.007
ggy-0.007
ver-0.006
ggie-0.006
 doll-0.006
Token a
Token ID257
Feature activation+2.93e-01

Pos logit contributions
ver+0.005
 yes+0.004
ggy+0.004
ggie+0.004
cher+0.004
Neg logit contributions
 habitat-0.005
 oceans-0.005
 hills-0.005
 mountains-0.005
 sav-0.004
Token cute
Token ID13779
Feature activation+1.46e+00

Pos logit contributions
 habitat+0.007
 exp+0.007
 horizon+0.007
 oceans+0.007
 sav+0.007
Neg logit contributions
 yes-0.006
ver-0.006
ggy-0.006
ggie-0.006
 doll-0.005
Token oct
Token ID19318
Feature activation-1.46e-02

Pos logit contributions
 habitat+0.042
 glory+0.038
 exp+0.038
 oceans+0.037
 horizon+0.037
Neg logit contributions
 yes-0.027
ggy-0.027
ggie-0.025
ver-0.024
 doll-0.024
Token she
Token ID673
Feature activation-5.61e-01

Pos logit contributions
ggy+0.047
tr+0.045
ggie+0.045
ery+0.044
ver+0.044
Neg logit contributions
 habitat-0.053
 sav-0.053
 oceans-0.053
 exp-0.052
joy-0.050
Token could
Token ID714
Feature activation-1.60e+00

Pos logit contributions
ggy+0.011
 yes+0.011
ggie+0.010
ver+0.009
 doll+0.009
Neg logit contributions
 habitat-0.015
 exp-0.014
ky-0.013
 sav-0.013
 oceans-0.013
Token use
Token ID779
Feature activation-1.32e+00

Pos logit contributions
ggy+0.029
 yes+0.029
ggie+0.028
ver+0.027
 doll+0.025
Neg logit contributions
 habitat-0.042
 exp-0.041
 horizon-0.038
 waters-0.038
 sav-0.038
Token the
Token ID262
Feature activation-1.03e+00

Pos logit contributions
 yes+0.024
ggy+0.024
ver+0.022
ggie+0.022
 doll+0.021
Neg logit contributions
 habitat-0.039
 exp-0.035
 oceans-0.034
 glory-0.034
 horizon-0.034
Token small
Token ID1402
Feature activation+5.25e-01

Pos logit contributions
 yes+0.015
ggy+0.015
ver+0.014
ggie+0.014
 doll+0.012
Neg logit contributions
 habitat-0.033
 exp-0.031
 oceans-0.030
 glory-0.030
 horizon-0.030
Token box
Token ID3091
Feature activation-3.51e+00

Pos logit contributions
 habitat+0.019
 exp+0.017
 habitats+0.017
 horizon+0.017
 sav+0.017
Neg logit contributions
 yes-0.007
ggy-0.006
 doll-0.006
ggie-0.006
ver-0.005
Token.
Token ID13
Feature activation-8.49e-01

Pos logit contributions
ggy+0.099
ggie+0.094
 yes+0.088
ver+0.086
balls+0.080
Neg logit contributions
 habitat-0.064
 glory-0.058
 oceans-0.056
 than-0.056
 ago-0.056
Token He
Token ID679
Feature activation-3.13e-01

Pos logit contributions
 yes+0.015
ggy+0.015
ggie+0.014
ver+0.014
 doll+0.013
Neg logit contributions
 habitat-0.025
 oceans-0.023
 glory-0.023
 horizon-0.023
ky-0.023
Token said
Token ID531
Feature activation-1.98e+00

Pos logit contributions
ggy+0.008
 yes+0.008
ggie+0.008
ver+0.007
 okay+0.007
Neg logit contributions
 habitat-0.006
 sav-0.005
 exp-0.005
ky-0.005
 waters-0.005
Token yes
Token ID3763
Feature activation+4.89e-01

Pos logit contributions
ggy+0.027
tr+0.026
ggie+0.026
ver+0.024
ery+0.024
Neg logit contributions
joy-0.050
 exp-0.050
 ago-0.050
 Now-0.048
 sav-0.048
Token.
Token ID13
Feature activation-4.54e-01

Pos logit contributions
 habitat+0.011
 exp+0.010
 oceans+0.009
 glory+0.009
 horizon+0.009
Neg logit contributions
 yes-0.012
ggy-0.012
ver-0.012
ggie-0.012
 doll-0.011
Token worked
Token ID3111
Feature activation+6.30e-01

Pos logit contributions
ggy+0.015
ggie+0.015
 yes+0.014
ver+0.014
 okay+0.013
Neg logit contributions
 habitat-0.014
 sav-0.013
ky-0.013
 exp-0.013
 oceans-0.012
Token hard
Token ID1327
Feature activation+2.78e+00

Pos logit contributions
 habitat+0.019
 exp+0.018
 horizon+0.017
 oceans+0.017
 glory+0.017
Neg logit contributions
 yes-0.011
ggy-0.011
ver-0.010
ggie-0.010
 doll-0.009
Token and
Token ID290
Feature activation+1.36e+00

Pos logit contributions
 habitat+0.082
 exp+0.075
 horizon+0.072
 habitats+0.070
 sav+0.070
Neg logit contributions
ver-0.050
 yes-0.049
ggy-0.048
ggie-0.045
balls-0.044
Token used
Token ID973
Feature activation-1.37e+00

Pos logit contributions
 habitat+0.037
 exp+0.033
 oceans+0.032
 glory+0.032
 horizon+0.032
Neg logit contributions
 yes-0.028
ggy-0.027
ver-0.026
ggie-0.026
 doll-0.024
Token many
Token ID867
Feature activation-3.30e-01

Pos logit contributions
ggy+0.030
 yes+0.030
ggie+0.028
ver+0.028
 doll+0.026
Neg logit contributions
 habitat-0.035
 exp-0.031
 oceans-0.031
 glory-0.031
 horizon-0.030
Token blocks
Token ID7021
Feature activation-3.66e+00

Pos logit contributions
 yes+0.006
ggy+0.006
 doll+0.006
ver+0.006
ggie+0.006
Neg logit contributions
 habitat-0.009
 exp-0.008
 horizon-0.008
 sav-0.008
 habitats-0.008
Token to
Token ID284
Feature activation-8.88e-01

Pos logit contributions
 yes+0.085
ggy+0.084
ver+0.080
ggie+0.079
 doll+0.075
Neg logit contributions
 habitat-0.089
 exp-0.079
 oceans-0.077
 glory-0.077
 horizon-0.076
Token make
Token ID787
Feature activation-1.90e+00

Pos logit contributions
ggy+0.017
 yes+0.016
ver+0.016
ggie+0.016
 okay+0.014
Neg logit contributions
 habitat-0.024
 exp-0.023
 oceans-0.023
 glory-0.022
 sav-0.022
Token the
Token ID262
Feature activation+2.64e-01

Pos logit contributions
ver+0.050
 yes+0.049
ggy+0.048
ggie+0.046
cher+0.044
Neg logit contributions
 oceans-0.038
 habitat-0.038
 hills-0.036
 glory-0.035
 sav-0.034
Token walls
Token ID7714
Feature activation-1.91e+00

Pos logit contributions
 habitat+0.006
 oceans+0.006
 exp+0.005
 glory+0.005
 horizon+0.005
Neg logit contributions
ggy-0.006
 yes-0.006
ver-0.006
ggie-0.006
 doll-0.005
Token,
Token ID11
Feature activation+6.63e-01

Pos logit contributions
ggy+0.047
 yes+0.047
ggie+0.045
ver+0.045
 doll+0.041
Neg logit contributions
 habitat-0.042
 oceans-0.038
 exp-0.038
 glory-0.037
 horizon-0.037
Token
Token ID198
Feature activation+2.16e-01

Pos logit contributions
 habitat+0.032
 glory+0.029
 habitats+0.028
 horizon+0.027
ky+0.027
Neg logit contributions
 yes-0.033
ggy-0.032
ver-0.030
 doll-0.030
 mom-0.030
Token
Token ID198
Feature activation+4.47e-01

Pos logit contributions
 habitat+0.004
 exp+0.004
 oceans+0.004
 sav+0.004
 horizon+0.003
Neg logit contributions
 yes-0.006
ggy-0.006
ggie-0.005
ver-0.005
 doll-0.005
TokenThe
Token ID464
Feature activation-1.33e+00

Pos logit contributions
 habitat+0.013
 exp+0.011
 glory+0.011
 oceans+0.011
 horizon+0.011
Neg logit contributions
ggy-0.009
 yes-0.009
ggie-0.008
ver-0.008
 doll-0.008
Token girl
Token ID2576
Feature activation-4.23e-02

Pos logit contributions
ver+0.036
ggy+0.034
ggie+0.033
 yes+0.031
cher+0.030
Neg logit contributions
 exp-0.028
 air-0.027
 habitat-0.027
 horizon-0.027
 oceans-0.025
Token and
Token ID290
Feature activation-2.32e+00

Pos logit contributions
 yes+0.001
ggy+0.001
ver+0.001
ggie+0.001
 doll+0.001
Neg logit contributions
 habitat-0.001
 exp-0.001
 oceans-0.001
 glory-0.001
 horizon-0.001
Token her
Token ID607
Feature activation-4.75e+00

Pos logit contributions
ver+0.059
ggy+0.059
 yes+0.058
ggie+0.057
cher+0.054
Neg logit contributions
 habitat-0.046
 exp-0.046
 oceans-0.043
 air-0.043
joy-0.043
Token friends
Token ID2460
Feature activation-6.25e-01

Pos logit contributions
ver+0.130
 yes+0.122
cher+0.122
ggie+0.114
ves+0.111
Neg logit contributions
 habitat-0.088
 waters-0.084
 wonders-0.084
 air-0.083
joy-0.080
Token looked
Token ID3114
Feature activation+1.61e+00

Pos logit contributions
ggy+0.013
 yes+0.013
ggie+0.012
ver+0.012
 doll+0.011
Neg logit contributions
 habitat-0.016
 exp-0.015
 oceans-0.014
 sav-0.014
ky-0.014
Token at
Token ID379
Feature activation-6.91e-02

Pos logit contributions
 habitat+0.048
 glory+0.042
 exp+0.041
 sav+0.041
 habitats+0.041
Neg logit contributions
 yes-0.030
ggy-0.028
ver-0.027
 doll-0.027
ggie-0.026
Token the
Token ID262
Feature activation+8.23e-01

Pos logit contributions
 yes+0.002
ggy+0.002
ver+0.002
ggie+0.002
cher+0.002
Neg logit contributions
 habitat-0.001
 exp-0.001
 oceans-0.001
 glory-0.001
 horizon-0.001
Token sky
Token ID6766
Feature activation+1.44e+00

Pos logit contributions
 habitat+0.015
 exp+0.012
 oceans+0.012
 glory+0.012
 horizon+0.012
Neg logit contributions
 yes-0.024
ggy-0.024
ver-0.023
ggie-0.023
 doll-0.022
Token home
Token ID1363
Feature activation+9.33e-02

Pos logit contributions
 habitat+0.029
 exp+0.025
 habitats+0.025
 glory+0.025
 oceans+0.025
Neg logit contributions
 yes-0.027
ggy-0.026
 doll-0.025
ver-0.025
ggie-0.024
Token,
Token ID11
Feature activation-2.00e+00

Pos logit contributions
 habitat+0.002
 exp+0.002
 oceans+0.002
 habitats+0.002
 glory+0.002
Neg logit contributions
 yes-0.002
ggy-0.002
ver-0.002
ggie-0.002
 doll-0.002
Token Aunt
Token ID38074
Feature activation-1.33e+00

Pos logit contributions
ggy+0.042
ver+0.042
ggie+0.041
ery+0.040
cher+0.040
Neg logit contributions
 sav-0.044
 glory-0.043
 habitat-0.043
 air-0.042
 horizon-0.042
Tokenie
Token ID494
Feature activation-6.97e-01

Pos logit contributions
ggy+0.029
ggie+0.027
 yes+0.027
ver+0.026
balls+0.024
Neg logit contributions
ky-0.032
 habitat-0.032
elly-0.030
 exp-0.029
az-0.029
Token gave
Token ID2921
Feature activation-1.86e+00

Pos logit contributions
ggy+0.015
 yes+0.015
ver+0.015
ggie+0.015
 doll+0.013
Neg logit contributions
 habitat-0.016
 sav-0.015
 exp-0.015
ky-0.014
 glory-0.014
Token Lily
Token ID20037
Feature activation-5.44e+00

Pos logit contributions
ggy+0.051
 yes+0.048
ggie+0.048
ver+0.048
keys+0.047
Neg logit contributions
 habitat-0.036
 air-0.033
ky-0.032
 sav-0.032
 oceans-0.031
Token a
Token ID257
Feature activation-3.31e+00

Pos logit contributions
ggy+0.110
 yes+0.105
ver+0.104
ggie+0.101
balls+0.090
Neg logit contributions
 habitat-0.141
 sav-0.127
ky-0.125
 exp-0.125
 oceans-0.125
Token big
Token ID1263
Feature activation-2.32e+00

Pos logit contributions
ggy+0.083
ggie+0.081
ver+0.079
keys+0.078
aches+0.075
Neg logit contributions
 exp-0.062
joy-0.058
 sav-0.057
 air-0.056
 habitat-0.053
Token hug
Token ID16225
Feature activation-1.02e+00

Pos logit contributions
ggy+0.044
 yes+0.043
ver+0.042
ggie+0.041
 doll+0.036
Neg logit contributions
 habitat-0.064
 exp-0.060
 sav-0.057
 horizon-0.057
 glory-0.057
Token and
Token ID290
Feature activation-3.79e-01

Pos logit contributions
 yes+0.029
ggy+0.028
ver+0.027
ggie+0.027
 doll+0.026
Neg logit contributions
 habitat-0.019
 exp-0.017
 oceans-0.016
 glory-0.016
 horizon-0.016
Token said
Token ID531
Feature activation-2.22e+00

Pos logit contributions
ver+0.009
ggy+0.009
ggie+0.009
 yes+0.008
ery+0.008
Neg logit contributions
 habitat-0.008
 sav-0.008
 exp-0.007
 glory-0.007
 waters-0.007
Token day
Token ID1110
Feature activation-2.01e+00

Pos logit contributions
 yes+0.011
ggy+0.010
ver+0.010
ggie+0.010
cher+0.009
Neg logit contributions
 habitat-0.008
 exp-0.007
 sav-0.007
 glory-0.007
 horizon-0.007
Token,
Token ID11
Feature activation-3.35e+00

Pos logit contributions
 yes+0.060
ggy+0.059
ggie+0.058
cher+0.057
isy+0.057
Neg logit contributions
 than-0.024
 habitat-0.023
 hills-0.023
 Now-0.023
 exp-0.023
Token he
Token ID339
Feature activation+3.90e-01

Pos logit contributions
ache+0.079
isy+0.076
cher+0.075
ery+0.075
ggy+0.075
Neg logit contributions
 hills-0.069
 than-0.065
 oceans-0.061
 Now-0.059
 mountains-0.059
Token found
Token ID1043
Feature activation-1.37e+00

Pos logit contributions
 habitat+0.010
 exp+0.009
 sav+0.009
 oceans+0.009
 glory+0.009
Neg logit contributions
 yes-0.008
ggy-0.008
ver-0.008
ggie-0.008
 doll-0.007
Token a
Token ID257
Feature activation-1.38e+00

Pos logit contributions
 yes+0.033
ver+0.032
ggy+0.031
keys+0.030
ggie+0.029
Neg logit contributions
 habitat-0.029
 air-0.028
 oceans-0.028
 hills-0.027
 sav-0.027
Token piece
Token ID3704
Feature activation-3.57e+00

Pos logit contributions
ver+0.035
owed+0.032
 yes+0.032
ggy+0.031
aches+0.030
Neg logit contributions
 exp-0.028
 habitat-0.027
 sav-0.027
 horizon-0.026
 ocean-0.026
Token of
Token ID286
Feature activation-1.42e+00

Pos logit contributions
 yes+0.078
ggy+0.075
ver+0.074
ggie+0.072
 okay+0.066
Neg logit contributions
 habitat-0.084
 than-0.076
ky-0.076
 sav-0.075
 horizon-0.075
Token rope
Token ID17182
Feature activation-1.08e+00

Pos logit contributions
ver+0.032
 yes+0.032
ggy+0.031
ggie+0.030
 okay+0.027
Neg logit contributions
 habitat-0.034
 sav-0.031
 glory-0.031
 exp-0.031
 oceans-0.030
Token on
Token ID319
Feature activation+1.48e+00

Pos logit contributions
 yes+0.024
ggy+0.023
ver+0.022
ggie+0.022
 doll+0.021
Neg logit contributions
 habitat-0.028
 exp-0.025
 oceans-0.024
 glory-0.024
 horizon-0.024
Token the
Token ID262
Feature activation+2.25e+00

Pos logit contributions
 habitat+0.042
 exp+0.038
 glory+0.037
 oceans+0.037
 horizon+0.036
Neg logit contributions
 yes-0.028
ggy-0.028
ggie-0.027
ver-0.026
 doll-0.025
Token ground
Token ID2323
Feature activation+1.76e+00

Pos logit contributions
 habitat+0.044
 exp+0.038
 glory+0.037
 oceans+0.037
 habitats+0.036
Neg logit contributions
ggy-0.062
 yes-0.062
ggie-0.060
ver-0.058
 doll-0.058