TOP ACTIVATIONS
MAX = 8.377

loved to swim around the coral reef with his friends .
She liked playing in the garden and looking at the flowers
picnic lunch here in the field ? '. His friend
. <|endoftext|> â T ie your shoes ,
loved playing outdoors in her garden . One day , when
things like trees , animals , and flowers . Suddenly she
friends . They played together in the water . But then
resa was a wealthy girl , whose parents owned a large
vegetables like lettuce , carrots , and tomatoes .
It included swimming and playing in the sand . It even
ter who played in the nearby pond . One
loved playing together in the garden . One day
lion who lived in a sunny forest . He was very
loved to swing in the garden . Every morning she 'd
in a hive near a garden full of fat yellow flowers
. <|endoftext|> â Come on , Mom my
an ot ter who played in the nearby pond .
loved to swim around the coral and explore all the hidden
. If you want to open
. It â s

MIN ACTIVATIONS
MIN = -7.074

the heavy bag had been fore shadow ed , and that
The wave had fore shadow ed L ola 's
We 'll help you get unst uck ." But
they didn 't get it unst uck . Just
there and wait . The fore shadow ing of the dull
. There were cans , wra ppers and bottles . Sara
, Billy accidentally turned the er aser too much and it
, but it was all fore shadow ed by the kind
could help get the car unst uck . The
eyes . She had been fore shadow ed about the power
The bad ending was fore shadow ed by Maggie 's
quickly helped Tim my get unst uck . She said ,
and Lily carefully put the therm ometer under her mom my
yard . He had been fore shadow ed about this bad
not want to give the chain . They liked the chain
The little girl took the er aser and starting running around
and pulls , but the box does not move . She
the floor and hugged the er aser tight . The er
that the zipper had become unst uck . She was relieved
, and Sue put the therm ometer in . They waited

INTERVAL 4.514 - 8.377
CONTAINS 0.281%

mom again . <|endoftext|> Once upon a time , there was
and sound . <|endoftext|> Once upon a time there was a
be friends . <|endoftext|> Once upon a time there was a
her work . <|endoftext|> Once upon a time , there was
a hug ! <|endoftext|> Once upon a time , there lived

INTERVAL 0.651 - 4.514
CONTAINS 30.934%

yes , but they had to be careful and come back
together . Just like you and me ." Sara hugged her
he made a new friend in the jungle . <|endoftext|> Once
, they heard some noises behind them . They turned around
?" They watched the bird for a little while before continuing

INTERVAL -3.211 - 0.651
CONTAINS 67.846%

never put them away . Her mom always told her to
, " Don 't worry , Lily . You can do
sang a song for Lily . Lily wanted to record the
the park to find someone and saw a bench . She
She woke up Tom . She showed him Bob o .

INTERVAL -7.074 - -3.211
CONTAINS 0.940%

?" L ily got up and brushed off her
happy and excited ! With the gem , they could play
" O uch !" cried Tim my .
to the lake . " Look Rachel , the lake is
on a ride . But then an idea came to her
Token loved
Token ID6151
Feature activation+1.52e+00

Pos logit contributions
 wedding+0.061
 visit+0.060
 parties+0.059
 pic+0.059
 appreciate+0.058
Neg logit contributions
aned-0.068
 collapsed-0.063
 fists-0.062
nown-0.060
 tipped-0.060
Token to
Token ID284
Feature activation+2.64e+00

Pos logit contributions
 appreciate+0.044
arium+0.041
|+0.041
 live+0.039
adows+0.038
Neg logit contributions
 fists-0.029
 off-0.027
aned-0.025
 heavier-0.024
 problem-0.024
Token swim
Token ID9422
Feature activation+1.40e+00

Pos logit contributions
Always+0.066
Em+0.065
arium+0.065
Sleep+0.063
 who+0.063
Neg logit contributions
 fists-0.050
 off-0.047
 pulls-0.047
aned-0.046
ered-0.045
Token around
Token ID1088
Feature activation+4.40e+00

Pos logit contributions
 appreciate+0.038
 wedding+0.037
 visit+0.035
 farm+0.034
 tale+0.033
Neg logit contributions
 off-0.030
ares-0.028
 firmly-0.027
 fists-0.027
ented-0.027
Token the
Token ID262
Feature activation+3.48e+00

Pos logit contributions
 appreciate+0.139
grand+0.130
 tale+0.123
forest+0.123
 wedding+0.122
Neg logit contributions
 off-0.077
 fists-0.071
 onto-0.065
 firmly-0.065
ares-0.063
Token coral
Token ID29537
Feature activation+6.28e+00

Pos logit contributions
 appreciate+0.075
 tale+0.067
 cherish+0.064
 visit+0.063
 who+0.063
Neg logit contributions
 off-0.085
 fists-0.085
ented-0.081
 problem-0.081
aned-0.080
Token reef
Token ID25088
Feature activation+4.66e+00

Pos logit contributions
Ell+0.117
 appreciate+0.114
grand+0.109
|+0.104
 visit+0.101
Neg logit contributions
 off-0.165
 hardest-0.160
ares-0.158
bled-0.157
 problem-0.154
Token with
Token ID351
Feature activation+1.67e+00

Pos logit contributions
 appreciate+0.122
 wedding+0.119
|+0.116
Ell+0.115
 visit+0.113
Neg logit contributions
 firmly-0.091
 off-0.089
 hardest-0.084
 fists-0.079
ares-0.079
Token his
Token ID465
Feature activation-1.77e-01

Pos logit contributions
 appreciate+0.048
 visit+0.048
 wedding+0.047
 farm+0.046
arium+0.046
Neg logit contributions
 fists-0.034
aned-0.031
ares-0.031
 off-0.029
 firmly-0.029
Token friends
Token ID2460
Feature activation+2.98e+00

Pos logit contributions
 fists+0.005
aned+0.005
ares+0.004
ented+0.004
 firmly+0.004
Neg logit contributions
 appreciate-0.004
 visit-0.004
 who-0.004
 wedding-0.004
 live-0.004
Token.
Token ID13
Feature activation+1.20e+00

Pos logit contributions
 appreciate+0.085
 visit+0.081
|+0.079
 wedding+0.079
 live+0.077
Neg logit contributions
 fists-0.060
 firmly-0.059
ula-0.057
ares-0.056
 off-0.056
Token She
Token ID1375
Feature activation+2.38e+00

Pos logit contributions
 wedding+0.012
 appreciate+0.012
 coral+0.012
 visit+0.011
 farm+0.011
Neg logit contributions
 fists-0.008
omm-0.007
ares-0.007
aned-0.007
 firmly-0.007
Token liked
Token ID8288
Feature activation+1.99e+00

Pos logit contributions
 appreciate+0.044
 visit+0.043
 coral+0.042
 wedding+0.041
 farm+0.039
Neg logit contributions
aned-0.068
 fists-0.065
 collapsed-0.062
 firmly-0.061
nown-0.061
Token playing
Token ID2712
Feature activation+1.89e+00

Pos logit contributions
 appreciate+0.053
 live+0.048
 visit+0.048
arium+0.047
|+0.046
Neg logit contributions
 fists-0.047
aned-0.041
 firmly-0.040
 off-0.040
ula-0.039
Token in
Token ID287
Feature activation+4.68e+00

Pos logit contributions
 appreciate+0.053
 habitats+0.046
 visit+0.046
 wedding+0.046
 cherish+0.045
Neg logit contributions
 off-0.037
 fists-0.037
 firmly-0.036
ula-0.036
bled-0.035
Token the
Token ID262
Feature activation+3.02e+00

Pos logit contributions
 appreciate+0.132
 tale+0.119
 wedding+0.118
 visit+0.118
arium+0.118
Neg logit contributions
 fists-0.100
aned-0.085
 off-0.085
ula-0.082
 firmly-0.082
Token garden
Token ID11376
Feature activation+6.06e+00

Pos logit contributions
 appreciate+0.068
 visit+0.059
arium+0.056
 who+0.056
 tale+0.054
Neg logit contributions
 fists-0.078
ented-0.075
 off-0.073
 problem-0.073
 heavier-0.072
Token and
Token ID290
Feature activation+3.34e+00

Pos logit contributions
 appreciate+0.180
|+0.170
Hop+0.167
Buzz+0.163
 visit+0.161
Neg logit contributions
 firmly-0.100
 off-0.091
 fists-0.090
 hardest-0.088
aned-0.086
Token looking
Token ID2045
Feature activation-9.36e-01

Pos logit contributions
 tale+0.075
arium+0.073
 appreciate+0.073
 wedding+0.071
 visit+0.071
Neg logit contributions
 fists-0.082
aned-0.077
 firmly-0.075
 off-0.071
 heavier-0.069
Token at
Token ID379
Feature activation+1.81e+00

Pos logit contributions
 fists+0.023
aned+0.022
ares+0.022
ented+0.021
 firmly+0.020
Neg logit contributions
 visit-0.025
 appreciate-0.025
 wedding-0.023
 farm-0.022
 who-0.022
Token the
Token ID262
Feature activation+1.72e+00

Pos logit contributions
 visit+0.041
 appreciate+0.040
 wedding+0.037
 live+0.036
 farm+0.036
Neg logit contributions
 fists-0.051
aned-0.050
ares-0.047
ented-0.046
 firmly-0.045
Token flowers
Token ID12734
Feature activation+3.12e+00

Pos logit contributions
 appreciate+0.035
 visit+0.035
arium+0.031
 live+0.031
 who+0.031
Neg logit contributions
 fists-0.050
ented-0.048
aned-0.046
ares-0.046
ula-0.045
Token picnic
Token ID35715
Feature activation+3.51e+00

Pos logit contributions
aned+0.031
 fists+0.030
ares+0.029
ented+0.028
 firmly+0.027
Neg logit contributions
 visit-0.026
 appreciate-0.026
 who-0.024
 live-0.023
 wedding-0.023
Token lunch
Token ID9965
Feature activation+3.13e+00

Pos logit contributions
 appreciate+0.080
 visit+0.073
 live+0.072
 coral+0.070
 who+0.067
Neg logit contributions
 fists-0.089
 firmly-0.089
ares-0.085
aned-0.085
ented-0.083
Token here
Token ID994
Feature activation+5.16e+00

Pos logit contributions
 appreciate+0.064
 visit+0.061
 live+0.058
 coral+0.057
 who+0.055
Neg logit contributions
aned-0.091
 fists-0.091
ares-0.089
 firmly-0.088
ented-0.086
Token in
Token ID287
Feature activation+4.21e+00

Pos logit contributions
 appreciate+0.111
 visit+0.107
 coral+0.106
 wedding+0.104
 farm+0.104
Neg logit contributions
 firmly-0.129
 fists-0.129
ares-0.127
aned-0.125
ented-0.122
Token the
Token ID262
Feature activation+2.69e+00

Pos logit contributions
 appreciate+0.101
 visit+0.092
 coral+0.091
Hop+0.091
 wedding+0.091
Neg logit contributions
 fists-0.102
ares-0.095
 firmly-0.095
ented-0.091
 off-0.091
Token field
Token ID2214
Feature activation+6.02e+00

Pos logit contributions
 appreciate+0.044
 visit+0.039
 who+0.038
 live+0.037
 celebrate+0.033
Neg logit contributions
 fists-0.090
ented-0.087
aned-0.085
 firmly-0.084
ares-0.082
Token?
Token ID30
Feature activation+1.12e+00

Pos logit contributions
 appreciate+0.134
 coral+0.128
Hop+0.127
 visit+0.127
 wedding+0.126
Neg logit contributions
 firmly-0.145
ares-0.139
 fists-0.137
aned-0.135
ented-0.133
Token'.
Token ID4458
Feature activation-5.57e-01

Pos logit contributions
 appreciate+0.028
 visit+0.027
 wedding+0.027
 coral+0.026
 farm+0.026
Neg logit contributions
 fists-0.027
ares-0.027
ented-0.026
aned-0.026
 firmly-0.025
Token
Token ID198
Feature activation+1.43e+00

Pos logit contributions
 fists+0.016
aned+0.016
ares+0.015
 firmly+0.015
ented+0.015
Neg logit contributions
 appreciate-0.012
 visit-0.011
 wedding-0.011
 farm-0.011
 coral-0.011
TokenHis
Token ID6653
Feature activation-2.60e+00

Pos logit contributions
 wedding+0.026
 appreciate+0.026
 visit+0.025
 coral+0.024
 live+0.024
Neg logit contributions
aned-0.046
 fists-0.043
 firmly-0.043
ula-0.043
ares-0.042
Token friend
Token ID1545
Feature activation-1.96e-01

Pos logit contributions
aned+0.108
ares+0.102
 fists+0.097
ented+0.096
uffed+0.095
Neg logit contributions
 visit-0.035
 farm-0.028
 wedding-0.026
 appreciate-0.026
 who-0.025
Token.
Token ID13
Feature activation+9.75e-01

Pos logit contributions
 visit+0.027
 appreciate+0.027
 wedding+0.025
 farm+0.025
 coral+0.025
Neg logit contributions
 fists-0.038
aned-0.037
ares-0.036
ented-0.034
 firmly-0.034
Token<|endoftext|>
Token ID50256
Feature activation+3.24e+00

Pos logit contributions
 wedding+0.017
 appreciate+0.017
 farm+0.016
 visit+0.016
 coral+0.016
Neg logit contributions
 fists-0.030
ares-0.030
omm-0.029
aned-0.029
 firmly-0.028
Tokenâ
Token ID22940
Feature activation+2.44e-01

Pos logit contributions
 appreciate+0.080
 wedding+0.077
 visit+0.074
 farm+0.072
 coral+0.072
Neg logit contributions
aned-0.078
 fists-0.077
ares-0.077
umbled-0.072
ula-0.071
Token
Token ID26391
Feature activation+2.13e-01

Pos logit contributions
 coral+0.006
 visit+0.006
 who+0.006
 farm+0.006
 appreciate+0.006
Neg logit contributions
aned-0.006
 fists-0.006
ares-0.006
ented-0.005
 firmly-0.005
Token
Token ID129
Feature activation+5.55e-02

Pos logit contributions
 appreciate+0.004
 coral+0.004
 wedding+0.004
 visit+0.003
 live+0.003
Neg logit contributions
 fists-0.007
aned-0.007
 firmly-0.006
ares-0.006
uffed-0.006
Token
Token ID241
Feature activation+5.98e+00

Pos logit contributions
 visit+0.001
 appreciate+0.001
 coral+0.001
 who+0.001
 wedding+0.001
Neg logit contributions
aned-0.001
 fists-0.001
ares-0.001
ented-0.001
 firmly-0.001
TokenT
Token ID51
Feature activation-8.27e-02

Pos logit contributions
 wedding+0.126
arium+0.123
 coral+0.119
 farm+0.116
 reef+0.112
Neg logit contributions
aned-0.163
ula-0.161
 fists-0.158
ares-0.156
umbled-0.153
Tokenie
Token ID494
Feature activation+1.65e+00

Pos logit contributions
aned+0.002
 fists+0.002
ares+0.002
ented+0.002
 firmly+0.002
Neg logit contributions
 visit-0.002
 appreciate-0.002
 who-0.002
 coral-0.002
 live-0.002
Token your
Token ID534
Feature activation-5.28e-02

Pos logit contributions
 appreciate+0.039
 visit+0.038
 coral+0.035
 wedding+0.035
 live+0.035
Neg logit contributions
 fists-0.044
aned-0.044
ares-0.040
 firmly-0.040
ented-0.040
Token shoes
Token ID10012
Feature activation+1.83e+00

Pos logit contributions
 fists+0.002
aned+0.001
ented+0.001
ares+0.001
 firmly+0.001
Neg logit contributions
 appreciate-0.001
 visit-0.001
 coral-0.001
 live-0.001
 who-0.001
Token,
Token ID11
Feature activation+3.04e+00

Pos logit contributions
 visit+0.040
 appreciate+0.039
 coral+0.038
 wedding+0.037
 farm+0.037
Neg logit contributions
aned-0.051
 fists-0.050
ares-0.048
ented-0.047
 firmly-0.046
Token loved
Token ID6151
Feature activation+2.48e+00

Pos logit contributions
 visit+0.048
 appreciate+0.047
 coral+0.044
 farm+0.043
 wedding+0.043
Neg logit contributions
aned-0.064
 fists-0.063
ares-0.059
ented-0.058
 firmly-0.058
Token playing
Token ID2712
Feature activation+1.64e+00

Pos logit contributions
 appreciate+0.055
 visit+0.053
arium+0.051
 live+0.050
 coral+0.049
Neg logit contributions
 fists-0.069
aned-0.066
 firmly-0.062
ares-0.061
ula-0.059
Token outdoors
Token ID24349
Feature activation+4.58e+00

Pos logit contributions
 appreciate+0.039
 visit+0.035
 wedding+0.032
arium+0.032
Sleep+0.031
Neg logit contributions
 fists-0.042
ula-0.041
 firmly-0.041
aned-0.040
ares-0.039
Token in
Token ID287
Feature activation+4.62e+00

Pos logit contributions
 appreciate+0.118
 visit+0.108
 live+0.098
 wedding+0.097
arium+0.097
Neg logit contributions
 fists-0.113
 firmly-0.109
aned-0.109
 off-0.100
ula-0.097
Token her
Token ID607
Feature activation+4.10e+00

Pos logit contributions
 appreciate+0.126
 wedding+0.118
 tale+0.116
 farm+0.112
Hop+0.111
Neg logit contributions
 fists-0.098
 off-0.085
 firmly-0.080
aned-0.078
ula-0.076
Token garden
Token ID11376
Feature activation+5.95e+00

Pos logit contributions
 appreciate+0.079
 visit+0.066
 live+0.065
 celebrate+0.064
|+0.060
Neg logit contributions
 fists-0.129
 firmly-0.117
ented-0.116
aned-0.111
 problem-0.109
Token.
Token ID13
Feature activation+2.22e+00

Pos logit contributions
|+0.175
 appreciate+0.174
Hop+0.168
Buzz+0.161
 visit+0.156
Neg logit contributions
 firmly-0.103
 off-0.093
 fists-0.088
aned-0.082
 heavier-0.080
Token One
Token ID1881
Feature activation+1.79e+00

Pos logit contributions
 appreciate+0.051
 coral+0.049
 wedding+0.048
 visit+0.047
 live+0.046
Neg logit contributions
 fists-0.058
omm-0.055
ares-0.055
aned-0.054
 firmly-0.053
Token day
Token ID1110
Feature activation-1.54e+00

Pos logit contributions
 appreciate+0.033
 visit+0.031
 coral+0.030
 wedding+0.030
 celebrate+0.029
Neg logit contributions
 fists-0.051
aned-0.049
 firmly-0.048
ares-0.048
ented-0.048
Token,
Token ID11
Feature activation-3.78e-01

Pos logit contributions
aned+0.044
 fists+0.044
ares+0.042
ented+0.040
 firmly+0.039
Neg logit contributions
 visit-0.036
 appreciate-0.035
 who-0.033
 live-0.032
 coral-0.031
Token when
Token ID618
Feature activation-1.57e+00

Pos logit contributions
 fists+0.010
aned+0.009
 firmly+0.009
ares+0.009
ented+0.009
Neg logit contributions
 appreciate-0.009
 visit-0.009
 coral-0.009
 wedding-0.009
 farm-0.008
Token things
Token ID1243
Feature activation+1.97e+00

Pos logit contributions
 appreciate+0.036
 visit+0.035
 wedding+0.033
 celebrate+0.033
arium+0.032
Neg logit contributions
 fists-0.049
aned-0.047
ares-0.044
ented-0.044
 firmly-0.042
Token like
Token ID588
Feature activation+3.20e+00

Pos logit contributions
 visit+0.043
 appreciate+0.042
 wedding+0.039
 farm+0.039
 coral+0.039
Neg logit contributions
aned-0.054
 fists-0.054
ares-0.053
 firmly-0.051
ented-0.051
Token trees
Token ID7150
Feature activation+3.19e+00

Pos logit contributions
 appreciate+0.066
 visit+0.065
 wedding+0.057
 live+0.056
 who+0.056
Neg logit contributions
 fists-0.096
aned-0.092
ares-0.087
 firmly-0.087
ented-0.087
Token,
Token ID11
Feature activation+5.09e+00

Pos logit contributions
 appreciate+0.079
 visit+0.075
 wedding+0.070
 celebrate+0.068
arium+0.067
Neg logit contributions
aned-0.077
 fists-0.077
 firmly-0.073
ares-0.073
ented-0.071
Token animals
Token ID4695
Feature activation+3.82e+00

Pos logit contributions
 appreciate+0.111
arium+0.109
 visit+0.108
 wedding+0.101
|+0.097
Neg logit contributions
 fists-0.127
 heavier-0.121
aned-0.112
 upside-0.108
 firmly-0.108
Token,
Token ID11
Feature activation+5.93e+00

Pos logit contributions
 appreciate+0.095
 visit+0.093
 wedding+0.088
|+0.087
 celebrate+0.086
Neg logit contributions
 fists-0.085
 firmly-0.082
aned-0.081
ented-0.079
ares-0.078
Token and
Token ID290
Feature activation+3.92e+00

Pos logit contributions
 appreciate+0.151
arium+0.143
|+0.142
 visit+0.141
 wedding+0.138
Neg logit contributions
 fists-0.127
 heavier-0.114
aned-0.108
 off-0.108
 firmly-0.108
Token flowers
Token ID12734
Feature activation+3.53e+00

Pos logit contributions
arium+0.081
 appreciate+0.080
 visit+0.080
|+0.077
 wedding+0.075
Neg logit contributions
 fists-0.103
 heavier-0.091
 off-0.088
ented-0.088
 firmly-0.087
Token.
Token ID13
Feature activation+8.13e-01

Pos logit contributions
 appreciate+0.091
 visit+0.088
|+0.082
 wedding+0.082
 coral+0.080
Neg logit contributions
 firmly-0.074
aned-0.073
ier-0.071
 fists-0.071
 off-0.070
Token Suddenly
Token ID24975
Feature activation-2.69e+00

Pos logit contributions
 coral+0.021
 wedding+0.020
 island+0.020
 appreciate+0.020
 reef+0.020
Neg logit contributions
 fists-0.018
aned-0.017
omm-0.017
ares-0.016
ented-0.016
Token she
Token ID673
Feature activation-8.11e-01

Pos logit contributions
aned+0.078
 fists+0.077
ares+0.074
ented+0.071
 firmly+0.068
Neg logit contributions
 visit-0.062
 appreciate-0.059
 who-0.056
 live-0.055
 coral-0.054
Token friends
Token ID2460
Feature activation+2.70e+00

Pos logit contributions
 visit+0.010
 appreciate+0.010
 live+0.009
 coral+0.009
 wedding+0.009
Neg logit contributions
aned-0.013
 fists-0.013
ares-0.012
 firmly-0.012
ented-0.012
Token.
Token ID13
Feature activation+1.83e-01

Pos logit contributions
 appreciate+0.079
 visit+0.076
 wedding+0.075
 farm+0.074
 celebrate+0.070
Neg logit contributions
 firmly-0.052
ares-0.050
 fists-0.049
aned-0.048
ula-0.046
Token They
Token ID1119
Feature activation+2.85e+00

Pos logit contributions
 appreciate+0.004
 visit+0.003
 wedding+0.003
 live+0.003
 coral+0.003
Neg logit contributions
 fists-0.006
aned-0.006
ares-0.005
ented-0.005
 firmly-0.005
Token played
Token ID2826
Feature activation+1.86e+00

Pos logit contributions
 visit+0.058
 farm+0.056
 appreciate+0.056
 wedding+0.056
 heaven+0.056
Neg logit contributions
 fists-0.074
aned-0.072
ares-0.069
 firmly-0.066
ented-0.066
Token together
Token ID1978
Feature activation+4.87e+00

Pos logit contributions
 appreciate+0.054
 wedding+0.052
grand+0.050
 visit+0.049
forest+0.048
Neg logit contributions
bled-0.037
 off-0.036
 fists-0.035
 firmly-0.035
aned-0.033
Token in
Token ID287
Feature activation+5.90e+00

Pos logit contributions
 appreciate+0.110
 visit+0.103
Sleep+0.095
 live+0.095
 wedding+0.094
Neg logit contributions
 fists-0.135
aned-0.130
 firmly-0.126
ares-0.123
 off-0.120
Token the
Token ID262
Feature activation+3.38e+00

Pos logit contributions
 appreciate+0.183
Sleep+0.176
 wedding+0.176
des+0.173
ugg+0.172
Neg logit contributions
 fists-0.099
 off-0.078
 upside-0.064
 firmly-0.063
 brakes-0.063
Token water
Token ID1660
Feature activation+4.31e+00

Pos logit contributions
 appreciate+0.074
 who+0.062
 visit+0.060
 cherish+0.057
 live+0.056
Neg logit contributions
 fists-0.088
 off-0.085
 problem-0.084
 hardest-0.080
ented-0.080
Token.
Token ID13
Feature activation+1.55e+00

Pos logit contributions
 appreciate+0.110
 visit+0.106
 wedding+0.097
|+0.097
Sleep+0.096
Neg logit contributions
aned-0.093
 fists-0.092
 firmly-0.090
ares-0.088
 off-0.087
Token But
Token ID887
Feature activation+7.60e-01

Pos logit contributions
 appreciate+0.033
 wedding+0.031
 visit+0.030
 live+0.029
 tale+0.028
Neg logit contributions
 fists-0.045
aned-0.043
ares-0.042
ented-0.041
 firmly-0.039
Token then
Token ID788
Feature activation-1.21e+00

Pos logit contributions
 visit+0.017
 appreciate+0.017
 wedding+0.015
 who+0.015
 live+0.015
Neg logit contributions
 fists-0.022
aned-0.022
ares-0.020
ented-0.020
 firmly-0.020
Tokenresa
Token ID14625
Feature activation+3.00e+00

Pos logit contributions
 appreciate+0.097
 visit+0.089
arium+0.087
 wedding+0.084
 live+0.083
Neg logit contributions
 fists-0.091
ares-0.082
ented-0.082
 firmly-0.081
aned-0.080
Token was
Token ID373
Feature activation+2.21e+00

Pos logit contributions
 appreciate+0.074
 visit+0.072
 coral+0.066
 live+0.066
 wedding+0.066
Neg logit contributions
 fists-0.074
aned-0.071
 firmly-0.069
ented-0.066
ares-0.066
Token a
Token ID257
Feature activation+3.64e+00

Pos logit contributions
 visit+0.048
 appreciate+0.047
 coral+0.043
 live+0.042
 who+0.042
Neg logit contributions
 fists-0.065
aned-0.065
ares-0.061
ented-0.060
 firmly-0.059
Token wealthy
Token ID11574
Feature activation+1.72e+00

Pos logit contributions
 appreciate+0.087
 visit+0.083
 live+0.080
 coral+0.078
arium+0.077
Neg logit contributions
 fists-0.096
aned-0.088
ented-0.088
 firmly-0.087
ares-0.084
Token girl
Token ID2576
Feature activation+3.35e+00

Pos logit contributions
 appreciate+0.040
 visit+0.039
 live+0.036
 coral+0.036
arium+0.034
Neg logit contributions
 fists-0.046
aned-0.044
ented-0.043
 firmly-0.042
ares-0.042
Token,
Token ID11
Feature activation+5.87e+00

Pos logit contributions
 appreciate+0.060
 visit+0.057
 coral+0.055
 live+0.050
 reef+0.048
Neg logit contributions
 fists-0.103
 firmly-0.101
aned-0.098
ented-0.098
ares-0.097
Token whose
Token ID3025
Feature activation+9.01e-01

Pos logit contributions
 appreciate+0.074
 coral+0.072
 wedding+0.068
 visit+0.066
 farm+0.063
Neg logit contributions
 fists-0.199
 firmly-0.199
aned-0.191
ented-0.184
nown-0.181
Token parents
Token ID3397
Feature activation+2.65e+00

Pos logit contributions
 appreciate+0.019
 coral+0.019
 visit+0.018
 who+0.018
arium+0.017
Neg logit contributions
 fists-0.025
ented-0.023
ares-0.023
aned-0.023
 firmly-0.022
Token owned
Token ID6898
Feature activation+1.86e+00

Pos logit contributions
 coral+0.053
 visit+0.052
 appreciate+0.050
 farm+0.049
arium+0.048
Neg logit contributions
aned-0.074
 fists-0.072
ares-0.070
ented-0.069
 firmly-0.069
Token a
Token ID257
Feature activation+2.80e+00

Pos logit contributions
 visit+0.038
 appreciate+0.037
 live+0.034
 coral+0.033
 who+0.033
Neg logit contributions
 fists-0.057
aned-0.056
ares-0.054
ented-0.052
 firmly-0.052
Token large
Token ID1588
Feature activation+2.28e+00

Pos logit contributions
 appreciate+0.061
 visit+0.059
 live+0.054
 who+0.054
 coral+0.053
Neg logit contributions
 fists-0.080
aned-0.076
ented-0.073
ares-0.073
 firmly-0.073
Token vegetables
Token ID13701
Feature activation+1.51e+00

Pos logit contributions
 appreciate+0.033
 visit+0.032
arium+0.030
 who+0.030
 live+0.029
Neg logit contributions
 fists-0.033
aned-0.031
ares-0.030
ented-0.028
 firmly-0.028
Token like
Token ID588
Feature activation+2.93e+00

Pos logit contributions
 visit+0.032
 appreciate+0.032
 live+0.028
 wedding+0.028
 coral+0.028
Neg logit contributions
 fists-0.044
aned-0.043
ares-0.041
 firmly-0.040
ented-0.040
Token lettuce
Token ID39406
Feature activation+1.92e+00

Pos logit contributions
 appreciate+0.067
 visit+0.065
 live+0.058
 who+0.057
arium+0.056
Neg logit contributions
 fists-0.082
aned-0.078
ares-0.075
 firmly-0.074
ented-0.073
Token,
Token ID11
Feature activation+5.45e+00

Pos logit contributions
 appreciate+0.044
 visit+0.044
 live+0.038
 celebrate+0.037
 wedding+0.037
Neg logit contributions
 fists-0.052
aned-0.052
ares-0.049
 firmly-0.049
ented-0.048
Token carrots
Token ID34397
Feature activation+1.97e+00

Pos logit contributions
 appreciate+0.137
 visit+0.132
arium+0.124
 live+0.121
|+0.119
Neg logit contributions
 fists-0.136
aned-0.125
 heavier-0.123
 firmly-0.122
ented-0.117
Token,
Token ID11
Feature activation+5.85e+00

Pos logit contributions
 appreciate+0.043
 visit+0.042
 wedding+0.037
 live+0.037
 coral+0.037
Neg logit contributions
 fists-0.056
aned-0.055
ares-0.053
 firmly-0.052
ented-0.052
Token and
Token ID290
Feature activation+4.08e+00

Pos logit contributions
 appreciate+0.153
 visit+0.143
arium+0.136
|+0.135
 live+0.134
Neg logit contributions
 fists-0.140
aned-0.130
 firmly-0.125
 heavier-0.124
ented-0.119
Token tomatoes
Token ID23972
Feature activation+1.58e+00

Pos logit contributions
 appreciate+0.096
 visit+0.095
arium+0.093
|+0.089
 live+0.086
Neg logit contributions
 fists-0.106
 heavier-0.092
aned-0.092
ented-0.090
 firmly-0.090
Token.
Token ID13
Feature activation-1.54e-01

Pos logit contributions
 appreciate+0.036
 visit+0.036
 coral+0.031
 live+0.031
 wedding+0.031
Neg logit contributions
aned-0.043
 fists-0.042
ares-0.041
ented-0.040
 firmly-0.040
Token
Token ID220
Feature activation+3.99e-01

Pos logit contributions
 fists+0.005
aned+0.005
ares+0.005
ented+0.004
 firmly+0.004
Neg logit contributions
 appreciate-0.003
 visit-0.003
 live-0.003
 coral-0.003
 wedding-0.003
Token
Token ID198
Feature activation+2.01e+00

Pos logit contributions
 visit+0.006
 appreciate+0.006
 wedding+0.005
 coral+0.005
 farm+0.005
Neg logit contributions
aned-0.014
 fists-0.014
ares-0.014
ented-0.013
 firmly-0.013
Token It
Token ID632
Feature activation+9.84e-01

Pos logit contributions
 wedding+0.014
 appreciate+0.014
 tale+0.013
 visit+0.013
 coral+0.013
Neg logit contributions
 fists-0.012
ares-0.011
aned-0.011
omm-0.010
ented-0.010
Token included
Token ID3017
Feature activation+2.80e+00

Pos logit contributions
 appreciate+0.028
 visit+0.027
 wedding+0.026
 celebrate+0.025
 farm+0.025
Neg logit contributions
aned-0.020
 fists-0.020
ares-0.018
ented-0.018
 collapsed-0.017
Token swimming
Token ID14899
Feature activation+3.06e+00

Pos logit contributions
 appreciate+0.065
 visit+0.064
 farm+0.058
arium+0.058
|+0.057
Neg logit contributions
 fists-0.070
bled-0.069
aned-0.065
ula-0.065
 off-0.064
Token and
Token ID290
Feature activation+4.27e+00

Pos logit contributions
 appreciate+0.073
 visit+0.071
 wedding+0.070
 farm+0.066
 heaven+0.066
Neg logit contributions
 fists-0.073
bled-0.072
aned-0.072
ares-0.070
ented-0.069
Token playing
Token ID2712
Feature activation+2.78e+00

Pos logit contributions
 visit+0.099
 appreciate+0.098
 tale+0.094
arium+0.092
 who+0.092
Neg logit contributions
 fists-0.107
aned-0.101
bled-0.101
ula-0.095
 firmly-0.093
Token in
Token ID287
Feature activation+5.84e+00

Pos logit contributions
 appreciate+0.075
 visit+0.071
grand+0.068
 wedding+0.067
forest+0.066
Neg logit contributions
bled-0.061
ula-0.055
 off-0.055
ares-0.054
 firmly-0.052
Token the
Token ID262
Feature activation+4.08e+00

Pos logit contributions
 tale+0.187
 appreciate+0.176
 wedding+0.173
forest+0.171
adows+0.170
Neg logit contributions
 off-0.083
 fists-0.071
 heavier-0.069
ula-0.068
 upside-0.068
Token sand
Token ID6450
Feature activation+3.72e+00

Pos logit contributions
 appreciate+0.102
 visit+0.099
 tale+0.095
 who+0.093
arium+0.090
Neg logit contributions
 fists-0.089
ented-0.087
 off-0.084
bled-0.083
aned-0.083
Token.
Token ID13
Feature activation+1.34e+00

Pos logit contributions
 appreciate+0.101
 visit+0.095
|+0.086
Hop+0.086
Sleep+0.086
Neg logit contributions
aned-0.080
ier-0.078
ares-0.077
 fists-0.076
 firmly-0.075
Token It
Token ID632
Feature activation+1.46e+00

Pos logit contributions
 appreciate+0.033
 wedding+0.032
 tale+0.030
 visit+0.030
 coral+0.029
Neg logit contributions
 fists-0.034
aned-0.033
ares-0.031
ented-0.030
omm-0.030
Token even
Token ID772
Feature activation+1.50e+00

Pos logit contributions
 appreciate+0.040
 visit+0.040
 wedding+0.038
 farm+0.037
 who+0.036
Neg logit contributions
aned-0.031
 fists-0.031
ares-0.028
ented-0.027
bled-0.026
Tokenter
Token ID353
Feature activation+2.54e+00

Pos logit contributions
ares+0.027
ented+0.026
 fists+0.026
ula+0.026
ier+0.026
Neg logit contributions
 visit-0.043
 appreciate-0.042
 wedding-0.038
 farm-0.038
 coral-0.038
Token who
Token ID508
Feature activation+1.58e+00

Pos logit contributions
 visit+0.059
 appreciate+0.058
 celebrate+0.053
|+0.052
 wedding+0.052
Neg logit contributions
aned-0.059
 fists-0.058
ula-0.057
ares-0.056
aser-0.056
Token played
Token ID2826
Feature activation+2.17e+00

Pos logit contributions
 visit+0.025
 appreciate+0.024
 wedding+0.023
 coral+0.022
 farm+0.022
Neg logit contributions
 fists-0.050
aned-0.049
ares-0.046
 firmly-0.046
ented-0.046
Token in
Token ID287
Feature activation+5.68e+00

Pos logit contributions
 appreciate+0.062
 wedding+0.061
grand+0.059
 visit+0.058
 farm+0.057
Neg logit contributions
bled-0.040
 off-0.039
ula-0.037
 firmly-0.037
 upside-0.037
Token the
Token ID262
Feature activation+2.96e+00

Pos logit contributions
 appreciate+0.176
 wedding+0.175
ugg+0.171
Sleep+0.166
grand+0.165
Neg logit contributions
 off-0.077
 upside-0.066
 fists-0.066
 firmly-0.063
 heavier-0.059
Token nearby
Token ID6716
Feature activation+5.80e+00

Pos logit contributions
 appreciate+0.059
 who+0.053
 visit+0.053
arium+0.049
|+0.048
Neg logit contributions
ented-0.074
 fists-0.072
 off-0.072
 firmly-0.069
 problem-0.068
Token pond
Token ID16723
Feature activation+5.19e+00

Pos logit contributions
 appreciate+0.120
 cherish+0.097
Sleep+0.096
Always+0.090
 visit+0.087
Neg logit contributions
 off-0.140
 fists-0.137
 problem-0.135
ented-0.131
 hardest-0.130
Token.
Token ID13
Feature activation+2.20e+00

Pos logit contributions
 appreciate+0.145
 visit+0.143
 wedding+0.136
|+0.132
Sleep+0.130
Neg logit contributions
 firmly-0.099
 off-0.094
aned-0.091
ares-0.087
bled-0.087
Token
Token ID198
Feature activation+3.34e+00

Pos logit contributions
 appreciate+0.059
 wedding+0.058
 tale+0.058
 cherish+0.053
 coral+0.053
Neg logit contributions
omm-0.041
ares-0.040
 fists-0.039
aned-0.039
 firmly-0.037
Token
Token ID198
Feature activation+1.50e+00

Pos logit contributions
 wedding+0.074
 coral+0.071
 appreciate+0.070
 farm+0.064
 visit+0.064
Neg logit contributions
aned-0.088
ares-0.086
ula-0.083
 firmly-0.082
 fists-0.080
TokenOne
Token ID3198
Feature activation+1.79e+00

Pos logit contributions
 wedding+0.033
 appreciate+0.031
 coral+0.029
 tale+0.029
 parties+0.029
Neg logit contributions
aned-0.039
nown-0.036
 firmly-0.036
ares-0.034
ula-0.034
Token loved
Token ID6151
Feature activation+2.11e+00

Pos logit contributions
 visit+0.047
 farm+0.045
arium+0.044
 wedding+0.044
 pic+0.042
Neg logit contributions
aned-0.062
 fists-0.062
 firmly-0.058
ented-0.058
bled-0.058
Token playing
Token ID2712
Feature activation+1.58e+00

Pos logit contributions
 appreciate+0.056
arium+0.055
 live+0.051
|+0.051
 visit+0.050
Neg logit contributions
 fists-0.044
 off-0.039
aned-0.037
 firmly-0.035
 problem-0.035
Token together
Token ID1978
Feature activation+3.67e+00

Pos logit contributions
 appreciate+0.044
 wedding+0.039
Sleep+0.039
 visit+0.039
 Sleep+0.038
Neg logit contributions
bled-0.030
 fists-0.029
 firmly-0.028
ula-0.028
driver-0.028
Token in
Token ID287
Feature activation+4.60e+00

Pos logit contributions
 appreciate+0.083
 visit+0.083
 wedding+0.074
 live+0.073
 coral+0.071
Neg logit contributions
 fists-0.100
aned-0.098
 firmly-0.095
ares-0.094
ented-0.090
Token the
Token ID262
Feature activation+3.44e+00

Pos logit contributions
 appreciate+0.132
 tale+0.129
Hop+0.129
 wedding+0.127
Always+0.125
Neg logit contributions
 fists-0.082
 off-0.062
ula-0.061
 collapse-0.058
 heavier-0.058
Token garden
Token ID11376
Feature activation+5.77e+00

Pos logit contributions
 appreciate+0.074
 cherish+0.062
 who+0.061
 visit+0.057
arium+0.056
Neg logit contributions
 problem-0.086
 fists-0.085
ented-0.082
 off-0.081
 breaks-0.080
Token.
Token ID13
Feature activation+1.68e+00

Pos logit contributions
Hop+0.174
 appreciate+0.170
Buzz+0.166
|+0.162
Sleep+0.161
Neg logit contributions
 firmly-0.085
 neither-0.079
ier-0.075
 hardest-0.075
 fists-0.074
Token
Token ID198
Feature activation+2.98e+00

Pos logit contributions
 appreciate+0.039
 wedding+0.037
 live+0.036
 visit+0.035
thank+0.035
Neg logit contributions
 fists-0.041
ares-0.041
ented-0.038
omm-0.037
aned-0.037
Token
Token ID198
Feature activation+1.30e+00

Pos logit contributions
 wedding+0.060
 appreciate+0.059
 coral+0.055
 visit+0.055
 celebrate+0.053
Neg logit contributions
ares-0.083
aned-0.080
ula-0.079
 fists-0.077
 firmly-0.075
TokenOne
Token ID3198
Feature activation+1.62e+00

Pos logit contributions
 wedding+0.026
 visit+0.025
 appreciate+0.025
 bask+0.024
 live+0.024
Neg logit contributions
ares-0.035
aned-0.033
ula-0.033
 firmly-0.032
ented-0.032
Token day
Token ID1110
Feature activation-1.85e+00

Pos logit contributions
 appreciate+0.029
 visit+0.029
 coral+0.028
 wedding+0.028
 hunt+0.027
Neg logit contributions
 fists-0.043
ares-0.042
ented-0.042
aned-0.041
ula-0.041
Token lion
Token ID18744
Feature activation+3.77e+00

Pos logit contributions
 appreciate+0.053
arium+0.051
 coral+0.051
 visit+0.050
 wedding+0.049
Neg logit contributions
 fists-0.066
aned-0.063
 firmly-0.060
ares-0.059
ented-0.058
Token who
Token ID508
Feature activation+2.96e+00

Pos logit contributions
 appreciate+0.089
 visit+0.087
 coral+0.080
 wedding+0.078
 farm+0.077
Neg logit contributions
 fists-0.102
aned-0.101
ares-0.095
 firmly-0.091
ented-0.089
Token lived
Token ID5615
Feature activation+3.44e+00

Pos logit contributions
 visit+0.057
 appreciate+0.055
 wedding+0.053
 farm+0.051
 coral+0.051
Neg logit contributions
 fists-0.088
aned-0.088
ares-0.082
 firmly-0.080
ented-0.079
Token in
Token ID287
Feature activation+4.48e+00

Pos logit contributions
 appreciate+0.080
 visit+0.078
 wedding+0.074
 farm+0.071
 coral+0.069
Neg logit contributions
 fists-0.092
aned-0.090
 firmly-0.088
ares-0.086
bled-0.084
Token a
Token ID257
Feature activation+4.31e+00

Pos logit contributions
 appreciate+0.113
 wedding+0.105
 visit+0.101
 coral+0.097
 farm+0.096
Neg logit contributions
 fists-0.113
aned-0.094
 firmly-0.091
 off-0.086
 problem-0.084
Token sunny
Token ID27737
Feature activation+5.76e+00

Pos logit contributions
 appreciate+0.106
 visit+0.090
thank+0.087
Always+0.087
adows+0.086
Neg logit contributions
 fists-0.103
 problem-0.102
 firmly-0.094
ented-0.094
nown-0.088
Token forest
Token ID8222
Feature activation+5.01e+00

Pos logit contributions
 appreciate+0.124
 cultures+0.105
 bask+0.100
Sleep+0.099
 cherish+0.098
Neg logit contributions
 problem-0.132
 fists-0.129
 firmly-0.125
 off-0.123
 collapsed-0.119
Token.
Token ID13
Feature activation+2.55e+00

Pos logit contributions
 appreciate+0.132
 visit+0.128
 wedding+0.125
 celebrate+0.121
 coral+0.118
Neg logit contributions
 firmly-0.110
aned-0.108
 fists-0.106
ier-0.090
 heavier-0.088
Token He
Token ID679
Feature activation+2.70e+00

Pos logit contributions
 appreciate+0.063
 wedding+0.061
 visit+0.059
 coral+0.056
 live+0.056
Neg logit contributions
 fists-0.062
aned-0.059
ares-0.058
omm-0.057
 firmly-0.055
Token was
Token ID373
Feature activation+1.30e+00

Pos logit contributions
 appreciate+0.058
 visit+0.058
 wedding+0.054
 celebrate+0.053
 coral+0.053
Neg logit contributions
 fists-0.074
aned-0.073
 firmly-0.067
ented-0.064
nown-0.064
Token very
Token ID845
Feature activation-1.71e-01

Pos logit contributions
 visit+0.030
 appreciate+0.030
 coral+0.027
 wedding+0.027
arium+0.027
Neg logit contributions
 fists-0.036
aned-0.035
 firmly-0.032
ented-0.032
ares-0.032
Token loved
Token ID6151
Feature activation+2.27e+00

Pos logit contributions
 coral+0.048
 appreciate+0.047
 visit+0.046
arium+0.044
 farm+0.044
Neg logit contributions
aned-0.082
 fists-0.080
 firmly-0.075
ented-0.075
nown-0.074
Token to
Token ID284
Feature activation+3.12e+00

Pos logit contributions
 appreciate+0.054
arium+0.051
 live+0.049
 visit+0.049
 coral+0.048
Neg logit contributions
 fists-0.058
aned-0.054
 firmly-0.050
 off-0.049
ares-0.049
Token swing
Token ID9628
Feature activation+9.38e-01

Pos logit contributions
arium+0.048
 coral+0.043
 appreciate+0.041
 who+0.041
 farm+0.040
Neg logit contributions
 fists-0.102
aned-0.097
 firmly-0.093
ares-0.092
 off-0.090
Token in
Token ID287
Feature activation+4.37e+00

Pos logit contributions
 visit+0.022
 appreciate+0.022
 who+0.020
 live+0.020
 coral+0.020
Neg logit contributions
aned-0.026
 fists-0.026
ares-0.025
ented-0.024
 firmly-0.023
Token the
Token ID262
Feature activation+3.60e+00

Pos logit contributions
 appreciate+0.096
 visit+0.094
 wedding+0.087
 coral+0.086
arium+0.086
Neg logit contributions
 fists-0.125
aned-0.120
ares-0.114
 firmly-0.112
ented-0.111
Token garden
Token ID11376
Feature activation+5.75e+00

Pos logit contributions
 appreciate+0.062
 visit+0.057
 live+0.052
 coral+0.052
arium+0.051
Neg logit contributions
 fists-0.121
aned-0.114
ented-0.113
ares-0.110
 firmly-0.109
Token.
Token ID13
Feature activation+1.20e+00

Pos logit contributions
 appreciate+0.158
|+0.153
Buzz+0.148
Hop+0.146
 visit+0.141
Neg logit contributions
 firmly-0.118
 fists-0.109
aned-0.107
 off-0.101
ented-0.098
Token Every
Token ID3887
Feature activation+2.34e+00

Pos logit contributions
 appreciate+0.026
 wedding+0.025
 visit+0.025
 coral+0.024
 who+0.024
Neg logit contributions
 fists-0.032
ares-0.031
omm-0.031
aned-0.030
ula-0.029
Token morning
Token ID3329
Feature activation-1.26e+00

Pos logit contributions
 appreciate+0.037
 visit+0.035
 coral+0.033
 who+0.032
 live+0.032
Neg logit contributions
 fists-0.080
aned-0.079
ares-0.075
 firmly-0.074
ented-0.073
Token she
Token ID673
Feature activation+2.09e+00

Pos logit contributions
aned+0.037
 fists+0.037
ares+0.035
ented+0.034
 firmly+0.033
Neg logit contributions
 visit-0.028
 appreciate-0.027
 who-0.025
 live-0.025
 wedding-0.025
Token'd
Token ID1549
Feature activation+3.30e+00

Pos logit contributions
 appreciate+0.044
 visit+0.043
 coral+0.042
 live+0.040
arium+0.039
Neg logit contributions
aned-0.059
 fists-0.058
ented-0.055
ares-0.054
 firmly-0.054
Token in
Token ID287
Feature activation+4.04e+00

Pos logit contributions
 appreciate+0.075
 visit+0.072
 wedding+0.070
 farm+0.066
 celebrate+0.066
Neg logit contributions
 firmly-0.064
bled-0.063
aned-0.063
 fists-0.059
uffed-0.055
Token a
Token ID257
Feature activation+4.37e+00

Pos logit contributions
 appreciate+0.103
 visit+0.094
 wedding+0.093
arium+0.093
 who+0.089
Neg logit contributions
 fists-0.102
aned-0.088
 firmly-0.083
omm-0.082
 heavier-0.082
Token hive
Token ID35881
Feature activation+5.39e+00

Pos logit contributions
 appreciate+0.125
 visit+0.111
 cherish+0.105
thank+0.105
 live+0.105
Neg logit contributions
 fists-0.091
 problem-0.086
 firmly-0.086
ented-0.083
aned-0.078
Token near
Token ID1474
Feature activation+3.90e+00

Pos logit contributions
 appreciate+0.151
Hop+0.146
|+0.146
 pic+0.146
 wedding+0.145
Neg logit contributions
 firmly-0.095
 off-0.084
aned-0.082
 fists-0.075
ier-0.075
Token a
Token ID257
Feature activation+3.83e+00

Pos logit contributions
 appreciate+0.099
 wedding+0.097
 visit+0.093
Hop+0.090
arium+0.089
Neg logit contributions
 fists-0.092
aned-0.081
 firmly-0.078
 off-0.076
ares-0.075
Token garden
Token ID11376
Feature activation+5.75e+00

Pos logit contributions
 appreciate+0.103
 cherish+0.088
Always+0.088
 visit+0.088
 live+0.086
Neg logit contributions
 problem-0.083
 fists-0.077
 firmly-0.076
ented-0.075
 heavier-0.074
Token full
Token ID1336
Feature activation+1.61e+00

Pos logit contributions
 appreciate+0.185
Hop+0.182
|+0.179
 cherish+0.170
 celebrate+0.170
Neg logit contributions
 firmly-0.070
 door-0.065
 problem-0.056
 off-0.055
aned-0.053
Token of
Token ID286
Feature activation+3.23e+00

Pos logit contributions
 appreciate+0.047
 visit+0.046
|+0.041
 wedding+0.041
 live+0.041
Neg logit contributions
 fists-0.033
ares-0.031
aned-0.030
 firmly-0.030
ented-0.030
Token fat
Token ID3735
Feature activation+2.57e+00

Pos logit contributions
 visit+0.077
 appreciate+0.076
arium+0.075
|+0.071
 wedding+0.069
Neg logit contributions
 fists-0.079
 firmly-0.070
aned-0.069
 heavier-0.069
 problem-0.068
Token yellow
Token ID7872
Feature activation+2.88e+00

Pos logit contributions
 appreciate+0.059
 visit+0.056
 celebrate+0.050
|+0.049
arium+0.049
Neg logit contributions
 fists-0.072
aned-0.065
 firmly-0.062
ented-0.062
ares-0.062
Token flowers
Token ID12734
Feature activation+4.11e+00

Pos logit contributions
 appreciate+0.064
 visit+0.061
 celebrate+0.056
|+0.054
arium+0.054
Neg logit contributions
 fists-0.080
aned-0.075
ares-0.072
 firmly-0.071
ented-0.069
Token.
Token ID13
Feature activation+4.63e-01

Pos logit contributions
 visit+0.011
 appreciate+0.011
 who+0.010
 live+0.010
 coral+0.010
Neg logit contributions
aned-0.017
 fists-0.017
ares-0.016
ented-0.015
 firmly-0.015
Token<|endoftext|>
Token ID50256
Feature activation+4.16e+00

Pos logit contributions
 coral+0.008
 visit+0.008
 appreciate+0.008
 wedding+0.008
 farm+0.008
Neg logit contributions
 fists-0.014
aned-0.014
ares-0.013
omm-0.013
 firmly-0.013
Tokenâ
Token ID22940
Feature activation+5.08e-01

Pos logit contributions
 appreciate+0.085
 visit+0.080
 wedding+0.079
 coral+0.074
 farm+0.074
Neg logit contributions
aned-0.121
 fists-0.121
ares-0.117
ented-0.111
 firmly-0.111
Token
Token ID26391
Feature activation+6.52e-01

Pos logit contributions
 coral+0.012
 visit+0.012
 farm+0.011
 who+0.011
 appreciate+0.011
Neg logit contributions
aned-0.014
ares-0.012
 fists-0.012
ented-0.012
 firmly-0.011
Token
Token ID129
Feature activation+3.16e-01

Pos logit contributions
 appreciate+0.012
 coral+0.012
 wedding+0.011
 visit+0.011
 live+0.010
Neg logit contributions
 fists-0.020
aned-0.020
 firmly-0.019
ares-0.019
omm-0.018
Token
Token ID241
Feature activation+5.71e+00

Pos logit contributions
 visit+0.008
 appreciate+0.008
 coral+0.007
 who+0.007
 wedding+0.007
Neg logit contributions
aned-0.008
 fists-0.008
ares-0.008
ented-0.007
 firmly-0.007
TokenCome
Token ID16773
Feature activation-7.79e-02

Pos logit contributions
 wedding+0.123
arium+0.119
 coral+0.117
 farm+0.114
 visit+0.113
Neg logit contributions
aned-0.158
 fists-0.153
ula-0.153
ares-0.149
umbled-0.142
Token on
Token ID319
Feature activation+4.15e-01

Pos logit contributions
aned+0.002
 fists+0.002
ares+0.002
ented+0.002
 firmly+0.002
Neg logit contributions
 appreciate-0.002
 visit-0.002
 coral-0.002
 who-0.002
 live-0.002
Token,
Token ID11
Feature activation+1.73e+00

Pos logit contributions
 visit+0.009
 appreciate+0.009
 who+0.008
 farm+0.008
 wedding+0.008
Neg logit contributions
aned-0.012
 fists-0.012
ares-0.012
ented-0.011
 firmly-0.011
Token Mom
Token ID11254
Feature activation+1.11e+00

Pos logit contributions
 appreciate+0.041
 visit+0.041
 wedding+0.038
 coral+0.037
 live+0.037
Neg logit contributions
 fists-0.046
aned-0.045
ares-0.043
ented-0.042
 firmly-0.042
Tokenmy
Token ID1820
Feature activation+1.19e+00

Pos logit contributions
 appreciate+0.024
 visit+0.024
 coral+0.022
 wedding+0.022
 live+0.021
Neg logit contributions
aned-0.032
 fists-0.031
ares-0.030
ented-0.029
 firmly-0.029
Token an
Token ID281
Feature activation+2.00e+00

Pos logit contributions
 appreciate+0.041
 visit+0.041
 farm+0.039
arium+0.039
 wedding+0.039
Neg logit contributions
 fists-0.059
 off-0.052
aned-0.052
ares-0.052
ented-0.052
Token ot
Token ID30972
Feature activation-1.40e+00

Pos logit contributions
 visit+0.045
 appreciate+0.044
 coral+0.041
 live+0.041
arium+0.040
Neg logit contributions
 fists-0.054
aned-0.052
ented-0.050
ares-0.049
 firmly-0.048
Tokenter
Token ID353
Feature activation+2.54e+00

Pos logit contributions
ares+0.027
ented+0.026
 fists+0.026
ula+0.026
ier+0.026
Neg logit contributions
 visit-0.043
 appreciate-0.042
 wedding-0.038
 farm-0.038
 coral-0.038
Token who
Token ID508
Feature activation+1.58e+00

Pos logit contributions
 visit+0.059
 appreciate+0.058
 celebrate+0.053
|+0.052
 wedding+0.052
Neg logit contributions
aned-0.059
 fists-0.058
ula-0.057
ares-0.056
aser-0.056
Token played
Token ID2826
Feature activation+2.17e+00

Pos logit contributions
 visit+0.025
 appreciate+0.024
 wedding+0.023
 coral+0.022
 farm+0.022
Neg logit contributions
 fists-0.050
aned-0.049
ares-0.046
 firmly-0.046
ented-0.046
Token in
Token ID287
Feature activation+5.68e+00

Pos logit contributions
 appreciate+0.062
 wedding+0.061
grand+0.059
 visit+0.058
 farm+0.057
Neg logit contributions
bled-0.040
 off-0.039
ula-0.037
 firmly-0.037
 upside-0.037
Token the
Token ID262
Feature activation+2.96e+00

Pos logit contributions
 appreciate+0.176
 wedding+0.175
ugg+0.171
Sleep+0.166
grand+0.165
Neg logit contributions
 off-0.077
 upside-0.066
 fists-0.066
 firmly-0.063
 heavier-0.059
Token nearby
Token ID6716
Feature activation+5.80e+00

Pos logit contributions
 appreciate+0.059
 who+0.053
 visit+0.053
arium+0.049
|+0.048
Neg logit contributions
ented-0.074
 fists-0.072
 off-0.072
 firmly-0.069
 problem-0.068
Token pond
Token ID16723
Feature activation+5.19e+00

Pos logit contributions
 appreciate+0.120
 cherish+0.097
Sleep+0.096
Always+0.090
 visit+0.087
Neg logit contributions
 off-0.140
 fists-0.137
 problem-0.135
ented-0.131
 hardest-0.130
Token.
Token ID13
Feature activation+2.20e+00

Pos logit contributions
 appreciate+0.145
 visit+0.143
 wedding+0.136
|+0.132
Sleep+0.130
Neg logit contributions
 firmly-0.099
 off-0.094
aned-0.091
ares-0.087
bled-0.087
Token
Token ID198
Feature activation+3.34e+00

Pos logit contributions
 appreciate+0.059
 wedding+0.058
 tale+0.058
 cherish+0.053
 coral+0.053
Neg logit contributions
omm-0.041
ares-0.040
 fists-0.039
aned-0.039
 firmly-0.037
Token loved
Token ID6151
Feature activation+1.95e+00

Pos logit contributions
 appreciate+0.050
 visit+0.050
 wedding+0.049
 heaven+0.047
 outdoors+0.046
Neg logit contributions
aned-0.061
 fists-0.059
 tipped-0.058
 collapsed-0.058
bled-0.057
Token to
Token ID284
Feature activation+2.93e+00

Pos logit contributions
 appreciate+0.056
|+0.053
arium+0.051
 tale+0.050
 visit+0.049
Neg logit contributions
 fists-0.037
 off-0.035
aned-0.031
 heavier-0.030
 problem-0.029
Token swim
Token ID9422
Feature activation+1.00e+00

Pos logit contributions
Em+0.074
Always+0.073
Sleep+0.072
Ell+0.068
Hope+0.068
Neg logit contributions
 fists-0.057
ered-0.055
 off-0.053
 pulls-0.052
aned-0.050
Token around
Token ID1088
Feature activation+4.19e+00

Pos logit contributions
 wedding+0.026
 appreciate+0.026
 visit+0.025
 farm+0.023
 tale+0.023
Neg logit contributions
 off-0.022
 firmly-0.022
 fists-0.021
ares-0.021
aned-0.021
Token the
Token ID262
Feature activation+3.68e+00

Pos logit contributions
 appreciate+0.129
grand+0.118
 tale+0.114
 wedding+0.114
forest+0.113
Neg logit contributions
 off-0.075
 fists-0.072
 firmly-0.070
ares-0.063
aned-0.063
Token coral
Token ID29537
Feature activation+5.68e+00

Pos logit contributions
 appreciate+0.066
 tale+0.065
 visit+0.061
 wedding+0.059
Ell+0.058
Neg logit contributions
 fists-0.105
ented-0.099
 off-0.097
bled-0.096
aned-0.095
Token and
Token ID290
Feature activation+2.88e+00

Pos logit contributions
 appreciate+0.109
Ell+0.107
|+0.104
grand+0.104
 visit+0.102
Neg logit contributions
 off-0.144
 hardest-0.142
bled-0.138
ares-0.137
 firmly-0.137
Token explore
Token ID7301
Feature activation+3.01e+00

Pos logit contributions
Sleep+0.060
 tale+0.059
Always+0.057
Em+0.057
arium+0.056
Neg logit contributions
 fists-0.073
 off-0.070
 firmly-0.064
 hardest-0.063
 heavier-0.062
Token all
Token ID477
Feature activation+2.85e+00

Pos logit contributions
 wedding+0.093
forest+0.089
 appreciate+0.088
|+0.087
 tale+0.087
Neg logit contributions
 off-0.048
 heavier-0.042
 upside-0.041
 harder-0.040
 firmly-0.040
Token the
Token ID262
Feature activation+3.62e+00

Pos logit contributions
 wedding+0.070
 visit+0.066
 tale+0.066
Sun+0.064
 farm+0.064
Neg logit contributions
 off-0.063
ares-0.060
aned-0.058
 fists-0.056
 upside-0.055
Token hidden
Token ID7104
Feature activation+1.32e+00

Pos logit contributions
 wedding+0.085
 appreciate+0.083
 visit+0.082
 celebrate+0.081
 heaven+0.080
Neg logit contributions
 fists-0.076
 problem-0.074
 hardest-0.073
 off-0.070
 heavier-0.068
Token.
Token ID13
Feature activation+3.02e+00

Pos logit contributions
 visit+0.012
 appreciate+0.011
 who+0.011
 live+0.010
 coral+0.010
Neg logit contributions
aned-0.019
 fists-0.019
ares-0.018
ented-0.017
omm-0.017
Token
Token ID6184
Feature activation-1.08e+00

Pos logit contributions
 appreciate+0.065
 visit+0.064
 wedding+0.061
 coral+0.060
 farm+0.059
Neg logit contributions
 fists-0.085
aned-0.084
ares-0.083
 firmly-0.079
ented-0.078
Token
Token ID95
Feature activation+1.18e-02

Pos logit contributions
aned+0.026
 fists+0.026
ares+0.025
ented+0.024
 firmly+0.023
Neg logit contributions
 visit-0.029
 appreciate-0.029
 coral-0.027
 who-0.027
 farm-0.027
Token
Token ID26391
Feature activation+7.92e-01

Pos logit contributions
 visit+0.000
 appreciate+0.000
 who+0.000
 coral+0.000
 live+0.000
Neg logit contributions
aned-0.000
 fists-0.000
ares-0.000
ented-0.000
 firmly-0.000
Token
Token ID129
Feature activation-1.58e-01

Pos logit contributions
 visit+0.013
 appreciate+0.013
 coral+0.012
 wedding+0.012
 farm+0.011
Neg logit contributions
aned-0.027
 fists-0.027
ares-0.026
ented-0.025
 firmly-0.025
Token
Token ID241
Feature activation+5.66e+00

Pos logit contributions
aned+0.004
 fists+0.004
ares+0.004
ented+0.004
 firmly+0.003
Neg logit contributions
 visit-0.004
 appreciate-0.004
 who-0.004
 live-0.004
 coral-0.004
TokenIf
Token ID1532
Feature activation+1.45e+00

Pos logit contributions
 wedding+0.106
 visit+0.105
arium+0.105
 coral+0.104
 farm+0.101
Neg logit contributions
aned-0.168
 fists-0.167
ares-0.163
ula-0.161
ented-0.156
Token you
Token ID345
Feature activation+1.89e+00

Pos logit contributions
 visit+0.030
 appreciate+0.030
 coral+0.027
 who+0.027
 farm+0.027
Neg logit contributions
 fists-0.043
aned-0.043
ares-0.041
ented-0.039
 firmly-0.039
Token want
Token ID765
Feature activation+8.34e-01

Pos logit contributions
 visit+0.040
 appreciate+0.039
 coral+0.037
 farm+0.036
 who+0.036
Neg logit contributions
aned-0.055
 fists-0.055
ares-0.053
ented-0.051
 firmly-0.050
Token to
Token ID284
Feature activation+1.69e+00

Pos logit contributions
 visit+0.016
 appreciate+0.016
 who+0.015
 live+0.014
 coral+0.014
Neg logit contributions
aned-0.026
 fists-0.026
ares-0.025
ented-0.024
 firmly-0.024
Token open
Token ID1280
Feature activation+3.97e-01

Pos logit contributions
 visit+0.034
 appreciate+0.033
 coral+0.032
 who+0.032
arium+0.032
Neg logit contributions
 fists-0.049
aned-0.049
ares-0.046
 firmly-0.045
ented-0.044
Token.
Token ID13
Feature activation+3.02e+00

Pos logit contributions
 appreciate+0.010
 visit+0.010
 coral+0.010
 wedding+0.010
 live+0.009
Neg logit contributions
aned-0.014
 fists-0.014
ented-0.013
ares-0.013
 firmly-0.013
Token
Token ID6184
Feature activation-1.08e+00

Pos logit contributions
 appreciate+0.065
 visit+0.064
 wedding+0.061
 coral+0.060
 farm+0.059
Neg logit contributions
 fists-0.085
aned-0.084
ares-0.083
 firmly-0.079
ented-0.078
Token
Token ID95
Feature activation+1.18e-02

Pos logit contributions
aned+0.026
 fists+0.026
ares+0.025
ented+0.024
 firmly+0.023
Neg logit contributions
 visit-0.029
 appreciate-0.029
 coral-0.027
 who-0.027
 farm-0.027
Token
Token ID26391
Feature activation+7.92e-01

Pos logit contributions
 visit+0.000
 appreciate+0.000
 who+0.000
 coral+0.000
 live+0.000
Neg logit contributions
aned-0.000
 fists-0.000
ares-0.000
ented-0.000
 firmly-0.000
Token
Token ID129
Feature activation-1.58e-01

Pos logit contributions
 visit+0.013
 appreciate+0.013
 coral+0.012
 wedding+0.012
 farm+0.011
Neg logit contributions
aned-0.027
 fists-0.027
ares-0.026
ented-0.025
 firmly-0.025
Token
Token ID241
Feature activation+5.66e+00

Pos logit contributions
aned+0.004
 fists+0.004
ares+0.004
ented+0.004
 firmly+0.003
Neg logit contributions
 visit-0.004
 appreciate-0.004
 who-0.004
 live-0.004
 coral-0.004
TokenIt
Token ID1026
Feature activation-3.59e-01

Pos logit contributions
 wedding+0.106
 visit+0.105
arium+0.105
 coral+0.104
 farm+0.101
Neg logit contributions
aned-0.168
 fists-0.167
ares-0.163
ula-0.161
ented-0.156
Tokenâ
Token ID22940
Feature activation-4.82e-01

Pos logit contributions
aned+0.010
 fists+0.010
ares+0.009
ented+0.009
 firmly+0.008
Neg logit contributions
 visit-0.009
 appreciate-0.009
 who-0.008
 live-0.008
 farm-0.008
Token
Token ID26391
Feature activation+7.83e-02

Pos logit contributions
aned+0.012
 fists+0.012
ares+0.011
ented+0.011
 firmly+0.010
Neg logit contributions
 visit-0.013
 appreciate-0.013
 who-0.012
 coral-0.012
 live-0.012
Token
Token ID8151
Feature activation+5.70e-01

Pos logit contributions
 appreciate+0.002
 visit+0.002
 coral+0.002
 wedding+0.002
 who+0.002
Neg logit contributions
aned-0.002
 fists-0.002
ares-0.002
ented-0.002
 firmly-0.002
Tokens
Token ID82
Feature activation+4.34e-01

Pos logit contributions
 visit+0.015
 appreciate+0.015
 who+0.014
 live+0.014
 celebrate+0.013
Neg logit contributions
 fists-0.015
aned-0.014
ented-0.013
ares-0.013
 firmly-0.012
Token the
Token ID262
Feature activation-1.17e+00

Pos logit contributions
aned+0.013
ares+0.013
 fists+0.012
ented+0.012
omm+0.012
Neg logit contributions
 visit-0.008
 who-0.007
 appreciate-0.007
 live-0.007
 coral-0.007
Token heavy
Token ID4334
Feature activation-1.69e+00

Pos logit contributions
 fists+0.031
aned+0.030
ares+0.028
ented+0.028
 firmly+0.027
Neg logit contributions
 visit-0.030
 appreciate-0.029
 who-0.027
 live-0.027
 coral-0.027
Token bag
Token ID6131
Feature activation-2.37e+00

Pos logit contributions
aned+0.043
 fists+0.042
ares+0.041
ented+0.038
 firmly+0.037
Neg logit contributions
 visit-0.046
 appreciate-0.044
 who-0.042
 farm-0.042
 live-0.041
Token had
Token ID550
Feature activation-4.06e-01

Pos logit contributions
aned+0.073
 fists+0.073
ares+0.070
ented+0.067
omm+0.065
Neg logit contributions
 visit-0.049
 appreciate-0.047
 who-0.045
 live-0.043
 farm-0.042
Token been
Token ID587
Feature activation-1.56e+00

Pos logit contributions
aned+0.012
 fists+0.012
ares+0.011
ented+0.011
omm+0.010
Neg logit contributions
 visit-0.010
 appreciate-0.009
 who-0.009
 live-0.009
 wedding-0.008
Token fore
Token ID1674
Feature activation-7.07e+00

Pos logit contributions
aned+0.045
 fists+0.045
ares+0.043
ented+0.041
omm+0.040
Neg logit contributions
 visit-0.036
 appreciate-0.035
 who-0.034
 live-0.033
 wedding-0.032
Tokenshadow
Token ID19106
Feature activation-1.59e+00

Pos logit contributions
 fists+0.152
aned+0.140
omm+0.135
ares+0.131
ula+0.123
Neg logit contributions
 visit-0.211
 who-0.204
 appreciate-0.202
 live-0.189
 outdoors-0.185
Tokened
Token ID276
Feature activation-1.19e+00

Pos logit contributions
 fists+0.032
aned+0.031
ares+0.031
ented+0.026
 brakes+0.026
Neg logit contributions
 visit-0.048
 who-0.047
 appreciate-0.045
 live-0.043
 living-0.042
Token,
Token ID11
Feature activation+2.66e+00

Pos logit contributions
aned+0.038
 fists+0.036
ares+0.036
ented+0.034
omm+0.034
Neg logit contributions
 visit-0.025
 appreciate-0.023
 who-0.023
 live-0.022
 coral-0.021
Token and
Token ID290
Feature activation-2.88e-01

Pos logit contributions
 visit+0.052
 appreciate+0.051
 live+0.046
 wedding+0.046
 coral+0.046
Neg logit contributions
 fists-0.084
aned-0.083
ares-0.078
 firmly-0.077
ented-0.077
Token that
Token ID326
Feature activation-5.01e-01

Pos logit contributions
aned+0.009
 fists+0.009
ares+0.009
ented+0.008
omm+0.008
Neg logit contributions
 visit-0.006
 appreciate-0.006
 who-0.006
 live-0.005
 coral-0.005
Token
Token ID198
Feature activation+8.70e-01

Pos logit contributions
aned+0.005
 fists+0.005
ares+0.005
ented+0.004
 firmly+0.004
Neg logit contributions
 visit-0.003
 appreciate-0.002
 who-0.002
 live-0.002
 coral-0.002
Token
Token ID198
Feature activation-7.24e-01

Pos logit contributions
 visit+0.012
 appreciate+0.011
 wedding+0.010
 coral+0.010
 farm+0.010
Neg logit contributions
aned-0.033
 fists-0.032
ares-0.031
ented-0.030
 firmly-0.030
TokenThe
Token ID464
Feature activation-4.20e-01

Pos logit contributions
aned+0.025
 fists+0.025
ares+0.024
ented+0.024
 firmly+0.023
Neg logit contributions
 visit-0.012
 appreciate-0.011
 who-0.010
 live-0.010
 coral-0.010
Token wave
Token ID6769
Feature activation-1.60e+00

Pos logit contributions
aned+0.012
 fists+0.012
ares+0.011
ented+0.011
 firmly+0.011
Neg logit contributions
 visit-0.010
 appreciate-0.009
 who-0.009
 live-0.009
 coral-0.009
Token had
Token ID550
Feature activation-8.87e-01

Pos logit contributions
 fists+0.045
aned+0.044
ares+0.042
ented+0.041
omm+0.039
Neg logit contributions
 visit-0.037
 appreciate-0.036
 who-0.036
 live-0.034
 wedding-0.034
Token fore
Token ID1674
Feature activation-7.00e+00

Pos logit contributions
aned+0.026
 fists+0.025
ares+0.025
ented+0.024
omm+0.023
Neg logit contributions
 visit-0.020
 appreciate-0.020
 who-0.018
 live-0.018
 coral-0.018
Tokenshadow
Token ID19106
Feature activation-2.49e+00

Pos logit contributions
 fists+0.154
aned+0.138
omm+0.134
ares+0.131
ula+0.124
Neg logit contributions
 visit-0.204
 who-0.201
 appreciate-0.199
 live-0.184
 outdoors-0.181
Tokened
Token ID276
Feature activation-1.14e+00

Pos logit contributions
 fists+0.045
aned+0.043
ares+0.042
 firmly+0.037
 brakes+0.035
Neg logit contributions
 who-0.079
 visit-0.078
 appreciate-0.076
 live-0.073
 living-0.071
Token L
Token ID406
Feature activation-1.45e+00

Pos logit contributions
aned+0.037
 fists+0.035
ares+0.035
ented+0.034
omm+0.033
Neg logit contributions
 visit-0.023
 appreciate-0.022
 who-0.021
 live-0.020
 farm-0.018
Tokenola
Token ID5708
Feature activation-1.37e+00

Pos logit contributions
 fists+0.041
aned+0.040
ented+0.036
 firmly+0.036
ares+0.035
Neg logit contributions
 visit-0.034
 appreciate-0.034
 who-0.032
 live-0.031
 wedding-0.031
Token's
Token ID338
Feature activation-1.84e+00

Pos logit contributions
 fists+0.041
aned+0.041
ares+0.040
ented+0.038
omm+0.037
Neg logit contributions
 visit-0.029
 appreciate-0.028
 who-0.027
 live-0.026
 farm-0.025
TokenWe
Token ID1135
Feature activation+5.75e-02

Pos logit contributions
 wedding+0.050
 visit+0.048
 coral+0.047
 farm+0.047
 parties+0.047
Neg logit contributions
aned-0.057
 fists-0.054
ares-0.053
bled-0.052
 firmly-0.052
Token'll
Token ID1183
Feature activation-1.05e+00

Pos logit contributions
 visit+0.001
 appreciate+0.001
 who+0.001
 live+0.001
 coral+0.001
Neg logit contributions
aned-0.002
 fists-0.002
ares-0.001
ented-0.001
 firmly-0.001
Token help
Token ID1037
Feature activation-1.42e+00

Pos logit contributions
 fists+0.031
aned+0.031
ares+0.029
ented+0.028
 firmly+0.028
Neg logit contributions
 visit-0.022
 appreciate-0.022
 coral-0.021
 wedding-0.020
 who-0.020
Token you
Token ID345
Feature activation-1.15e+00

Pos logit contributions
 fists+0.042
aned+0.042
ares+0.039
 firmly+0.038
ented+0.038
Neg logit contributions
 appreciate-0.030
 visit-0.030
 wedding-0.028
 coral-0.028
 farm-0.028
Token get
Token ID651
Feature activation-3.04e+00

Pos logit contributions
 fists+0.033
aned+0.033
ares+0.031
ented+0.030
 firmly+0.030
Neg logit contributions
 visit-0.025
 appreciate-0.025
 wedding-0.024
 coral-0.023
 farm-0.023
Token unst
Token ID15014
Feature activation-6.94e+00

Pos logit contributions
aned+0.087
 fists+0.085
ares+0.081
omm+0.077
ented+0.077
Neg logit contributions
 visit-0.074
 appreciate-0.070
 who-0.067
 live-0.067
 coral-0.064
Tokenuck
Token ID1347
Feature activation-1.03e+00

Pos logit contributions
 fists+0.144
aned+0.136
ares+0.123
ula+0.119
ented+0.115
Neg logit contributions
 visit-0.211
 appreciate-0.191
 live-0.187
 outdoors-0.185
 play-0.181
Token."
Token ID526
Feature activation-4.33e-01

Pos logit contributions
aned+0.032
 fists+0.031
ares+0.030
ented+0.029
 firmly+0.028
Neg logit contributions
 visit-0.021
 appreciate-0.021
 who-0.019
 live-0.019
 coral-0.019
Token
Token ID198
Feature activation+2.90e-01

Pos logit contributions
aned+0.017
 fists+0.017
ares+0.016
ented+0.016
 firmly+0.016
Neg logit contributions
 visit-0.005
 appreciate-0.005
 who-0.005
 live-0.004
 coral-0.004
Token
Token ID198
Feature activation-1.48e+00

Pos logit contributions
 visit+0.004
 appreciate+0.004
 wedding+0.004
 coral+0.004
 live+0.004
Neg logit contributions
aned-0.011
 fists-0.010
ares-0.010
ented-0.010
 firmly-0.010
TokenBut
Token ID1537
Feature activation-1.98e+00

Pos logit contributions
aned+0.048
 fists+0.048
ares+0.046
ented+0.045
 firmly+0.044
Neg logit contributions
 visit-0.028
 appreciate-0.027
 wedding-0.025
 live-0.024
 who-0.024
Token they
Token ID484
Feature activation-1.51e+00

Pos logit contributions
aned+0.092
ares+0.089
 fists+0.085
ented+0.082
omm+0.079
Neg logit contributions
 visit-0.050
 who-0.045
 live-0.045
 appreciate-0.043
 farm-0.041
Token didn
Token ID1422
Feature activation-2.89e+00

Pos logit contributions
aned+0.046
 fists+0.045
ares+0.044
omm+0.043
ula+0.042
Neg logit contributions
 visit-0.034
 appreciate-0.034
 live-0.032
 who-0.032
 celebrate-0.029
Token't
Token ID470
Feature activation-2.28e+00

Pos logit contributions
 fists+0.090
ented+0.084
aned+0.084
uffed+0.079
anted+0.078
Neg logit contributions
 visit-0.066
 live-0.058
 play-0.054
 celebrate-0.053
 who-0.053
Token get
Token ID651
Feature activation-4.28e+00

Pos logit contributions
aned+0.074
 fists+0.073
ares+0.068
ented+0.068
omm+0.066
Neg logit contributions
 visit-0.047
 appreciate-0.046
 live-0.043
 who-0.042
 celebrate-0.039
Token it
Token ID340
Feature activation-4.74e+00

Pos logit contributions
aned+0.130
omm+0.120
 fists+0.119
ares+0.115
ula+0.112
Neg logit contributions
 visit-0.101
 who-0.097
 live-0.095
 appreciate-0.092
 outdoors-0.085
Token unst
Token ID15014
Feature activation-6.81e+00

Pos logit contributions
 fists+0.169
aned+0.169
omm+0.162
ares+0.155
uffed+0.151
Neg logit contributions
 visit-0.082
 who-0.073
 live-0.069
 outdoors-0.068
 play-0.064
Tokenuck
Token ID1347
Feature activation-1.91e+00

Pos logit contributions
 fists+0.142
aned+0.139
ares+0.122
ula+0.118
ier+0.113
Neg logit contributions
 visit-0.203
 live-0.178
 appreciate-0.176
 outdoors-0.176
 farm-0.175
Token.
Token ID13
Feature activation-3.90e-01

Pos logit contributions
aned+0.073
 fists+0.071
omm+0.069
ares+0.068
ented+0.066
Neg logit contributions
 who-0.026
 visit-0.026
 appreciate-0.023
 live-0.023
 outdoors-0.021
Token
Token ID198
Feature activation+1.06e+00

Pos logit contributions
aned+0.015
 fists+0.015
ares+0.015
ented+0.014
 firmly+0.014
Neg logit contributions
 visit-0.005
 appreciate-0.005
 who-0.004
 live-0.004
 farm-0.004
Token
Token ID198
Feature activation-1.02e+00

Pos logit contributions
 visit+0.014
 appreciate+0.013
 wedding+0.012
 coral+0.012
 live+0.011
Neg logit contributions
aned-0.041
 fists-0.040
ares-0.039
ented-0.038
 firmly-0.037
TokenJust
Token ID5703
Feature activation-4.04e-01

Pos logit contributions
 fists+0.034
aned+0.034
ares+0.032
ented+0.031
 firmly+0.030
Neg logit contributions
 visit-0.019
 appreciate-0.019
 who-0.017
 live-0.016
 farm-0.016
Token there
Token ID612
Feature activation+1.63e+00

Pos logit contributions
 fists+0.009
aned+0.009
ares+0.008
ented+0.008
 firmly+0.008
Neg logit contributions
 visit-0.008
 appreciate-0.008
 who-0.007
 live-0.007
 farm-0.007
Token and
Token ID290
Feature activation+3.58e-01

Pos logit contributions
 visit+0.034
 appreciate+0.034
 coral+0.031
 live+0.031
 wedding+0.031
Neg logit contributions
 fists-0.048
aned-0.048
ares-0.045
 firmly-0.045
ented-0.044
Token wait
Token ID4043
Feature activation+9.81e-01

Pos logit contributions
 visit+0.007
 appreciate+0.007
 coral+0.006
 farm+0.006
 wedding+0.006
Neg logit contributions
 fists-0.011
aned-0.011
 firmly-0.010
ares-0.010
ented-0.010
Token.
Token ID13
Feature activation-2.96e-01

Pos logit contributions
 visit+0.021
 appreciate+0.021
 who+0.019
 live+0.019
 coral+0.019
Neg logit contributions
aned-0.029
 fists-0.029
ares-0.027
ented-0.027
 firmly-0.026
Token The
Token ID383
Feature activation-1.12e+00

Pos logit contributions
 fists+0.009
aned+0.009
ares+0.009
ented+0.008
 firmly+0.008
Neg logit contributions
 visit-0.006
 appreciate-0.006
 who-0.005
 live-0.005
 coral-0.005
Token fore
Token ID1674
Feature activation-6.81e+00

Pos logit contributions
aned+0.033
 fists+0.033
ares+0.032
ented+0.030
 firmly+0.029
Neg logit contributions
 visit-0.026
 appreciate-0.025
 who-0.023
 farm-0.023
 live-0.023
Tokenshadow
Token ID19106
Feature activation-2.71e+00

Pos logit contributions
 fists+0.147
aned+0.130
ares+0.125
omm+0.118
ented+0.118
Neg logit contributions
 visit-0.204
 who-0.201
 appreciate-0.201
 live-0.188
 wedding-0.182
Tokening
Token ID278
Feature activation-2.87e-01

Pos logit contributions
 fists+0.047
aned+0.045
ares+0.044
ented+0.037
 firmly+0.037
Neg logit contributions
 visit-0.089
 who-0.088
 appreciate-0.087
 live-0.083
arium-0.079
Token of
Token ID286
Feature activation+1.77e+00

Pos logit contributions
aned+0.008
 fists+0.008
ares+0.008
ented+0.008
 firmly+0.007
Neg logit contributions
 visit-0.007
 appreciate-0.006
 who-0.006
 live-0.006
 farm-0.006
Token the
Token ID262
Feature activation-1.15e+00

Pos logit contributions
 visit+0.036
 appreciate+0.035
 who+0.032
 live+0.032
 coral+0.031
Neg logit contributions
 fists-0.055
aned-0.054
ares-0.051
ented-0.050
 firmly-0.050
Token dull
Token ID19222
Feature activation-9.89e-01

Pos logit contributions
aned+0.035
 fists+0.034
ares+0.033
ented+0.031
 firmly+0.030
Neg logit contributions
 visit-0.026
 appreciate-0.025
 who-0.023
 farm-0.023
 wedding-0.023
Token.
Token ID13
Feature activation-1.43e+00

Pos logit contributions
 visit+0.002
 who+0.002
 appreciate+0.002
 live+0.002
 farm+0.002
Neg logit contributions
 fists-0.004
aned-0.004
ares-0.003
ented-0.003
 firmly-0.003
Token There
Token ID1318
Feature activation-2.19e+00

Pos logit contributions
aned+0.047
 fists+0.045
ares+0.043
ented+0.042
 firmly+0.041
Neg logit contributions
 visit-0.028
 appreciate-0.027
 who-0.025
 live-0.025
 coral-0.025
Token were
Token ID547
Feature activation-6.71e-01

Pos logit contributions
aned+0.086
 fists+0.082
ented+0.080
ares+0.080
ula+0.074
Neg logit contributions
 visit-0.034
 live-0.034
 lived-0.031
 who-0.029
 appreciate-0.027
Token cans
Token ID23916
Feature activation-2.09e+00

Pos logit contributions
aned+0.021
ares+0.020
 fists+0.019
ented+0.018
omm+0.018
Neg logit contributions
 visit-0.014
 who-0.014
 appreciate-0.014
 coral-0.013
 live-0.013
Token,
Token ID11
Feature activation+1.63e+00

Pos logit contributions
aned+0.074
 fists+0.073
ares+0.069
omm+0.069
ented+0.066
Neg logit contributions
 who-0.034
 visit-0.034
 live-0.033
 appreciate-0.031
 coral-0.029
Token wra
Token ID7917
Feature activation-6.75e+00

Pos logit contributions
 visit+0.041
 appreciate+0.040
 who+0.040
 coral+0.038
 live+0.038
Neg logit contributions
aned-0.044
ares-0.041
 fists-0.041
ented-0.038
omm-0.038
Tokenppers
Token ID11799
Feature activation-1.82e+00

Pos logit contributions
 fists+0.163
aned+0.162
ares+0.158
omm+0.147
nown+0.137
Neg logit contributions
 who-0.172
 visit-0.166
 live-0.155
 appreciate-0.153
 farm-0.152
Token and
Token ID290
Feature activation+5.30e-01

Pos logit contributions
aned+0.060
 fists+0.060
ares+0.058
omm+0.056
ented+0.056
Neg logit contributions
 visit-0.033
 who-0.032
 live-0.031
 appreciate-0.029
 farm-0.029
Token bottles
Token ID14096
Feature activation-2.15e+00

Pos logit contributions
 visit+0.013
 appreciate+0.013
 who+0.012
 coral+0.012
 live+0.012
Neg logit contributions
aned-0.014
ares-0.014
 fists-0.014
ented-0.013
 firmly-0.012
Token.
Token ID13
Feature activation-1.15e+00

Pos logit contributions
aned+0.078
 fists+0.076
omm+0.074
ares+0.072
ented+0.070
Neg logit contributions
 who-0.033
 visit-0.032
 live-0.032
 appreciate-0.030
 coral-0.028
Token Sara
Token ID24799
Feature activation-9.26e-01

Pos logit contributions
aned+0.036
 fists+0.036
ares+0.034
ented+0.033
 firmly+0.032
Neg logit contributions
 visit-0.024
 appreciate-0.023
 who-0.021
 live-0.021
 coral-0.021
Token,
Token ID11
Feature activation-2.04e+00

Pos logit contributions
aned+0.052
 fists+0.051
ares+0.049
ented+0.048
omm+0.046
Neg logit contributions
 visit-0.028
 who-0.024
 live-0.023
 named-0.023
 farm-0.022
Token Billy
Token ID15890
Feature activation-2.39e+00

Pos logit contributions
aned+0.066
 fists+0.064
ares+0.063
ented+0.061
omm+0.057
Neg logit contributions
 visit-0.043
 appreciate-0.039
 who-0.038
 live-0.037
 farm-0.037
Token accidentally
Token ID14716
Feature activation-1.49e+00

Pos logit contributions
 fists+0.073
aned+0.072
ares+0.069
ented+0.066
 firmly+0.065
Neg logit contributions
 visit-0.052
 appreciate-0.048
 who-0.047
 farm-0.046
 live-0.045
Token turned
Token ID2900
Feature activation-3.66e+00

Pos logit contributions
ares+0.036
aned+0.036
omm+0.035
ented+0.035
 fists+0.035
Neg logit contributions
 visit-0.041
 who-0.039
 live-0.038
 appreciate-0.038
 play-0.037
Token the
Token ID262
Feature activation-3.49e+00

Pos logit contributions
aned+0.158
omm+0.153
ares+0.141
ented+0.139
bled+0.139
Neg logit contributions
 visit-0.029
 who-0.028
 play-0.028
 coral-0.026
 outdoors-0.023
Token er
Token ID1931
Feature activation-6.73e+00

Pos logit contributions
aned+0.110
ares+0.100
 firmly+0.097
 fists+0.096
uffed+0.094
Neg logit contributions
 visit-0.074
 living-0.071
 who-0.067
 farm-0.063
 appreciate-0.062
Tokenaser
Token ID6005
Feature activation-4.58e+00

Pos logit contributions
 fists+0.122
aned+0.111
 firmly+0.097
 brakes+0.084
 collapsed+0.082
Neg logit contributions
 who-0.223
 appreciate-0.202
 visit-0.201
 live-0.199
 living-0.196
Token too
Token ID1165
Feature activation-2.64e+00

Pos logit contributions
omm+0.168
aned+0.162
 fists+0.155
uffed+0.153
bled+0.147
Neg logit contributions
 who-0.078
 visit-0.068
 play-0.065
 living-0.058
 live-0.056
Token much
Token ID881
Feature activation-3.33e+00

Pos logit contributions
omm+0.095
aned+0.093
 fists+0.093
bled+0.083
ares+0.082
Neg logit contributions
 visit-0.046
 who-0.045
 live-0.042
 play-0.041
 appreciate-0.040
Token and
Token ID290
Feature activation-2.97e+00

Pos logit contributions
aned+0.125
 fists+0.119
omm+0.114
bled+0.112
ares+0.111
Neg logit contributions
 visit-0.055
 who-0.050
 appreciate-0.048
 live-0.046
 play-0.042
Token it
Token ID340
Feature activation-4.69e+00

Pos logit contributions
aned+0.100
ares+0.099
omm+0.097
 fists+0.095
ula+0.091
Neg logit contributions
 visit-0.062
 live-0.056
 play-0.056
 who-0.055
 appreciate-0.053
Token,
Token ID11
Feature activation+2.35e+00

Pos logit contributions
 appreciate+0.001
 visit+0.001
 coral+0.001
 live+0.001
 wedding+0.001
Neg logit contributions
 fists-0.002
aned-0.002
 firmly-0.002
ares-0.002
ented-0.002
Token but
Token ID475
Feature activation-3.01e-01

Pos logit contributions
 visit+0.051
 appreciate+0.050
 wedding+0.046
 live+0.046
 coral+0.045
Neg logit contributions
 fists-0.068
aned-0.065
 firmly-0.063
ares-0.062
ented-0.061
Token it
Token ID340
Feature activation-1.25e+00

Pos logit contributions
aned+0.008
 fists+0.008
ares+0.008
ented+0.008
 firmly+0.007
Neg logit contributions
 visit-0.007
 appreciate-0.007
 who-0.007
 live-0.006
 coral-0.006
Token was
Token ID373
Feature activation-9.51e-01

Pos logit contributions
aned+0.033
 fists+0.033
ares+0.031
ented+0.030
 firmly+0.029
Neg logit contributions
 visit-0.031
 appreciate-0.030
 who-0.028
 coral-0.028
 live-0.028
Token all
Token ID477
Feature activation-1.78e-01

Pos logit contributions
aned+0.026
 fists+0.026
ares+0.025
ented+0.024
 firmly+0.023
Neg logit contributions
 visit-0.023
 appreciate-0.023
 who-0.021
 live-0.021
 wedding-0.020
Token fore
Token ID1674
Feature activation-6.64e+00

Pos logit contributions
 fists+0.004
aned+0.004
ares+0.004
ented+0.004
 firmly+0.004
Neg logit contributions
 visit-0.005
 appreciate-0.005
 coral-0.004
 farm-0.004
 wedding-0.004
Tokenshadow
Token ID19106
Feature activation-1.50e+00

Pos logit contributions
 fists+0.136
aned+0.127
ares+0.120
omm+0.117
ented+0.112
Neg logit contributions
 visit-0.203
 appreciate-0.196
 who-0.195
 live-0.184
 farm-0.181
Tokened
Token ID276
Feature activation-1.09e+00

Pos logit contributions
 fists+0.027
aned+0.026
ares+0.025
ented+0.022
 firmly+0.021
Neg logit contributions
 visit-0.049
 who-0.048
 appreciate-0.048
 live-0.045
 coral-0.043
Token by
Token ID416
Feature activation+1.11e+00

Pos logit contributions
aned+0.033
 fists+0.032
ares+0.032
ented+0.030
omm+0.030
Neg logit contributions
 visit-0.024
 appreciate-0.023
 who-0.022
 live-0.021
 coral-0.020
Token the
Token ID262
Feature activation-3.47e-01

Pos logit contributions
 visit+0.023
 appreciate+0.023
 who+0.021
 live+0.021
 coral+0.021
Neg logit contributions
aned-0.034
 fists-0.033
ares-0.032
ented-0.031
 firmly-0.030
Token kind
Token ID1611
Feature activation-9.97e-01

Pos logit contributions
aned+0.009
 fists+0.009
ares+0.009
ented+0.008
 firmly+0.008
Neg logit contributions
 visit-0.009
 appreciate-0.009
 who-0.008
 live-0.008
 farm-0.008
Token could
Token ID714
Feature activation-1.51e+00

Pos logit contributions
 fists+0.051
aned+0.050
ares+0.049
ented+0.046
omm+0.045
Neg logit contributions
 visit-0.044
 who-0.042
 appreciate-0.042
 live-0.040
 coral-0.039
Token help
Token ID1037
Feature activation-9.82e-01

Pos logit contributions
aned+0.043
 fists+0.043
ares+0.041
ented+0.040
 firmly+0.038
Neg logit contributions
 visit-0.035
 appreciate-0.034
 live-0.032
 who-0.032
 farm-0.031
Token get
Token ID651
Feature activation-3.39e+00

Pos logit contributions
aned+0.032
 fists+0.031
ares+0.031
ented+0.030
uffed+0.028
Neg logit contributions
 visit-0.021
 appreciate-0.019
 who-0.019
 live-0.018
 celebrate-0.017
Token the
Token ID262
Feature activation-2.48e+00

Pos logit contributions
aned+0.110
ares+0.103
omm+0.102
 fists+0.101
ula+0.096
Neg logit contributions
 visit-0.076
 live-0.071
 who-0.068
 appreciate-0.068
 play-0.061
Token car
Token ID1097
Feature activation-2.79e+00

Pos logit contributions
aned+0.068
ares+0.064
 fists+0.063
omm+0.057
ented+0.057
Neg logit contributions
 visit-0.066
 appreciate-0.061
 farm-0.061
 who-0.060
 live-0.060
Token unst
Token ID15014
Feature activation-6.57e+00

Pos logit contributions
aned+0.079
 fists+0.079
ares+0.073
omm+0.071
ented+0.070
Neg logit contributions
 visit-0.068
 appreciate-0.063
 who-0.063
 live-0.062
 farm-0.059
Tokenuck
Token ID1347
Feature activation-2.60e-01

Pos logit contributions
 fists+0.133
aned+0.129
ares+0.119
ula+0.111
omm+0.106
Neg logit contributions
 visit-0.203
 live-0.182
 appreciate-0.179
 farm-0.177
 outdoors-0.175
Token.
Token ID13
Feature activation-5.88e-01

Pos logit contributions
aned+0.008
 fists+0.008
ares+0.007
ented+0.007
omm+0.007
Neg logit contributions
 visit-0.006
 appreciate-0.005
 who-0.005
 live-0.005
 coral-0.005
Token
Token ID198
Feature activation+6.89e-01

Pos logit contributions
aned+0.021
 fists+0.021
ares+0.020
ented+0.019
 firmly+0.019
Neg logit contributions
 visit-0.010
 appreciate-0.009
 who-0.009
 live-0.008
 farm-0.008
Token
Token ID198
Feature activation-1.08e+00

Pos logit contributions
 visit+0.010
 appreciate+0.010
 coral+0.009
 wedding+0.009
 farm+0.009
Neg logit contributions
aned-0.025
 fists-0.024
ares-0.023
 firmly-0.023
ented-0.023
TokenThe
Token ID464
Feature activation-2.15e+00

Pos logit contributions
aned+0.036
 fists+0.035
ares+0.034
ented+0.033
 firmly+0.033
Neg logit contributions
 visit-0.020
 appreciate-0.019
 coral-0.017
 live-0.017
 who-0.017
Token eyes
Token ID2951
Feature activation-1.56e+00

Pos logit contributions
aned+0.084
ares+0.069
ainted+0.065
umbled+0.063
 fists+0.062
Neg logit contributions
 visit-0.083
 coral-0.081
 who-0.078
 farm-0.077
 planet-0.077
Token.
Token ID13
Feature activation+1.41e-01

Pos logit contributions
 fists+0.052
aned+0.052
ares+0.050
omm+0.049
ented+0.048
Neg logit contributions
 visit-0.029
 who-0.027
 appreciate-0.026
 live-0.025
 coral-0.023
Token She
Token ID1375
Feature activation+4.59e-02

Pos logit contributions
 visit+0.003
 appreciate+0.003
 who+0.002
 live+0.002
 coral+0.002
Neg logit contributions
aned-0.005
 fists-0.005
ares-0.004
ented-0.004
 firmly-0.004
Token had
Token ID550
Feature activation+1.21e+00

Pos logit contributions
 visit+0.001
 appreciate+0.001
 who+0.001
 coral+0.001
 live+0.001
Neg logit contributions
aned-0.001
 fists-0.001
ares-0.001
ented-0.001
omm-0.001
Token been
Token ID587
Feature activation-9.57e-01

Pos logit contributions
 visit+0.026
 appreciate+0.026
 who+0.024
 live+0.023
 coral+0.023
Neg logit contributions
aned-0.036
 fists-0.036
ares-0.034
ented-0.033
 firmly-0.032
Token fore
Token ID1674
Feature activation-6.56e+00

Pos logit contributions
aned+0.031
 fists+0.030
ares+0.030
ented+0.028
omm+0.028
Neg logit contributions
 visit-0.019
 who-0.019
 appreciate-0.018
 live-0.017
 wedding-0.017
Tokenshadow
Token ID19106
Feature activation-1.82e+00

Pos logit contributions
 fists+0.143
aned+0.130
omm+0.127
ares+0.122
ented+0.115
Neg logit contributions
 visit-0.191
 who-0.186
 appreciate-0.182
 outdoors-0.171
 live-0.169
Tokened
Token ID276
Feature activation-7.85e-01

Pos logit contributions
 fists+0.035
aned+0.033
ares+0.032
 firmly+0.027
 brakes+0.027
Neg logit contributions
 who-0.057
 visit-0.056
 appreciate-0.054
 live-0.051
 outdoors-0.051
Token about
Token ID546
Feature activation+2.19e+00

Pos logit contributions
aned+0.025
 fists+0.024
ares+0.023
ented+0.023
omm+0.022
Neg logit contributions
 visit-0.016
 appreciate-0.016
 who-0.015
 live-0.014
 coral-0.014
Token the
Token ID262
Feature activation-4.31e-01

Pos logit contributions
 visit+0.047
 appreciate+0.047
 live+0.042
 wedding+0.042
 farm+0.042
Neg logit contributions
 fists-0.064
aned-0.062
ares-0.059
 firmly-0.058
ented-0.057
Token power
Token ID1176
Feature activation-2.19e+00

Pos logit contributions
 fists+0.013
aned+0.012
ares+0.012
ented+0.012
 firmly+0.011
Neg logit contributions
 appreciate-0.009
 visit-0.009
 live-0.008
 who-0.008
 coral-0.008
Token
Token ID198
Feature activation+3.35e-01

Pos logit contributions
 visit+0.024
 appreciate+0.022
 wedding+0.021
 farm+0.020
 coral+0.020
Neg logit contributions
aned-0.056
 fists-0.055
ares-0.053
 firmly-0.052
ented-0.051
TokenThe
Token ID464
Feature activation-9.44e-01

Pos logit contributions
 visit+0.008
 appreciate+0.007
 wedding+0.007
 farm+0.007
 live+0.007
Neg logit contributions
aned-0.009
 fists-0.009
ares-0.009
 firmly-0.009
ented-0.009
Token bad
Token ID2089
Feature activation-1.60e+00

Pos logit contributions
aned+0.029
 fists+0.029
ares+0.027
ented+0.027
 firmly+0.026
Neg logit contributions
 visit-0.020
 appreciate-0.019
 who-0.018
 live-0.018
 wedding-0.018
Token ending
Token ID7464
Feature activation-1.30e+00

Pos logit contributions
aned+0.046
 fists+0.045
ares+0.043
ented+0.042
 firmly+0.041
Neg logit contributions
 visit-0.037
 appreciate-0.036
 who-0.034
 live-0.033
 wedding-0.033
Token was
Token ID373
Feature activation-4.01e-01

Pos logit contributions
aned+0.039
 fists+0.039
ares+0.037
ented+0.036
omm+0.035
Neg logit contributions
 visit-0.028
 appreciate-0.027
 who-0.026
 live-0.026
arium-0.024
Token fore
Token ID1674
Feature activation-6.55e+00

Pos logit contributions
aned+0.012
 fists+0.012
ares+0.011
ented+0.011
omm+0.010
Neg logit contributions
 visit-0.009
 appreciate-0.009
 who-0.008
 live-0.008
 wedding-0.008
Tokenshadow
Token ID19106
Feature activation-1.54e+00

Pos logit contributions
 fists+0.135
aned+0.124
ares+0.115
omm+0.112
ented+0.108
Neg logit contributions
 visit-0.203
 appreciate-0.198
 who-0.197
 live-0.186
 farm-0.181
Tokened
Token ID276
Feature activation-1.21e+00

Pos logit contributions
 fists+0.027
aned+0.025
ares+0.025
ented+0.022
 firmly+0.021
Neg logit contributions
 visit-0.051
 who-0.051
 appreciate-0.050
 live-0.048
 coral-0.046
Token by
Token ID416
Feature activation+1.24e+00

Pos logit contributions
aned+0.036
 fists+0.035
ares+0.034
ented+0.033
omm+0.031
Neg logit contributions
 visit-0.027
 appreciate-0.026
 who-0.025
 live-0.024
 coral-0.023
Token Maggie
Token ID33014
Feature activation-7.81e-03

Pos logit contributions
 visit+0.027
 appreciate+0.026
 farm+0.024
 who+0.024
 live+0.024
Neg logit contributions
 fists-0.037
aned-0.036
ares-0.034
ented-0.033
 firmly-0.033
Token's
Token ID338
Feature activation-1.71e+00

Pos logit contributions
aned+0.000
 fists+0.000
ares+0.000
ented+0.000
 firmly+0.000
Neg logit contributions
 visit-0.000
 appreciate-0.000
 who-0.000
 live-0.000
 coral-0.000
Token quickly
Token ID2952
Feature activation-1.73e+00

Pos logit contributions
aned+0.005
 fists+0.005
ares+0.005
ented+0.005
 firmly+0.005
Neg logit contributions
 visit-0.004
 appreciate-0.004
 who-0.004
 live-0.004
 coral-0.003
Token helped
Token ID4193
Feature activation-9.51e-01

Pos logit contributions
 fists+0.049
aned+0.048
ares+0.047
omm+0.046
ented+0.044
Neg logit contributions
 visit-0.040
 appreciate-0.039
 who-0.038
 live-0.038
 wedding-0.035
Token Tim
Token ID5045
Feature activation-1.15e+00

Pos logit contributions
aned+0.031
 fists+0.030
ares+0.029
ented+0.028
uffed+0.027
Neg logit contributions
 visit-0.021
 appreciate-0.019
 who-0.019
 live-0.018
 celebrate-0.017
Tokenmy
Token ID1820
Feature activation-1.62e+00

Pos logit contributions
 fists+0.038
aned+0.038
ares+0.036
ented+0.036
 firmly+0.035
Neg logit contributions
 visit-0.022
 appreciate-0.021
 who-0.019
 live-0.019
 farm-0.018
Token get
Token ID651
Feature activation-3.34e+00

Pos logit contributions
aned+0.048
 fists+0.048
ares+0.045
ented+0.044
omm+0.044
Neg logit contributions
 visit-0.038
 appreciate-0.035
 who-0.034
 live-0.033
 celebrate-0.031
Token unst
Token ID15014
Feature activation-6.47e+00

Pos logit contributions
aned+0.108
 fists+0.103
ares+0.100
omm+0.096
ented+0.094
Neg logit contributions
 visit-0.077
 live-0.070
 appreciate-0.068
 who-0.068
 celebrate-0.065
Tokenuck
Token ID1347
Feature activation-1.19e+00

Pos logit contributions
 fists+0.134
aned+0.127
ares+0.115
ula+0.107
ented+0.104
Neg logit contributions
 visit-0.201
 appreciate-0.185
 outdoors-0.175
 farm-0.174
 live-0.174
Token.
Token ID13
Feature activation-8.18e-01

Pos logit contributions
aned+0.041
 fists+0.040
ares+0.039
ented+0.038
omm+0.037
Neg logit contributions
 visit-0.021
 appreciate-0.020
 who-0.020
 live-0.018
 coral-0.018
Token She
Token ID1375
Feature activation-3.98e-01

Pos logit contributions
aned+0.026
 fists+0.026
ares+0.025
ented+0.024
 firmly+0.024
Neg logit contributions
 visit-0.016
 appreciate-0.015
 who-0.014
 live-0.014
 farm-0.014
Token said
Token ID531
Feature activation-2.65e+00

Pos logit contributions
 fists+0.012
aned+0.012
ares+0.012
ented+0.011
ula+0.011
Neg logit contributions
 visit-0.009
 appreciate-0.008
 who-0.008
 live-0.008
 farm-0.008
Token,
Token ID11
Feature activation+8.50e-01

Pos logit contributions
aned+0.087
 fists+0.085
ares+0.081
ented+0.078
omm+0.073
Neg logit contributions
 visit-0.051
 appreciate-0.049
 who-0.049
 live-0.045
 wedding-0.045
Token and
Token ID290
Feature activation-1.44e+00

Pos logit contributions
 fists+0.008
aned+0.008
ares+0.008
ented+0.007
bled+0.007
Neg logit contributions
 visit-0.003
 who-0.003
 appreciate-0.003
 farm-0.002
 wedding-0.002
Token Lily
Token ID20037
Feature activation-7.66e-01

Pos logit contributions
 fists+0.048
aned+0.048
ares+0.046
ented+0.043
omm+0.041
Neg logit contributions
 visit-0.029
 appreciate-0.027
 who-0.026
 live-0.025
 celebrate-0.024
Token carefully
Token ID7773
Feature activation-1.50e+00

Pos logit contributions
 fists+0.024
ares+0.024
aned+0.023
ented+0.022
ula+0.021
Neg logit contributions
 visit-0.016
 appreciate-0.015
 who-0.015
 live-0.014
 slept-0.013
Token put
Token ID1234
Feature activation-1.12e+00

Pos logit contributions
 fists+0.050
ares+0.048
aned+0.048
ented+0.045
omm+0.044
Neg logit contributions
 visit-0.030
 appreciate-0.027
 who-0.027
 live-0.025
 wedding-0.024
Token the
Token ID262
Feature activation-3.33e+00

Pos logit contributions
aned+0.043
ares+0.042
 fists+0.041
ented+0.038
omm+0.037
Neg logit contributions
 visit-0.017
 who-0.016
 live-0.014
 appreciate-0.013
 outdoors-0.013
Token therm
Token ID21969
Feature activation-6.43e+00

Pos logit contributions
ares+0.090
aned+0.088
 fists+0.085
ented+0.078
 firmly+0.074
Neg logit contributions
 visit-0.087
 who-0.077
 appreciate-0.077
 farm-0.077
 living-0.076
Tokenometer
Token ID15635
Feature activation-2.72e+00

Pos logit contributions
ares+0.139
 fists+0.137
aned+0.128
 cheating+0.112
ived+0.111
Neg logit contributions
 who-0.170
 visit-0.166
 appreciate-0.160
 living-0.152
 live-0.150
Token under
Token ID739
Feature activation+1.60e+00

Pos logit contributions
aned+0.086
 fists+0.085
ares+0.084
omm+0.079
ented+0.078
Neg logit contributions
 visit-0.055
 who-0.053
 appreciate-0.050
 live-0.048
 outdoors-0.046
Token her
Token ID607
Feature activation-1.47e-01

Pos logit contributions
 visit+0.027
 who+0.024
 appreciate+0.023
 live+0.022
 celebrate+0.021
Neg logit contributions
aned-0.059
ares-0.057
 fists-0.056
ented-0.054
uffed-0.053
Token mom
Token ID1995
Feature activation-5.34e-01

Pos logit contributions
aned+0.004
 fists+0.004
ares+0.004
ented+0.004
 firmly+0.004
Neg logit contributions
 visit-0.003
 appreciate-0.003
 who-0.003
 farm-0.003
 wedding-0.003
Tokenmy
Token ID1820
Feature activation-8.47e-01

Pos logit contributions
aned+0.017
 fists+0.017
ares+0.017
ented+0.016
 firmly+0.016
Neg logit contributions
 visit-0.010
 appreciate-0.010
 who-0.009
 live-0.009
 farm-0.009
Token yard
Token ID12699
Feature activation+2.28e+00

Pos logit contributions
 appreciate+0.019
 visit+0.018
 live+0.016
 who+0.016
 celebrate+0.016
Neg logit contributions
 fists-0.030
aned-0.029
 firmly-0.027
ented-0.026
ares-0.026
Token.
Token ID13
Feature activation-6.29e-01

Pos logit contributions
 appreciate+0.050
 visit+0.049
 coral+0.045
 live+0.044
 wedding+0.044
Neg logit contributions
 fists-0.066
aned-0.066
ares-0.061
 firmly-0.061
ented-0.060
Token He
Token ID679
Feature activation+1.80e-01

Pos logit contributions
aned+0.020
 fists+0.019
ares+0.019
ented+0.018
bled+0.017
Neg logit contributions
 visit-0.013
 appreciate-0.012
 who-0.012
 live-0.011
 farm-0.011
Token had
Token ID550
Feature activation+8.26e-01

Pos logit contributions
 visit+0.004
 appreciate+0.004
 who+0.004
 live+0.004
 farm+0.003
Neg logit contributions
aned-0.005
 fists-0.005
ares-0.005
ented-0.005
omm-0.005
Token been
Token ID587
Feature activation-1.29e+00

Pos logit contributions
 visit+0.018
 appreciate+0.017
 who+0.016
 live+0.016
 coral+0.015
Neg logit contributions
aned-0.025
 fists-0.025
ares-0.025
ented-0.023
omm-0.022
Token fore
Token ID1674
Feature activation-6.40e+00

Pos logit contributions
aned+0.039
 fists+0.038
ares+0.038
ented+0.035
omm+0.035
Neg logit contributions
 visit-0.028
 who-0.028
 appreciate-0.027
 live-0.025
 wedding-0.025
Tokenshadow
Token ID19106
Feature activation-1.89e+00

Pos logit contributions
 fists+0.137
aned+0.126
omm+0.119
ares+0.117
ented+0.110
Neg logit contributions
 visit-0.191
 who-0.187
 appreciate-0.183
 live-0.170
 outdoors-0.169
Tokened
Token ID276
Feature activation-1.21e+00

Pos logit contributions
 fists+0.034
ares+0.032
aned+0.032
ented+0.026
 firmly+0.025
Neg logit contributions
 who-0.061
 visit-0.060
 appreciate-0.058
 live-0.055
 living-0.054
Token about
Token ID546
Feature activation+1.45e+00

Pos logit contributions
aned+0.040
 fists+0.038
ares+0.038
ented+0.036
omm+0.035
Neg logit contributions
 visit-0.025
 appreciate-0.023
 who-0.023
 live-0.021
 farm-0.020
Token this
Token ID428
Feature activation-2.20e-01

Pos logit contributions
 visit+0.031
 appreciate+0.031
 who+0.028
 live+0.028
 wedding+0.028
Neg logit contributions
 fists-0.043
aned-0.043
ares-0.040
ented-0.039
 firmly-0.039
Token bad
Token ID2089
Feature activation-9.56e-01

Pos logit contributions
aned+0.007
 fists+0.007
ares+0.007
ented+0.006
 firmly+0.006
Neg logit contributions
 visit-0.004
 appreciate-0.004
 who-0.004
 live-0.004
 farm-0.004
Token not
Token ID407
Feature activation-5.87e-01

Pos logit contributions
aned+0.049
 fists+0.049
ented+0.046
ares+0.046
omm+0.046
Neg logit contributions
 visit-0.040
 appreciate-0.039
 who-0.038
 live-0.036
 celebrate-0.033
Token want
Token ID765
Feature activation-1.34e+00

Pos logit contributions
 fists+0.019
aned+0.019
ares+0.018
ented+0.017
 firmly+0.017
Neg logit contributions
 visit-0.011
 appreciate-0.011
 farm-0.010
 wedding-0.010
 coral-0.010
Token to
Token ID284
Feature activation-2.60e+00

Pos logit contributions
aned+0.052
ares+0.049
 fists+0.049
ented+0.047
uffed+0.046
Neg logit contributions
 visit-0.023
 appreciate-0.020
 who-0.019
 live-0.018
 coral-0.017
Token give
Token ID1577
Feature activation-3.82e+00

Pos logit contributions
aned+0.080
 fists+0.079
ares+0.075
ented+0.074
 firmly+0.072
Neg logit contributions
 visit-0.056
 appreciate-0.054
 live-0.050
 who-0.050
 wedding-0.048
Token the
Token ID262
Feature activation-2.36e+00

Pos logit contributions
aned+0.118
omm+0.108
ares+0.105
 fists+0.102
ula+0.098
Neg logit contributions
 visit-0.093
 who-0.089
 live-0.087
 appreciate-0.084
 play-0.080
Token chain
Token ID6333
Feature activation-6.39e+00

Pos logit contributions
aned+0.067
 fists+0.066
ares+0.062
ented+0.059
 firmly+0.059
Neg logit contributions
 visit-0.058
 appreciate-0.056
 who-0.053
 live-0.052
 farm-0.052
Token.
Token ID13
Feature activation-7.72e-01

Pos logit contributions
aned+0.222
 fists+0.213
omm+0.209
uffed+0.195
ares+0.190
Neg logit contributions
 who-0.120
 visit-0.118
 live-0.113
 play-0.103
 appreciate-0.100
Token They
Token ID1119
Feature activation-8.14e-02

Pos logit contributions
 fists+0.028
aned+0.027
ares+0.026
ented+0.026
 firmly+0.025
Neg logit contributions
 visit-0.012
 appreciate-0.012
 wedding-0.010
 who-0.010
 coral-0.010
Token liked
Token ID8288
Feature activation-3.05e-02

Pos logit contributions
aned+0.002
 fists+0.002
ares+0.002
omm+0.002
ula+0.002
Neg logit contributions
 who-0.002
 appreciate-0.002
 visit-0.002
 live-0.002
 liked-0.001
Token the
Token ID262
Feature activation-2.20e+00

Pos logit contributions
aned+0.001
 fists+0.001
ares+0.001
ented+0.001
omm+0.001
Neg logit contributions
 visit-0.001
 appreciate-0.001
 who-0.001
 live-0.001
 farm-0.000
Token chain
Token ID6333
Feature activation-4.31e+00

Pos logit contributions
aned+0.054
 fists+0.054
ares+0.051
ented+0.049
 firmly+0.047
Neg logit contributions
 visit-0.060
 appreciate-0.058
 who-0.055
 live-0.054
 farm-0.054
TokenThe
Token ID464
Feature activation-2.45e+00

Pos logit contributions
aned+0.023
 fists+0.022
ares+0.022
ula+0.022
 firmly+0.022
Neg logit contributions
 visit-0.012
 coral-0.011
 wedding-0.011
 farm-0.011
 appreciate-0.011
Token little
Token ID1310
Feature activation-3.22e+00

Pos logit contributions
aned+0.084
ares+0.078
 fists+0.078
 firmly+0.073
ented+0.073
Neg logit contributions
 visit-0.048
 appreciate-0.045
 who-0.043
 wedding-0.041
 farm-0.040
Token girl
Token ID2576
Feature activation+3.06e-01

Pos logit contributions
aned+0.130
 fists+0.121
ares+0.120
ented+0.116
 firmly+0.114
Neg logit contributions
 visit-0.044
 appreciate-0.041
 who-0.038
 live-0.035
 wedding-0.034
Token took
Token ID1718
Feature activation-2.08e+00

Pos logit contributions
 visit+0.007
 appreciate+0.007
 live+0.006
 coral+0.006
 who+0.006
Neg logit contributions
aned-0.008
 fists-0.008
ares-0.008
ented-0.008
 firmly-0.008
Token the
Token ID262
Feature activation-3.18e+00

Pos logit contributions
aned+0.087
ares+0.083
 fists+0.080
ented+0.078
uffed+0.078
Neg logit contributions
 visit-0.030
 appreciate-0.023
 celebrate-0.022
 live-0.021
 who-0.021
Token er
Token ID1931
Feature activation-6.39e+00

Pos logit contributions
aned+0.095
ares+0.090
 fists+0.086
 firmly+0.083
bled+0.083
Neg logit contributions
 visit-0.077
 who-0.066
 appreciate-0.066
 living-0.065
 play-0.063
Tokenaser
Token ID6005
Feature activation-1.73e+00

Pos logit contributions
 fists+0.103
aned+0.094
 firmly+0.076
 brakes+0.074
 collapsed+0.070
Neg logit contributions
 who-0.218
 appreciate-0.209
 visit-0.205
 live-0.200
Always-0.197
Token and
Token ID290
Feature activation-5.06e-01

Pos logit contributions
aned+0.049
 fists+0.049
ares+0.046
ented+0.045
 firmly+0.043
Neg logit contributions
 visit-0.040
 appreciate-0.039
 who-0.036
 live-0.036
 farm-0.035
Token starting
Token ID3599
Feature activation-3.56e-01

Pos logit contributions
aned+0.014
 fists+0.014
ares+0.014
ented+0.013
omm+0.013
Neg logit contributions
 visit-0.012
 appreciate-0.012
 who-0.011
 live-0.011
 coral-0.010
Token running
Token ID2491
Feature activation-7.19e-01

Pos logit contributions
ares+0.012
aned+0.012
ented+0.011
 fists+0.011
omm+0.011
Neg logit contributions
 visit-0.008
 appreciate-0.007
 who-0.006
 live-0.006
 outdoors-0.006
Token around
Token ID1088
Feature activation+2.04e+00

Pos logit contributions
aned+0.022
 fists+0.022
ares+0.021
ented+0.020
omm+0.020
Neg logit contributions
 visit-0.016
 appreciate-0.015
 who-0.014
 live-0.014
 coral-0.014
Token and
Token ID290
Feature activation-2.71e+00

Pos logit contributions
aned+0.122
uffed+0.114
omm+0.113
ares+0.113
cases+0.113
Neg logit contributions
 who-0.019
 like-0.019
 and-0.016
-0.013
 the-0.012
Token pulls
Token ID16194
Feature activation-2.78e+00

Pos logit contributions
aned+0.054
ier+0.052
omm+0.051
bled+0.049
umbled+0.047
Neg logit contributions
 who-0.083
 visit-0.082
 live-0.078
 play-0.077
 sing-0.074
Token,
Token ID11
Feature activation+8.70e-01

Pos logit contributions
aned+0.123
uffed+0.116
ares+0.114
omm+0.113
ounced+0.112
Neg logit contributions
 who-0.025
 like-0.023
-0.017
 visit-0.017
 and-0.017
Token but
Token ID475
Feature activation-2.96e+00

Pos logit contributions
 who+0.010
 visit+0.007
 appreciate+0.006
 farm+0.005
 live+0.005
Neg logit contributions
aned-0.036
ares-0.035
omm-0.034
 fists-0.034
bled-0.033
Token the
Token ID262
Feature activation-2.21e+00

Pos logit contributions
ares+0.120
aned+0.119
 fists+0.107
omm+0.105
inged+0.104
Neg logit contributions
 who-0.036
 visit-0.034
 live-0.034
 play-0.031
 every-0.031
Token box
Token ID3091
Feature activation-6.37e+00

Pos logit contributions
aned+0.060
 fists+0.058
ares+0.057
ented+0.053
 firmly+0.052
Neg logit contributions
 visit-0.056
 appreciate-0.054
 who-0.051
 live-0.050
 farm-0.050
Token does
Token ID857
Feature activation-2.87e+00

Pos logit contributions
ula+0.191
omm+0.181
 fists+0.177
aned+0.176
ging+0.169
Neg logit contributions
 live-0.125
 lived-0.110
 visit-0.109
 who-0.107
 liked-0.106
Token not
Token ID407
Feature activation-3.89e+00

Pos logit contributions
 fists+0.099
aned+0.098
ares+0.097
umbled+0.096
ented+0.096
Neg logit contributions
 visit-0.046
 appreciate-0.043
 who-0.042
 live-0.042
 sing-0.037
Token move
Token ID1445
Feature activation-3.46e+00

Pos logit contributions
aned+0.118
 fists+0.115
ares+0.108
omm+0.107
uffed+0.104
Neg logit contributions
 visit-0.095
 appreciate-0.087
 live-0.087
 who-0.080
 celebrate-0.078
Token.
Token ID13
Feature activation-1.76e+00

Pos logit contributions
aned+0.156
omm+0.153
 fists+0.150
uffed+0.148
bled+0.145
Neg logit contributions
 who-0.027
 live-0.021
 visit-0.020
 like-0.015
 outdoors-0.013
Token She
Token ID1375
Feature activation-1.97e+00

Pos logit contributions
aned+0.069
 fists+0.067
ares+0.064
ented+0.062
 firmly+0.061
Neg logit contributions
 visit-0.024
 appreciate-0.021
 who-0.021
 live-0.019
 farm-0.017
Token the
Token ID262
Feature activation-7.13e-01

Pos logit contributions
 visit+0.035
 appreciate+0.034
 who+0.031
 live+0.031
 wedding+0.030
Neg logit contributions
aned-0.049
 fists-0.049
ares-0.047
ented-0.045
 firmly-0.044
Token floor
Token ID4314
Feature activation+1.17e+00

Pos logit contributions
aned+0.021
ares+0.020
 fists+0.019
 firmly+0.018
ented+0.018
Neg logit contributions
 visit-0.017
 appreciate-0.016
 who-0.016
 farm-0.015
 wedding-0.015
Token and
Token ID290
Feature activation-1.04e+00

Pos logit contributions
 visit+0.018
 appreciate+0.017
 who+0.017
 live+0.016
 farm+0.015
Neg logit contributions
aned-0.041
 fists-0.041
ares-0.040
ented-0.039
omm-0.037
Token hugged
Token ID41130
Feature activation-8.61e-01

Pos logit contributions
ares+0.030
aned+0.030
 fists+0.030
ented+0.028
omm+0.028
Neg logit contributions
 visit-0.024
 who-0.023
 appreciate-0.023
 live-0.021
 coral-0.020
Token the
Token ID262
Feature activation-2.23e+00

Pos logit contributions
aned+0.027
 fists+0.026
ares+0.026
ented+0.025
omm+0.023
Neg logit contributions
 visit-0.018
 appreciate-0.018
 who-0.017
 live-0.016
 farm-0.015
Token er
Token ID1931
Feature activation-6.33e+00

Pos logit contributions
aned+0.067
ares+0.064
 fists+0.061
 firmly+0.058
uffed+0.057
Neg logit contributions
 visit-0.052
 appreciate-0.049
 who-0.048
 living-0.045
 live-0.045
Tokenaser
Token ID6005
Feature activation-5.50e-01

Pos logit contributions
 fists+0.103
aned+0.094
 brakes+0.076
 firmly+0.073
 collapsed+0.068
Neg logit contributions
 who-0.222
 appreciate-0.206
 live-0.200
 visit-0.197
 living-0.196
Token tight
Token ID5381
Feature activation+1.06e-02

Pos logit contributions
 fists+0.016
aned+0.016
ares+0.016
ented+0.015
 firmly+0.015
Neg logit contributions
 visit-0.012
 appreciate-0.011
 live-0.010
 who-0.010
 coral-0.010
Token.
Token ID13
Feature activation-6.79e-01

Pos logit contributions
 visit+0.000
 appreciate+0.000
 who+0.000
 live+0.000
 wedding+0.000
Neg logit contributions
aned-0.000
 fists-0.000
ares-0.000
ented-0.000
omm-0.000
Token The
Token ID383
Feature activation-2.47e+00

Pos logit contributions
aned+0.024
 fists+0.024
ares+0.023
ented+0.023
 firmly+0.022
Neg logit contributions
 visit-0.011
 appreciate-0.010
 who-0.009
 live-0.009
 farm-0.009
Token er
Token ID1931
Feature activation-5.45e+00

Pos logit contributions
aned+0.075
ares+0.071
 fists+0.067
 firmly+0.064
uffed+0.064
Neg logit contributions
 visit-0.058
 appreciate-0.054
 who-0.054
 living-0.050
 wedding-0.050
Token that
Token ID326
Feature activation+3.77e-01

Pos logit contributions
aned+0.008
 fists+0.008
ares+0.008
ented+0.008
 firmly+0.007
Neg logit contributions
 visit-0.005
 appreciate-0.005
 who-0.004
 live-0.004
 wedding-0.004
Token the
Token ID262
Feature activation-1.87e+00

Pos logit contributions
 visit+0.009
 appreciate+0.009
 coral+0.008
 farm+0.008
 wedding+0.008
Neg logit contributions
 fists-0.010
aned-0.010
ares-0.009
 firmly-0.009
ented-0.009
Token zipper
Token ID48992
Feature activation-5.08e+00

Pos logit contributions
 fists+0.052
aned+0.052
ares+0.049
ented+0.048
 firmly+0.047
Neg logit contributions
 visit-0.043
 appreciate-0.043
 who-0.040
 live-0.039
 coral-0.039
Token had
Token ID550
Feature activation-1.96e+00

Pos logit contributions
 fists+0.156
aned+0.153
ares+0.152
omm+0.145
ented+0.143
Neg logit contributions
 visit-0.107
 who-0.102
 appreciate-0.099
 live-0.098
 farm-0.088
Token become
Token ID1716
Feature activation-3.26e+00

Pos logit contributions
aned+0.059
ares+0.059
 fists+0.059
ented+0.056
omm+0.054
Neg logit contributions
 visit-0.043
 appreciate-0.041
 live-0.038
 who-0.037
 wedding-0.035
Token unst
Token ID15014
Feature activation-6.33e+00

Pos logit contributions
aned+0.092
ares+0.088
 fists+0.087
omm+0.080
ented+0.080
Neg logit contributions
 visit-0.078
 appreciate-0.078
 who-0.076
 live-0.074
 coral-0.069
Tokenuck
Token ID1347
Feature activation-1.00e+00

Pos logit contributions
 fists+0.128
aned+0.125
ares+0.107
 firmly+0.102
 brakes+0.101
Neg logit contributions
 visit-0.188
 appreciate-0.170
 outdoors-0.167
Always-0.165
 live-0.164
Token.
Token ID13
Feature activation-1.36e-01

Pos logit contributions
aned+0.033
 fists+0.033
ares+0.032
ented+0.030
omm+0.030
Neg logit contributions
 visit-0.018
 appreciate-0.018
 who-0.017
 live-0.016
 coral-0.016
Token She
Token ID1375
Feature activation-4.11e-01

Pos logit contributions
 fists+0.004
aned+0.004
ares+0.004
ented+0.004
omm+0.004
Neg logit contributions
 visit-0.003
 appreciate-0.003
 wedding-0.003
 coral-0.003
 farm-0.003
Token was
Token ID373
Feature activation-9.89e-01

Pos logit contributions
 fists+0.012
aned+0.012
ares+0.011
ented+0.011
 firmly+0.010
Neg logit contributions
 visit-0.010
 appreciate-0.009
 who-0.009
 live-0.009
 coral-0.008
Token relieved
Token ID22598
Feature activation+1.44e-01

Pos logit contributions
aned+0.029
 fists+0.029
ares+0.027
ented+0.026
 firmly+0.026
Neg logit contributions
 visit-0.022
 appreciate-0.022
 who-0.020
 live-0.020
 wedding-0.020
Token,
Token ID11
Feature activation+2.25e+00

Pos logit contributions
 fists+0.055
aned+0.054
ares+0.051
ented+0.049
omm+0.049
Neg logit contributions
 visit-0.014
 who-0.014
 appreciate-0.011
 coral-0.010
 farm-0.010
Token and
Token ID290
Feature activation-1.35e+00

Pos logit contributions
 visit+0.049
 appreciate+0.048
 wedding+0.045
 live+0.045
 coral+0.043
Neg logit contributions
aned-0.067
 fists-0.067
 firmly-0.064
ented-0.061
ares-0.059
Token Sue
Token ID26089
Feature activation-1.74e+00

Pos logit contributions
aned+0.042
 fists+0.041
ares+0.041
ented+0.038
omm+0.037
Neg logit contributions
 visit-0.028
 appreciate-0.027
 who-0.027
 live-0.025
 coral-0.025
Token put
Token ID1234
Feature activation-7.61e-01

Pos logit contributions
aned+0.048
 fists+0.048
ares+0.045
ented+0.044
 firmly+0.043
Neg logit contributions
 visit-0.041
 appreciate-0.040
 who-0.037
 live-0.037
 coral-0.037
Token the
Token ID262
Feature activation-3.21e+00

Pos logit contributions
aned+0.030
ares+0.029
 fists+0.029
ented+0.027
omm+0.027
Neg logit contributions
 visit-0.011
 who-0.010
 live-0.009
 appreciate-0.008
 celebrate-0.008
Token therm
Token ID21969
Feature activation-6.31e+00

Pos logit contributions
ares+0.091
aned+0.088
 fists+0.083
ented+0.079
ived+0.077
Neg logit contributions
 visit-0.081
 farm-0.075
 who-0.074
 living-0.072
 live-0.071
Tokenometer
Token ID15635
Feature activation-2.16e+00

Pos logit contributions
ares+0.137
 fists+0.130
aned+0.127
 cheating+0.110
 excuses+0.109
Neg logit contributions
 who-0.168
 visit-0.158
 appreciate-0.155
 live-0.150
 living-0.146
Token in
Token ID287
Feature activation+1.25e+00

Pos logit contributions
aned+0.066
 fists+0.065
ares+0.063
ented+0.060
omm+0.059
Neg logit contributions
 visit-0.046
 appreciate-0.043
 who-0.043
 live-0.041
 farm-0.040
Token.
Token ID13
Feature activation-1.42e+00

Pos logit contributions
 visit+0.023
 appreciate+0.022
 who+0.020
 live+0.020
 coral+0.019
Neg logit contributions
aned-0.044
 fists-0.042
ares-0.042
ented-0.041
uffed-0.039
Token They
Token ID1119
Feature activation+4.30e-01

Pos logit contributions
aned+0.047
 fists+0.047
ares+0.045
ented+0.044
 firmly+0.042
Neg logit contributions
 visit-0.026
 appreciate-0.025
 who-0.023
 live-0.023
 farm-0.022
Token waited
Token ID13488
Feature activation-2.49e-01

Pos logit contributions
 visit+0.010
 appreciate+0.010
 wedding+0.009
 farm+0.009
 coral+0.009
Neg logit contributions
 fists-0.011
aned-0.011
 firmly-0.010
ented-0.010
ares-0.010
Token mom
Token ID1995
Feature activation-7.20e-01

Pos logit contributions
aned+0.082
ares+0.079
 fists+0.073
ula+0.072
uffed+0.072
Neg logit contributions
 visit-0.054
 appreciate-0.050
 farm-0.050
 who-0.048
 live-0.044
Token again
Token ID757
Feature activation+1.40e+00

Pos logit contributions
 fists+0.022
aned+0.022
ares+0.021
ented+0.020
 firmly+0.020
Neg logit contributions
 visit-0.015
 appreciate-0.014
 coral-0.013
 live-0.013
 wedding-0.013
Token.
Token ID13
Feature activation-5.76e-02

Pos logit contributions
 visit+0.028
 appreciate+0.028
 coral+0.026
 wedding+0.026
 live+0.026
Neg logit contributions
 fists-0.041
aned-0.041
ares-0.039
 firmly-0.038
ented-0.038
Token<|endoftext|>
Token ID50256
Feature activation+3.84e+00

Pos logit contributions
 fists+0.002
omm+0.002
aned+0.002
ares+0.002
ula+0.002
Neg logit contributions
 wedding-0.001
 coral-0.001
 appreciate-0.001
 visit-0.001
 farm-0.001
TokenOnce
Token ID7454
Feature activation+1.12e+00

Pos logit contributions
 appreciate+0.072
 wedding+0.068
 visit+0.064
 coral+0.063
 farm+0.062
Neg logit contributions
aned-0.118
 fists-0.117
ares-0.112
ula-0.110
 firmly-0.109
Token upon
Token ID2402
Feature activation+4.73e+00

Pos logit contributions
 visit+0.020
 appreciate+0.019
 who+0.017
 live+0.017
 coral+0.017
Neg logit contributions
aned-0.038
 fists-0.038
ares-0.036
ented-0.035
 firmly-0.034
Token a
Token ID257
Feature activation+2.26e+00

Pos logit contributions
 wedding+0.153
 farm+0.150
 ranch+0.148
 habitats+0.147
arium+0.147
Neg logit contributions
 fists-0.061
aned-0.059
 off-0.056
 firmly-0.056
 worse-0.055
Token time
Token ID640
Feature activation-4.42e-01

Pos logit contributions
 coral+0.070
 appreciate+0.069
 live+0.067
 visit+0.064
 celebrate+0.063
Neg logit contributions
 fists-0.042
aned-0.039
 firmly-0.038
ares-0.037
 problem-0.035
Token,
Token ID11
Feature activation+1.23e+00

Pos logit contributions
aned+0.012
 fists+0.012
ares+0.012
ented+0.011
 firmly+0.011
Neg logit contributions
 visit-0.010
 appreciate-0.010
 who-0.009
 live-0.009
 coral-0.009
Token there
Token ID612
Feature activation+8.35e-01

Pos logit contributions
 appreciate+0.030
 visit+0.030
 wedding+0.029
 farm+0.028
 coral+0.027
Neg logit contributions
 fists-0.032
 firmly-0.030
ares-0.030
aned-0.030
ented-0.028
Token was
Token ID373
Feature activation+1.53e+00

Pos logit contributions
 visit+0.020
 appreciate+0.019
 who+0.018
 live+0.018
 farm+0.017
Neg logit contributions
aned-0.024
 fists-0.024
ares-0.022
ented-0.022
 firmly-0.021
Token and
Token ID290
Feature activation-1.34e-01

Pos logit contributions
 visit+0.030
 appreciate+0.030
 wedding+0.027
 live+0.027
 farm+0.027
Neg logit contributions
 fists-0.040
aned-0.040
 firmly-0.037
ares-0.037
ented-0.036
Token sound
Token ID2128
Feature activation-8.04e-01

Pos logit contributions
 fists+0.004
aned+0.004
 firmly+0.004
ented+0.003
bled+0.003
Neg logit contributions
 visit-0.003
 farm-0.003
 appreciate-0.003
 coral-0.003
arium-0.003
Token.
Token ID13
Feature activation+6.80e-01

Pos logit contributions
aned+0.026
 fists+0.026
ares+0.024
ented+0.024
omm+0.023
Neg logit contributions
 visit-0.016
 appreciate-0.015
 who-0.014
 live-0.014
 wedding-0.014
Token<|endoftext|>
Token ID50256
Feature activation+3.76e+00

Pos logit contributions
 visit+0.010
 appreciate+0.010
 live+0.009
 who+0.008
 wedding+0.008
Neg logit contributions
 fists-0.025
aned-0.025
ares-0.024
ented-0.023
 firmly-0.023
TokenOnce
Token ID7454
Feature activation+1.50e+00

Pos logit contributions
 appreciate+0.086
 visit+0.080
 wedding+0.080
 coral+0.075
 farm+0.074
Neg logit contributions
aned-0.101
 fists-0.101
ares-0.098
ula-0.093
ented-0.092
Token upon
Token ID2402
Feature activation+4.68e+00

Pos logit contributions
 visit+0.025
 appreciate+0.024
 who+0.022
 live+0.021
 coral+0.021
Neg logit contributions
aned-0.052
 fists-0.052
ares-0.049
ented-0.049
 firmly-0.047
Token a
Token ID257
Feature activation+2.97e+00

Pos logit contributions
 wedding+0.149
arium+0.146
 farm+0.146
 ranch+0.144
 habitats+0.141
Neg logit contributions
 fists-0.066
aned-0.059
 firmly-0.059
ula-0.058
ares-0.056
Token time
Token ID640
Feature activation-5.47e-01

Pos logit contributions
 coral+0.090
 appreciate+0.090
 live+0.087
 visit+0.083
 celebrate+0.082
Neg logit contributions
 fists-0.056
aned-0.052
 firmly-0.051
ares-0.049
ented-0.047
Token there
Token ID612
Feature activation+1.27e+00

Pos logit contributions
aned+0.016
 fists+0.016
ares+0.015
ented+0.015
 firmly+0.014
Neg logit contributions
 visit-0.012
 appreciate-0.012
 who-0.011
 live-0.011
 coral-0.011
Token was
Token ID373
Feature activation+1.41e+00

Pos logit contributions
 visit+0.029
 appreciate+0.028
 who+0.027
 live+0.026
 coral+0.025
Neg logit contributions
aned-0.037
 fists-0.037
ares-0.035
ented-0.034
 firmly-0.033
Token a
Token ID257
Feature activation+2.79e+00

Pos logit contributions
 appreciate+0.041
arium+0.040
 visit+0.039
 wedding+0.039
 tale+0.038
Neg logit contributions
 fists-0.025
ula-0.024
bled-0.022
omm-0.021
 firmly-0.021
Token be
Token ID307
Feature activation-9.88e-03

Pos logit contributions
arium+0.011
 coral+0.010
 farm+0.010
 visit+0.010
 appreciate+0.010
Neg logit contributions
aned-0.016
 fists-0.016
ares-0.015
 firmly-0.015
ented-0.014
Token friends
Token ID2460
Feature activation+2.21e+00

Pos logit contributions
 fists+0.000
aned+0.000
 firmly+0.000
ares+0.000
ented+0.000
Neg logit contributions
 visit-0.000
 appreciate-0.000
 coral-0.000
arium-0.000
 live-0.000
Token.
Token ID13
Feature activation+9.69e-01

Pos logit contributions
 visit+0.057
 appreciate+0.057
 farm+0.056
 coral+0.055
 galaxy+0.054
Neg logit contributions
 firmly-0.046
 off-0.041
 fists-0.041
ares-0.040
ier-0.040
Token<|endoftext|>
Token ID50256
Feature activation+4.31e+00

Pos logit contributions
 visit+0.020
 appreciate+0.019
 coral+0.018
 live+0.018
 farm+0.018
Neg logit contributions
 fists-0.029
aned-0.029
ares-0.028
ented-0.027
 firmly-0.027
TokenOnce
Token ID7454
Feature activation+1.73e+00

Pos logit contributions
 appreciate+0.092
 wedding+0.087
 visit+0.086
 farm+0.081
 coral+0.080
Neg logit contributions
aned-0.119
 fists-0.119
ares-0.116
 firmly-0.110
ula-0.109
Token upon
Token ID2402
Feature activation+5.15e+00

Pos logit contributions
 visit+0.030
 appreciate+0.029
 who+0.026
 live+0.026
 coral+0.025
Neg logit contributions
aned-0.059
 fists-0.059
ares-0.056
ented-0.055
 firmly-0.053
Token a
Token ID257
Feature activation+3.41e+00

Pos logit contributions
 wedding+0.170
arium+0.168
 farm+0.168
 ranch+0.165
 habitats+0.161
Neg logit contributions
 fists-0.064
 firmly-0.059
 off-0.058
aned-0.058
 harder-0.055
Token time
Token ID640
Feature activation-3.88e-01

Pos logit contributions
 coral+0.106
 appreciate+0.106
 live+0.102
 visit+0.098
 celebrate+0.097
Neg logit contributions
 fists-0.061
aned-0.056
 firmly-0.056
ares-0.052
omm-0.050
Token there
Token ID612
Feature activation+1.37e+00

Pos logit contributions
aned+0.011
 fists+0.011
ares+0.010
ented+0.010
 firmly+0.010
Neg logit contributions
 visit-0.009
 appreciate-0.009
 who-0.008
 live-0.008
 coral-0.008
Token was
Token ID373
Feature activation+1.50e+00

Pos logit contributions
 visit+0.033
 appreciate+0.032
 who+0.030
 live+0.030
 coral+0.029
Neg logit contributions
aned-0.038
 fists-0.038
ares-0.036
ented-0.035
 firmly-0.034
Token a
Token ID257
Feature activation+2.92e+00

Pos logit contributions
 appreciate+0.043
 visit+0.041
arium+0.041
 hunt+0.039
 wedding+0.039
Neg logit contributions
 fists-0.029
ula-0.027
bled-0.025
ares-0.025
omm-0.024
Token her
Token ID607
Feature activation-1.31e+00

Pos logit contributions
 visit+0.013
 appreciate+0.013
 who+0.012
 live+0.012
 coral+0.011
Neg logit contributions
aned-0.022
 fists-0.022
ares-0.021
ented-0.020
 firmly-0.019
Token work
Token ID670
Feature activation-1.18e+00

Pos logit contributions
 fists+0.036
aned+0.036
ares+0.034
ented+0.033
 firmly+0.032
Neg logit contributions
 visit-0.031
 appreciate-0.031
 who-0.028
 live-0.028
 coral-0.028
Token.
Token ID13
Feature activation+1.92e-01

Pos logit contributions
aned+0.040
 fists+0.039
ares+0.038
ented+0.037
 firmly+0.035
Neg logit contributions
 visit-0.022
 appreciate-0.021
 who-0.019
 live-0.018
 wedding-0.018
Token<|endoftext|>
Token ID50256
Feature activation+4.05e+00

Pos logit contributions
 visit+0.003
 appreciate+0.003
 coral+0.003
 wedding+0.003
 live+0.003
Neg logit contributions
 fists-0.006
aned-0.006
ares-0.006
ented-0.006
omm-0.006
TokenOnce
Token ID7454
Feature activation+1.59e+00

Pos logit contributions
 appreciate+0.085
 wedding+0.081
 visit+0.078
 coral+0.076
 farm+0.075
Neg logit contributions
aned-0.112
 fists-0.112
ares-0.110
ula-0.105
umbled-0.104
Token upon
Token ID2402
Feature activation+4.78e+00

Pos logit contributions
 visit+0.027
 appreciate+0.026
 who+0.024
 live+0.024
 coral+0.023
Neg logit contributions
aned-0.055
 fists-0.054
ares-0.052
ented-0.051
 firmly-0.049
Token a
Token ID257
Feature activation+2.58e+00

Pos logit contributions
 farm+0.155
 wedding+0.155
arium+0.153
 ranch+0.152
 habitats+0.150
Neg logit contributions
 fists-0.059
 worse-0.055
aned-0.054
 shocked-0.054
 off-0.052
Token time
Token ID640
Feature activation-3.83e-01

Pos logit contributions
 coral+0.082
 appreciate+0.080
 live+0.077
 visit+0.074
 celebrate+0.073
Neg logit contributions
 fists-0.045
aned-0.042
 firmly-0.041
ares-0.040
 problem-0.038
Token,
Token ID11
Feature activation+1.70e+00

Pos logit contributions
aned+0.010
 fists+0.010
ares+0.010
ented+0.009
 firmly+0.009
Neg logit contributions
 visit-0.009
 appreciate-0.009
 who-0.008
 live-0.008
 coral-0.008
Token there
Token ID612
Feature activation+1.20e+00

Pos logit contributions
 wedding+0.044
 visit+0.043
 appreciate+0.043
 farm+0.042
 coral+0.041
Neg logit contributions
 fists-0.041
 firmly-0.040
ares-0.040
aned-0.039
bled-0.038
Token was
Token ID373
Feature activation+1.65e+00

Pos logit contributions
 visit+0.030
 appreciate+0.030
 wedding+0.028
 who+0.028
 coral+0.028
Neg logit contributions
 fists-0.030
aned-0.030
ares-0.028
ented-0.027
 firmly-0.027
Token a
Token ID257
Feature activation-2.93e+00

Pos logit contributions
aned+0.065
 fists+0.062
ares+0.061
ented+0.058
omm+0.058
Neg logit contributions
 visit-0.040
 appreciate-0.039
 who-0.037
 live-0.035
 celebrate-0.034
Token hug
Token ID16225
Feature activation-6.23e-01

Pos logit contributions
aned+0.101
 fists+0.092
ares+0.092
bled+0.087
ented+0.084
Neg logit contributions
 visit-0.066
 appreciate-0.059
 who-0.055
 wedding-0.053
 farm-0.053
Token!
Token ID0
Feature activation-1.13e-01

Pos logit contributions
aned+0.022
 fists+0.022
ares+0.021
ented+0.020
uffed+0.020
Neg logit contributions
 visit-0.011
 appreciate-0.010
 who-0.010
 live-0.009
 wedding-0.009
Token<|endoftext|>
Token ID50256
Feature activation+4.30e+00

Pos logit contributions
 fists+0.004
aned+0.004
ares+0.003
omm+0.003
ented+0.003
Neg logit contributions
 visit-0.002
 appreciate-0.002
 wedding-0.002
 farm-0.002
 coral-0.002
TokenOnce
Token ID7454
Feature activation+1.28e+00

Pos logit contributions
 appreciate+0.089
 wedding+0.085
 visit+0.078
 coral+0.078
 farm+0.078
Neg logit contributions
aned-0.120
 fists-0.120
ares-0.116
ula-0.114
umbled-0.111
Token upon
Token ID2402
Feature activation+4.70e+00

Pos logit contributions
 visit+0.022
 appreciate+0.022
 who+0.020
 live+0.019
 coral+0.019
Neg logit contributions
aned-0.043
 fists-0.043
ares-0.041
ented-0.040
 firmly-0.039
Token a
Token ID257
Feature activation+2.84e+00

Pos logit contributions
 wedding+0.157
 farm+0.154
 habitats+0.154
 ranch+0.153
arium+0.151
Neg logit contributions
 fists-0.053
 off-0.052
 worse-0.051
 firmly-0.049
aned-0.049
Token time
Token ID640
Feature activation-2.82e-01

Pos logit contributions
 coral+0.094
 appreciate+0.090
 live+0.087
 cultures+0.084
 celebrate+0.084
Neg logit contributions
 fists-0.045
aned-0.043
 firmly-0.042
ares-0.041
 problem-0.038
Token,
Token ID11
Feature activation+1.53e+00

Pos logit contributions
aned+0.008
 fists+0.008
ares+0.007
ented+0.007
 firmly+0.007
Neg logit contributions
 visit-0.007
 appreciate-0.006
 who-0.006
 live-0.006
 coral-0.006
Token there
Token ID612
Feature activation+1.07e+00

Pos logit contributions
 wedding+0.039
 appreciate+0.039
 visit+0.039
 farm+0.038
 coral+0.037
Neg logit contributions
 fists-0.037
 firmly-0.036
ares-0.035
aned-0.034
bled-0.033
Token lived
Token ID5615
Feature activation+1.75e+00

Pos logit contributions
 visit+0.026
 appreciate+0.025
 who+0.024
 live+0.023
 coral+0.023
Neg logit contributions
aned-0.029
 fists-0.029
ares-0.027
ented-0.026
 firmly-0.026
Token yes
Token ID3763
Feature activation+4.73e-01

Pos logit contributions
aned+0.045
 fists+0.044
ares+0.042
ented+0.041
omm+0.038
Neg logit contributions
 visit-0.030
 appreciate-0.028
 who-0.028
 live-0.026
 wedding-0.026
Token,
Token ID11
Feature activation+2.12e+00

Pos logit contributions
 visit+0.009
 who+0.008
 appreciate+0.008
 farm+0.007
 wedding+0.007
Neg logit contributions
 fists-0.017
aned-0.016
ares-0.016
ented-0.015
bled-0.015
Token but
Token ID475
Feature activation-1.07e+00

Pos logit contributions
 visit+0.042
 appreciate+0.041
 live+0.037
 coral+0.037
 farm+0.037
Neg logit contributions
 fists-0.066
aned-0.066
ares-0.063
ented-0.062
 firmly-0.061
Token they
Token ID484
Feature activation+1.85e-02

Pos logit contributions
aned+0.036
 fists+0.035
ares+0.033
ented+0.033
bled+0.031
Neg logit contributions
 visit-0.022
 appreciate-0.021
 who-0.020
 live-0.019
 wedding-0.019
Token had
Token ID550
Feature activation+4.09e-01

Pos logit contributions
 visit+0.000
 appreciate+0.000
 who+0.000
 live+0.000
 celebrate+0.000
Neg logit contributions
 fists-0.001
aned-0.001
ares-0.001
ula-0.001
ented-0.001
Token to
Token ID284
Feature activation+1.00e+00

Pos logit contributions
 visit+0.008
 appreciate+0.008
 who+0.007
 live+0.007
 coral+0.007
Neg logit contributions
 fists-0.013
aned-0.013
ares-0.012
ented-0.012
 firmly-0.012
Token be
Token ID307
Feature activation-7.99e-01

Pos logit contributions
 visit+0.022
 appreciate+0.022
 coral+0.021
 who+0.020
 farm+0.020
Neg logit contributions
 fists-0.029
aned-0.028
ares-0.027
ented-0.026
 firmly-0.026
Token careful
Token ID8161
Feature activation+4.54e-01

Pos logit contributions
aned+0.025
ares+0.025
 fists+0.025
omm+0.022
ented+0.022
Neg logit contributions
 visit-0.017
 appreciate-0.016
 who-0.016
 live-0.015
 farm-0.014
Token and
Token ID290
Feature activation-2.21e+00

Pos logit contributions
 visit+0.008
 appreciate+0.008
 who+0.008
 live+0.007
 farm+0.007
Neg logit contributions
 fists-0.015
aned-0.015
ares-0.015
ented-0.014
omm-0.014
Token come
Token ID1282
Feature activation-2.78e+00

Pos logit contributions
aned+0.066
 fists+0.065
ares+0.063
ented+0.060
omm+0.059
Neg logit contributions
 visit-0.050
 appreciate-0.049
 who-0.046
 live-0.045
 farm-0.043
Token back
Token ID736
Feature activation-1.16e-04

Pos logit contributions
aned+0.084
 fists+0.081
ares+0.078
omm+0.073
ented+0.071
Neg logit contributions
 visit-0.071
 who-0.064
 appreciate-0.063
 live-0.062
 outdoors-0.057
Token together
Token ID1978
Feature activation+1.48e+00

Pos logit contributions
 visit+0.012
 appreciate+0.012
 who+0.011
 live+0.011
 coral+0.011
Neg logit contributions
aned-0.015
 fists-0.015
ares-0.014
ented-0.014
 firmly-0.013
Token.
Token ID13
Feature activation+2.30e+00

Pos logit contributions
 visit+0.030
 appreciate+0.030
 coral+0.028
 wedding+0.028
 farm+0.027
Neg logit contributions
 fists-0.044
aned-0.043
ares-0.041
ented-0.040
 firmly-0.040
Token Just
Token ID2329
Feature activation+1.47e+00

Pos logit contributions
 appreciate+0.045
 coral+0.045
 wedding+0.044
 visit+0.044
 farm+0.042
Neg logit contributions
 fists-0.064
ares-0.064
aned-0.063
omm-0.063
 firmly-0.060
Token like
Token ID588
Feature activation+1.96e+00

Pos logit contributions
 visit+0.031
 coral+0.031
 farm+0.031
 appreciate+0.030
arium+0.030
Neg logit contributions
 fists-0.041
aned-0.039
 firmly-0.038
ares-0.037
ented-0.036
Token you
Token ID345
Feature activation+1.54e+00

Pos logit contributions
 visit+0.042
 appreciate+0.041
 wedding+0.038
 farm+0.038
 coral+0.038
Neg logit contributions
 fists-0.057
aned-0.054
ares-0.052
 firmly-0.051
ented-0.050
Token and
Token ID290
Feature activation+8.17e-01

Pos logit contributions
 visit+0.034
 farm+0.033
 appreciate+0.033
 coral+0.032
 wedding+0.032
Neg logit contributions
 fists-0.042
aned-0.042
ares-0.040
ented-0.039
 firmly-0.038
Token me
Token ID502
Feature activation+1.62e+00

Pos logit contributions
 visit+0.018
 appreciate+0.018
 farm+0.017
 coral+0.017
 wedding+0.017
Neg logit contributions
 fists-0.022
aned-0.021
ares-0.020
 firmly-0.020
ented-0.020
Token."
Token ID526
Feature activation+2.22e+00

Pos logit contributions
 visit+0.033
 appreciate+0.031
 coral+0.031
 farm+0.031
 wedding+0.030
Neg logit contributions
aned-0.048
 fists-0.048
ares-0.046
ented-0.044
 firmly-0.044
Token Sara
Token ID24799
Feature activation+2.05e+00

Pos logit contributions
 appreciate+0.046
 coral+0.045
 visit+0.044
 farm+0.043
 wedding+0.042
Neg logit contributions
 fists-0.061
aned-0.060
 firmly-0.059
ares-0.058
omm-0.057
Token hugged
Token ID41130
Feature activation+3.50e-01

Pos logit contributions
 visit+0.052
 coral+0.051
 appreciate+0.051
 farm+0.049
 wedding+0.049
Neg logit contributions
aned-0.051
 fists-0.048
 firmly-0.046
ares-0.045
ented-0.044
Token her
Token ID607
Feature activation-3.00e-01

Pos logit contributions
 visit+0.008
 appreciate+0.008
 live+0.007
 coral+0.007
 who+0.007
Neg logit contributions
aned-0.010
 fists-0.010
ares-0.009
ented-0.009
 firmly-0.009
Token he
Token ID339
Feature activation+1.29e-01

Pos logit contributions
aned+0.003
 fists+0.003
ares+0.003
ented+0.003
 firmly+0.003
Neg logit contributions
 visit-0.003
 appreciate-0.003
 who-0.002
 live-0.002
 coral-0.002
Token made
Token ID925
Feature activation+2.82e-01

Pos logit contributions
 visit+0.003
 appreciate+0.003
 who+0.003
 live+0.003
 farm+0.003
Neg logit contributions
aned-0.004
 fists-0.004
ares-0.003
ented-0.003
 firmly-0.003
Token a
Token ID257
Feature activation-1.68e+00

Pos logit contributions
 visit+0.007
 appreciate+0.007
 who+0.006
 live+0.006
 farm+0.006
Neg logit contributions
 fists-0.008
aned-0.008
ares-0.007
ented-0.007
 firmly-0.007
Token new
Token ID649
Feature activation-1.19e+00

Pos logit contributions
 fists+0.047
aned+0.046
ares+0.044
ented+0.043
 firmly+0.043
Neg logit contributions
 visit-0.038
 appreciate-0.037
 who-0.034
 live-0.034
 coral-0.034
Token friend
Token ID1545
Feature activation+1.73e+00

Pos logit contributions
 fists+0.033
aned+0.031
ares+0.029
 firmly+0.029
ented+0.029
Neg logit contributions
 appreciate-0.027
 visit-0.026
 live-0.025
 coral-0.025
 who-0.024
Token in
Token ID287
Feature activation+2.73e+00

Pos logit contributions
 appreciate+0.041
 visit+0.041
 farm+0.039
 coral+0.038
 live+0.037
Neg logit contributions
 fists-0.043
ares-0.040
 firmly-0.040
aned-0.040
 off-0.038
Token the
Token ID262
Feature activation+1.94e+00

Pos logit contributions
 visit+0.056
 appreciate+0.055
 who+0.050
 live+0.050
 coral+0.049
Neg logit contributions
 fists-0.084
aned-0.083
ares-0.079
ented-0.077
 firmly-0.076
Token jungle
Token ID20712
Feature activation+3.66e+00

Pos logit contributions
 appreciate+0.033
 visit+0.032
 live+0.029
 who+0.029
 coral+0.028
Neg logit contributions
 fists-0.066
aned-0.063
ented-0.061
 firmly-0.060
ares-0.059
Token.
Token ID13
Feature activation+3.18e-01

Pos logit contributions
 appreciate+0.082
 visit+0.080
 coral+0.074
 wedding+0.072
 live+0.071
Neg logit contributions
 fists-0.100
aned-0.097
 firmly-0.093
ares-0.091
ented-0.089
Token<|endoftext|>
Token ID50256
Feature activation+4.11e+00

Pos logit contributions
 visit+0.006
 appreciate+0.006
 wedding+0.006
 live+0.006
 coral+0.006
Neg logit contributions
 fists-0.010
aned-0.009
ares-0.009
ented-0.009
 firmly-0.009
TokenOnce
Token ID7454
Feature activation+1.58e+00

Pos logit contributions
 appreciate+0.088
 wedding+0.083
 visit+0.081
 farm+0.076
 coral+0.076
Neg logit contributions
 fists-0.115
aned-0.115
ares-0.111
 firmly-0.106
ula-0.106
Token,
Token ID11
Feature activation-1.09e+00

Pos logit contributions
aned+0.078
 fists+0.076
ares+0.074
ented+0.071
ula+0.068
Neg logit contributions
 visit-0.055
 appreciate-0.052
 who-0.050
 live-0.050
 coral-0.048
Token they
Token ID484
Feature activation-3.67e-01

Pos logit contributions
 fists+0.034
aned+0.034
ares+0.032
ented+0.031
 firmly+0.031
Neg logit contributions
 visit-0.022
 appreciate-0.022
 who-0.020
 live-0.020
 coral-0.019
Token heard
Token ID2982
Feature activation+1.19e+00

Pos logit contributions
aned+0.013
 fists+0.012
ares+0.012
ented+0.012
omm+0.012
Neg logit contributions
 visit-0.007
 appreciate-0.006
 who-0.006
 coral-0.006
 live-0.006
Token some
Token ID617
Feature activation+2.87e-02

Pos logit contributions
 appreciate+0.025
 visit+0.025
 live+0.022
 farm+0.022
 wedding+0.022
Neg logit contributions
 fists-0.035
aned-0.035
ares-0.033
ented-0.032
 firmly-0.032
Token noises
Token ID26782
Feature activation+5.88e-01

Pos logit contributions
 visit+0.001
 appreciate+0.001
 who+0.001
 live+0.001
 farm+0.001
Neg logit contributions
aned-0.001
 fists-0.001
ares-0.001
ented-0.001
 firmly-0.001
Token behind
Token ID2157
Feature activation+2.79e+00

Pos logit contributions
 appreciate+0.014
 visit+0.014
 coral+0.013
 farm+0.013
 wedding+0.013
Neg logit contributions
aned-0.016
 fists-0.016
ares-0.015
ented-0.014
 firmly-0.014
Token them
Token ID606
Feature activation+1.23e+00

Pos logit contributions
 appreciate+0.072
 visit+0.069
 wedding+0.065
 farm+0.064
 coral+0.064
Neg logit contributions
 fists-0.070
aned-0.067
ares-0.062
 firmly-0.061
ented-0.058
Token.
Token ID13
Feature activation-4.69e-01

Pos logit contributions
 visit+0.025
 appreciate+0.025
 wedding+0.022
 coral+0.022
 farm+0.022
Neg logit contributions
 fists-0.038
aned-0.037
ares-0.036
ented-0.035
 firmly-0.034
Token They
Token ID1119
Feature activation+6.43e-01

Pos logit contributions
 fists+0.015
aned+0.015
ares+0.014
ented+0.014
 firmly+0.014
Neg logit contributions
 visit-0.009
 appreciate-0.009
 wedding-0.008
 live-0.008
 who-0.008
Token turned
Token ID2900
Feature activation-2.23e+00

Pos logit contributions
 visit+0.014
 appreciate+0.014
 who+0.013
 live+0.013
 coral+0.013
Neg logit contributions
aned-0.019
 fists-0.019
ares-0.018
ented-0.017
omm-0.017
Token around
Token ID1088
Feature activation+1.91e+00

Pos logit contributions
aned+0.074
 fists+0.071
omm+0.069
ares+0.068
ented+0.067
Neg logit contributions
 visit-0.043
 who-0.041
 coral-0.039
 appreciate-0.038
 live-0.037
Token?"
Token ID1701
Feature activation+8.69e-01

Pos logit contributions
aned+0.035
 fists+0.035
ares+0.033
ented+0.032
 firmly+0.031
Neg logit contributions
 visit-0.024
 appreciate-0.023
 who-0.022
 live-0.021
 wedding-0.021
Token They
Token ID1119
Feature activation+1.50e+00

Pos logit contributions
 appreciate+0.018
 coral+0.018
 visit+0.018
 farm+0.017
 live+0.017
Neg logit contributions
aned-0.025
 fists-0.024
 firmly-0.024
ares-0.024
omm-0.023
Token watched
Token ID7342
Feature activation-8.30e-02

Pos logit contributions
 visit+0.036
 appreciate+0.035
 who+0.033
 live+0.033
 coral+0.032
Neg logit contributions
aned-0.041
 fists-0.041
ares-0.039
ented-0.037
 firmly-0.036
Token the
Token ID262
Feature activation-1.49e-01

Pos logit contributions
 fists+0.002
aned+0.002
ares+0.002
ented+0.002
 firmly+0.002
Neg logit contributions
 visit-0.002
 appreciate-0.002
 who-0.002
 live-0.002
 coral-0.002
Token bird
Token ID6512
Feature activation+6.21e-01

Pos logit contributions
 fists+0.004
aned+0.004
ares+0.004
ented+0.004
 firmly+0.004
Neg logit contributions
 visit-0.003
 appreciate-0.003
 who-0.003
 live-0.003
 coral-0.003
Token for
Token ID329
Feature activation+2.19e+00

Pos logit contributions
 appreciate+0.012
 visit+0.011
 coral+0.011
 Sleep+0.011
arium+0.011
Neg logit contributions
 fists-0.018
ares-0.018
aned-0.018
 firmly-0.017
ented-0.017
Token a
Token ID257
Feature activation+2.80e-01

Pos logit contributions
 appreciate+0.051
 visit+0.051
 farm+0.049
arium+0.049
 coral+0.047
Neg logit contributions
 fists-0.057
aned-0.052
 firmly-0.051
ula-0.048
ented-0.047
Token little
Token ID1310
Feature activation-9.42e-01

Pos logit contributions
 appreciate+0.007
 live+0.006
 visit+0.006
Always+0.006
 habitats+0.006
Neg logit contributions
 fists-0.007
 firmly-0.007
ula-0.007
aned-0.007
ares-0.006
Token while
Token ID981
Feature activation+9.76e-01

Pos logit contributions
 fists+0.023
 firmly+0.021
ares+0.021
aned+0.021
ented+0.021
Neg logit contributions
 appreciate-0.024
 visit-0.023
 coral-0.023
 live-0.022
 farm-0.022
Token before
Token ID878
Feature activation+3.47e-01

Pos logit contributions
 visit+0.021
 appreciate+0.020
 who+0.018
 live+0.018
 coral+0.018
Neg logit contributions
aned-0.030
 fists-0.030
ares-0.028
ented-0.027
 firmly-0.027
Token continuing
Token ID8282
Feature activation+6.19e-01

Pos logit contributions
 visit+0.009
 appreciate+0.008
 who+0.008
 live+0.008
 coral+0.008
Neg logit contributions
 fists-0.009
aned-0.009
ares-0.009
ented-0.008
 firmly-0.008
Token never
Token ID1239
Feature activation+3.19e-01

Pos logit contributions
 visit+0.001
 appreciate+0.001
 who+0.001
 live+0.001
 farm+0.001
Neg logit contributions
 fists-0.002
aned-0.002
ares-0.002
ented-0.002
 firmly-0.002
Token put
Token ID1234
Feature activation-1.55e+00

Pos logit contributions
 visit+0.007
 appreciate+0.007
 who+0.007
 coral+0.006
 farm+0.006
Neg logit contributions
aned-0.009
 fists-0.009
ares-0.009
ented-0.008
 firmly-0.008
Token them
Token ID606
Feature activation-1.94e+00

Pos logit contributions
aned+0.053
ares+0.049
 fists+0.049
ented+0.047
omm+0.046
Neg logit contributions
 who-0.029
 visit-0.029
 live-0.026
 outdoors-0.026
 appreciate-0.026
Token away
Token ID1497
Feature activation-4.75e-01

Pos logit contributions
aned+0.051
 fists+0.051
ares+0.047
omm+0.047
ented+0.045
Neg logit contributions
 visit-0.049
 who-0.047
 appreciate-0.046
 live-0.045
 outdoors-0.043
Token.
Token ID13
Feature activation+5.60e-01

Pos logit contributions
aned+0.015
 fists+0.015
ares+0.014
ented+0.014
 firmly+0.014
Neg logit contributions
 visit-0.009
 appreciate-0.009
 who-0.008
 live-0.008
 coral-0.008
Token Her
Token ID2332
Feature activation-1.97e+00

Pos logit contributions
 appreciate+0.012
 coral+0.011
 visit+0.011
 live+0.010
 wedding+0.010
Neg logit contributions
 fists-0.016
ares-0.016
aned-0.016
omm-0.016
ented-0.015
Token mom
Token ID1995
Feature activation+2.78e-01

Pos logit contributions
aned+0.051
 fists+0.050
ares+0.049
ented+0.046
 firmly+0.044
Neg logit contributions
 visit-0.053
 appreciate-0.049
 farm-0.048
 wedding-0.047
 who-0.047
Token always
Token ID1464
Feature activation-1.35e-02

Pos logit contributions
 coral+0.006
 visit+0.006
 appreciate+0.006
 live+0.005
 farm+0.005
Neg logit contributions
aned-0.008
 fists-0.008
ares-0.008
 firmly-0.007
ented-0.007
Token told
Token ID1297
Feature activation-1.19e-01

Pos logit contributions
 fists+0.000
aned+0.000
ares+0.000
ented+0.000
 firmly+0.000
Neg logit contributions
 visit-0.000
 appreciate-0.000
 who-0.000
 live-0.000
 wedding-0.000
Token her
Token ID607
Feature activation-1.43e-01

Pos logit contributions
aned+0.004
 fists+0.004
ares+0.004
ented+0.004
 firmly+0.004
Neg logit contributions
 visit-0.002
 appreciate-0.002
 who-0.002
 wedding-0.002
 live-0.002
Token to
Token ID284
Feature activation+6.73e-01

Pos logit contributions
 fists+0.004
aned+0.004
ares+0.004
ented+0.004
 firmly+0.004
Neg logit contributions
 visit-0.003
 appreciate-0.003
 who-0.003
 live-0.003
 coral-0.003
Token,
Token ID11
Feature activation+1.62e+00

Pos logit contributions
aned+0.024
 fists+0.024
ares+0.023
ented+0.022
omm+0.020
Neg logit contributions
 visit-0.016
 who-0.015
 appreciate-0.015
 live-0.014
 wedding-0.014
Token "
Token ID366
Feature activation+1.70e+00

Pos logit contributions
 visit+0.042
 appreciate+0.042
 who+0.039
 live+0.039
 coral+0.038
Neg logit contributions
aned-0.041
 fists-0.040
ares-0.038
ented-0.037
 firmly-0.036
TokenDon
Token ID3987
Feature activation-3.12e+00

Pos logit contributions
 wedding+0.041
 visit+0.041
 live+0.040
 coral+0.040
 farm+0.040
Neg logit contributions
aned-0.042
ula-0.039
ented-0.039
ares-0.038
 fists-0.038
Token't
Token ID470
Feature activation-1.14e+00

Pos logit contributions
 fists+0.079
aned+0.072
ares+0.068
ented+0.067
 firmly+0.063
Neg logit contributions
 visit-0.092
 appreciate-0.082
 who-0.081
 live-0.080
 celebrate-0.077
Token worry
Token ID5490
Feature activation-2.47e+00

Pos logit contributions
aned+0.030
 fists+0.030
ares+0.028
ented+0.027
 firmly+0.026
Neg logit contributions
 visit-0.029
 appreciate-0.029
 who-0.027
 live-0.026
 coral-0.026
Token,
Token ID11
Feature activation-7.78e-01

Pos logit contributions
aned+0.078
 fists+0.076
ares+0.074
ented+0.070
bled+0.068
Neg logit contributions
 visit-0.051
 who-0.047
 appreciate-0.047
 live-0.044
 farm-0.044
Token Lily
Token ID20037
Feature activation-4.64e-01

Pos logit contributions
 fists+0.022
aned+0.021
ares+0.020
ented+0.020
 firmly+0.020
Neg logit contributions
 visit-0.018
 appreciate-0.018
 coral-0.016
 live-0.016
 wedding-0.016
Token.
Token ID13
Feature activation-1.22e+00

Pos logit contributions
aned+0.014
 fists+0.014
ares+0.014
ented+0.013
 firmly+0.013
Neg logit contributions
 visit-0.010
 appreciate-0.009
 who-0.009
 live-0.008
 coral-0.008
Token You
Token ID921
Feature activation-4.52e-03

Pos logit contributions
 fists+0.032
aned+0.031
ares+0.030
ented+0.030
omm+0.029
Neg logit contributions
 visit-0.030
 appreciate-0.030
 wedding-0.029
 coral-0.029
 farm-0.028
Token can
Token ID460
Feature activation-1.32e+00

Pos logit contributions
 fists+0.000
aned+0.000
ares+0.000
ented+0.000
 firmly+0.000
Neg logit contributions
 visit-0.000
 appreciate-0.000
 coral-0.000
 farm-0.000
 wedding-0.000
Token do
Token ID466
Feature activation-8.06e-01

Pos logit contributions
aned+0.039
 fists+0.038
ares+0.037
ented+0.036
 firmly+0.035
Neg logit contributions
 coral-0.027
 visit-0.026
 appreciate-0.026
arium-0.026
 wedding-0.025
Token sang
Token ID25889
Feature activation-2.22e-01

Pos logit contributions
aned+0.029
 fists+0.028
 firmly+0.026
ares+0.026
ented+0.026
Neg logit contributions
 visit-0.035
 appreciate-0.035
 farm-0.033
 outdoors-0.033
 wedding-0.033
Token a
Token ID257
Feature activation-4.31e-01

Pos logit contributions
 off+0.005
aned+0.005
 firmly+0.005
 fists+0.005
ares+0.005
Neg logit contributions
 farm-0.006
 visit-0.005
 appreciate-0.005
 wedding-0.005
arium-0.005
Token song
Token ID3496
Feature activation+1.66e+00

Pos logit contributions
 fists+0.011
aned+0.010
ares+0.010
ula+0.010
 firmly+0.010
Neg logit contributions
 visit-0.009
arium-0.009
 farm-0.009
 appreciate-0.009
 habitats-0.009
Token for
Token ID329
Feature activation+2.09e-01

Pos logit contributions
 appreciate+0.043
 visit+0.042
 farm+0.041
 coral+0.040
 live+0.039
Neg logit contributions
ares-0.039
aned-0.038
 fists-0.037
 firmly-0.036
ula-0.036
Token Lily
Token ID20037
Feature activation+1.60e+00

Pos logit contributions
 visit+0.005
 appreciate+0.005
 who+0.004
 farm+0.004
 coral+0.004
Neg logit contributions
 fists-0.006
aned-0.006
ares-0.006
ented-0.005
 firmly-0.005
Token.
Token ID13
Feature activation-3.03e-01

Pos logit contributions
 appreciate+0.040
 visit+0.039
 coral+0.039
 farm+0.037
 reef+0.036
Neg logit contributions
 fists-0.039
aned-0.038
ares-0.037
 firmly-0.036
ented-0.035
Token Lily
Token ID20037
Feature activation+5.98e-01

Pos logit contributions
aned+0.008
 fists+0.008
ares+0.008
ented+0.008
 firmly+0.007
Neg logit contributions
 appreciate-0.007
 visit-0.007
 coral-0.007
 wedding-0.007
 live-0.006
Token wanted
Token ID2227
Feature activation-7.69e-01

Pos logit contributions
 appreciate+0.014
 visit+0.014
 coral+0.014
 outdoors+0.014
 live+0.013
Neg logit contributions
aned-0.015
 fists-0.014
ares-0.013
 firmly-0.013
ented-0.013
Token to
Token ID284
Feature activation-4.22e-02

Pos logit contributions
 fists+0.020
aned+0.020
ares+0.019
 firmly+0.018
ented+0.018
Neg logit contributions
 appreciate-0.018
 visit-0.017
 live-0.016
 farm-0.016
 coral-0.016
Token record
Token ID1700
Feature activation-9.71e-01

Pos logit contributions
 off+0.001
aned+0.001
 fists+0.001
ares+0.001
 firmly+0.001
Neg logit contributions
arium-0.001
 coral-0.001
 farm-0.001
 living-0.001
 who-0.001
Token the
Token ID262
Feature activation-1.76e+00

Pos logit contributions
 fists+0.027
aned+0.027
ares+0.026
ented+0.025
 firmly+0.024
Neg logit contributions
 visit-0.023
 appreciate-0.022
 farm-0.020
 who-0.020
 live-0.020
Token the
Token ID262
Feature activation+2.53e+00

Pos logit contributions
 tale+0.083
 appreciate+0.081
Hop+0.079
adows+0.079
 coral+0.079
Neg logit contributions
 fists-0.065
 off-0.058
ares-0.055
ula-0.054
aned-0.053
Token park
Token ID3952
Feature activation+2.08e+00

Pos logit contributions
 appreciate+0.043
 visit+0.038
 live+0.036
 who+0.034
arium+0.034
Neg logit contributions
 fists-0.081
ented-0.078
aned-0.076
ula-0.076
omm-0.076
Token to
Token ID284
Feature activation+3.26e+00

Pos logit contributions
 appreciate+0.052
 coral+0.050
Buzz+0.048
 galaxy+0.047
Hop+0.046
Neg logit contributions
 firmly-0.046
aned-0.045
 fists-0.045
 off-0.041
ares-0.041
Token find
Token ID1064
Feature activation-5.74e-01

Pos logit contributions
 tale+0.043
 coral+0.043
arium+0.042
 appreciate+0.040
 who+0.040
Neg logit contributions
 fists-0.101
ares-0.099
 off-0.098
aned-0.097
 unst-0.094
Token someone
Token ID2130
Feature activation+1.53e-01

Pos logit contributions
 fists+0.015
ented+0.014
ares+0.014
aned+0.014
 firmly+0.014
Neg logit contributions
 visit-0.013
 appreciate-0.013
 wedding-0.012
 farm-0.012
|-0.012
Token and
Token ID290
Feature activation+6.40e-01

Pos logit contributions
 appreciate+0.003
 coral+0.003
 visit+0.003
 farm+0.003
 wedding+0.003
Neg logit contributions
 fists-0.004
 firmly-0.004
ares-0.004
ented-0.004
aned-0.004
Token saw
Token ID2497
Feature activation+5.75e-01

Pos logit contributions
 appreciate+0.011
 coral+0.011
 visit+0.010
 wedding+0.010
 farm+0.010
Neg logit contributions
 fists-0.020
aned-0.019
 firmly-0.018
ented-0.018
ares-0.018
Token a
Token ID257
Feature activation+8.73e-01

Pos logit contributions
 visit+0.012
 appreciate+0.011
 wedding+0.010
 live+0.010
 farm+0.010
Neg logit contributions
 fists-0.018
aned-0.018
ares-0.017
ented-0.017
 firmly-0.016
Token bench
Token ID7624
Feature activation+4.95e-01

Pos logit contributions
 visit+0.019
 appreciate+0.018
 who+0.017
 live+0.016
 coral+0.016
Neg logit contributions
aned-0.027
 fists-0.026
ares-0.025
ented-0.024
 firmly-0.024
Token.
Token ID13
Feature activation-5.93e-01

Pos logit contributions
 visit+0.010
 appreciate+0.010
 coral+0.009
 wedding+0.009
 live+0.009
Neg logit contributions
aned-0.015
 fists-0.015
ares-0.014
ented-0.014
 firmly-0.014
Token She
Token ID1375
Feature activation+8.82e-01

Pos logit contributions
 fists+0.015
aned+0.014
ares+0.014
ented+0.014
 firmly+0.014
Neg logit contributions
 appreciate-0.014
 coral-0.014
 wedding-0.014
 island-0.013
 reef-0.013
TokenShe
Token ID3347
Feature activation+6.26e-02

Pos logit contributions
aned+0.001
 fists+0.001
 firmly+0.001
ula+0.001
ented+0.001
Neg logit contributions
 wedding-0.001
 visit-0.001
 appreciate-0.001
 coral-0.001
 farm-0.001
Token woke
Token ID19092
Feature activation-2.51e+00

Pos logit contributions
 visit+0.001
 who+0.001
 appreciate+0.001
 live+0.001
 wedding+0.001
Neg logit contributions
 fists-0.002
aned-0.002
ares-0.002
ented-0.002
omm-0.002
Token up
Token ID510
Feature activation+2.23e-01

Pos logit contributions
 fists+0.054
aned+0.054
ares+0.050
ented+0.048
 firmly+0.045
Neg logit contributions
 visit-0.075
 appreciate-0.071
 who-0.071
 farm-0.069
 wedding-0.068
Token Tom
Token ID4186
Feature activation-2.71e-01

Pos logit contributions
 visit+0.004
 appreciate+0.004
 who+0.004
 live+0.004
 coral+0.004
Neg logit contributions
aned-0.007
 fists-0.007
ares-0.007
ented-0.007
 firmly-0.007
Token.
Token ID13
Feature activation-4.24e-01

Pos logit contributions
aned+0.008
 fists+0.008
ares+0.008
ented+0.008
 firmly+0.008
Neg logit contributions
 visit-0.005
 appreciate-0.005
 live-0.005
 coral-0.005
 who-0.005
Token She
Token ID1375
Feature activation+9.17e-02

Pos logit contributions
 fists+0.013
aned+0.012
ares+0.012
ented+0.011
 firmly+0.011
Neg logit contributions
 visit-0.009
 appreciate-0.009
 wedding-0.008
 coral-0.008
 who-0.008
Token showed
Token ID3751
Feature activation-1.41e+00

Pos logit contributions
 visit+0.002
 appreciate+0.002
 who+0.002
 live+0.002
 coral+0.002
Neg logit contributions
aned-0.003
 fists-0.003
ares-0.003
ented-0.002
 firmly-0.002
Token him
Token ID683
Feature activation-9.06e-01

Pos logit contributions
aned+0.046
 fists+0.045
ares+0.043
ented+0.042
 firmly+0.041
Neg logit contributions
 visit-0.028
 appreciate-0.026
 who-0.025
 live-0.024
 wedding-0.023
Token Bob
Token ID5811
Feature activation-1.91e-01

Pos logit contributions
 fists+0.026
aned+0.025
ares+0.024
 firmly+0.023
ented+0.023
Neg logit contributions
 visit-0.020
 appreciate-0.020
 farm-0.018
 wedding-0.018
 live-0.018
Tokeno
Token ID78
Feature activation-6.17e-02

Pos logit contributions
 fists+0.005
aned+0.005
 firmly+0.005
ares+0.005
ented+0.005
Neg logit contributions
 visit-0.004
 appreciate-0.004
 wedding-0.004
 farm-0.004
 coral-0.004
Token.
Token ID13
Feature activation-2.90e-01

Pos logit contributions
 fists+0.002
aned+0.002
ares+0.002
ented+0.002
 firmly+0.002
Neg logit contributions
 visit-0.001
 appreciate-0.001
 wedding-0.001
 farm-0.001
 live-0.001
Token?"
Token ID1701
Feature activation-5.87e-01

Pos logit contributions
 coral+0.001
 appreciate+0.001
 visit+0.001
 wedding+0.001
 bask+0.001
Neg logit contributions
ares-0.001
aned-0.001
 firmly-0.001
 fists-0.001
ented-0.001
Token
Token ID198
Feature activation+4.41e-01

Pos logit contributions
aned+0.014
 fists+0.013
ares+0.013
 firmly+0.013
omm+0.012
Neg logit contributions
 appreciate-0.016
 coral-0.015
 visit-0.015
 farm-0.014
 reef-0.014
Token
Token ID198
Feature activation-1.59e+00

Pos logit contributions
 appreciate+0.007
 coral+0.007
 visit+0.007
 wedding+0.007
 farm+0.006
Neg logit contributions
aned-0.015
 fists-0.014
ares-0.014
 firmly-0.014
ula-0.014
TokenL
Token ID43
Feature activation-1.72e+00

Pos logit contributions
aned+0.049
 fists+0.047
ares+0.046
 firmly+0.046
ented+0.045
Neg logit contributions
 visit-0.032
 appreciate-0.032
 coral-0.030
 wedding-0.029
 farm-0.029
Tokenily
Token ID813
Feature activation-7.93e-01

Pos logit contributions
 fists+0.047
aned+0.046
ares+0.043
ented+0.042
 firmly+0.042
Neg logit contributions
 visit-0.041
 appreciate-0.041
 who-0.038
 live-0.038
 wedding-0.037
Token got
Token ID1392
Feature activation-3.35e+00

Pos logit contributions
 fists+0.024
aned+0.023
ares+0.023
ented+0.022
ula+0.022
Neg logit contributions
 visit-0.017
 who-0.016
 appreciate-0.016
 farm-0.015
 wedding-0.015
Token up
Token ID510
Feature activation-8.90e-02

Pos logit contributions
aned+0.097
 fists+0.087
ier+0.084
ares+0.084
ula+0.082
Neg logit contributions
 visit-0.082
 who-0.079
 live-0.077
 appreciate-0.075
 named-0.073
Token and
Token ID290
Feature activation-2.42e+00

Pos logit contributions
aned+0.003
 fists+0.003
ares+0.003
ented+0.003
uffed+0.003
Neg logit contributions
 visit-0.001
 appreciate-0.001
 who-0.001
 farm-0.001
 wedding-0.001
Token brushed
Token ID31782
Feature activation-2.05e+00

Pos logit contributions
aned+0.077
 fists+0.076
ares+0.074
ented+0.070
omm+0.069
Neg logit contributions
 visit-0.051
 who-0.049
 appreciate-0.046
 live-0.044
 farm-0.043
Token off
Token ID572
Feature activation-3.60e-01

Pos logit contributions
ares+0.073
aned+0.070
 fists+0.069
ented+0.068
omm+0.067
Neg logit contributions
 who-0.030
 visit-0.030
 appreciate-0.025
 live-0.024
 play-0.023
Token her
Token ID607
Feature activation-2.06e+00

Pos logit contributions
aned+0.014
 fists+0.013
ares+0.013
ented+0.013
omm+0.012
Neg logit contributions
 visit-0.005
 who-0.005
 appreciate-0.004
 live-0.004
 coral-0.004
Token happy
Token ID3772
Feature activation+1.13e+00

Pos logit contributions
aned+0.036
 fists+0.036
ares+0.034
ented+0.033
 firmly+0.032
Neg logit contributions
 appreciate-0.018
 visit-0.018
 who-0.016
 live-0.016
 coral-0.015
Token and
Token ID290
Feature activation-1.09e+00

Pos logit contributions
 appreciate+0.028
 visit+0.028
 gra+0.027
 farm+0.026
 wedding+0.026
Neg logit contributions
 fists-0.026
aned-0.025
ares-0.025
ula-0.024
 off-0.023
Token excited
Token ID6568
Feature activation+1.99e-01

Pos logit contributions
aned+0.033
 fists+0.033
ares+0.032
ented+0.031
omm+0.030
Neg logit contributions
 visit-0.023
 appreciate-0.023
 who-0.021
 live-0.021
 coral-0.021
Token!
Token ID0
Feature activation-1.02e+00

Pos logit contributions
 visit+0.004
 appreciate+0.004
 live+0.004
 farm+0.004
 coral+0.004
Neg logit contributions
aned-0.006
 fists-0.006
ares-0.006
ented-0.005
 firmly-0.005
Token With
Token ID2080
Feature activation-9.22e-02

Pos logit contributions
aned+0.039
 fists+0.039
ares+0.037
ented+0.036
 firmly+0.036
Neg logit contributions
 visit-0.014
 appreciate-0.013
 who-0.011
 coral-0.011
 farm-0.011
Token the
Token ID262
Feature activation-3.31e+00

Pos logit contributions
aned+0.003
 fists+0.003
ares+0.003
ented+0.003
 firmly+0.003
Neg logit contributions
 visit-0.002
 appreciate-0.002
 who-0.001
 coral-0.001
 live-0.001
Token gem
Token ID16840
Feature activation-3.85e+00

Pos logit contributions
aned+0.121
 fists+0.119
ares+0.114
ented+0.112
 firmly+0.108
Neg logit contributions
 visit-0.053
 appreciate-0.051
 live-0.046
 who-0.044
 coral-0.044
Token,
Token ID11
Feature activation-7.96e-01

Pos logit contributions
aned+0.114
 fists+0.112
ares+0.108
ented+0.104
 firmly+0.100
Neg logit contributions
 visit-0.086
 appreciate-0.082
 who-0.078
 live-0.077
 coral-0.076
Token they
Token ID484
Feature activation+5.08e-01

Pos logit contributions
aned+0.027
 fists+0.026
ares+0.025
ented+0.024
omm+0.024
Neg logit contributions
 visit-0.015
 appreciate-0.014
 who-0.014
 live-0.013
 coral-0.013
Token could
Token ID714
Feature activation-4.06e-01

Pos logit contributions
 visit+0.011
 appreciate+0.011
 farm+0.010
 wedding+0.010
 live+0.010
Neg logit contributions
aned-0.014
 fists-0.014
ares-0.013
ented-0.013
 firmly-0.013
Token play
Token ID711
Feature activation+2.68e-01

Pos logit contributions
aned+0.012
 fists+0.011
ares+0.011
 firmly+0.011
ented+0.010
Neg logit contributions
 appreciate-0.008
 farm-0.008
 visit-0.008
 coral-0.008
arium-0.008
Token
Token ID220
Feature activation-2.46e-01

Pos logit contributions
 fists+0.036
aned+0.036
ares+0.035
ented+0.034
ier+0.033
Neg logit contributions
 visit-0.015
 appreciate-0.013
 who-0.013
 live-0.012
 farm-0.012
Token
Token ID198
Feature activation+1.49e+00

Pos logit contributions
 fists+0.010
aned+0.010
ares+0.009
ented+0.009
 firmly+0.009
Neg logit contributions
 visit-0.003
 appreciate-0.003
 who-0.002
 live-0.002
 farm-0.002
Token
Token ID198
Feature activation-1.13e+00

Pos logit contributions
 appreciate+0.021
 visit+0.021
 wedding+0.019
 coral+0.019
 farm+0.018
Neg logit contributions
aned-0.055
 fists-0.054
ares-0.052
 firmly-0.051
ented-0.050
Token"
Token ID1
Feature activation-5.82e-01

Pos logit contributions
 fists+0.040
aned+0.039
ares+0.038
ented+0.037
 firmly+0.036
Neg logit contributions
 visit-0.019
 appreciate-0.018
 who-0.017
 live-0.016
 farm-0.016
TokenO
Token ID46
Feature activation-3.30e+00

Pos logit contributions
aned+0.015
 fists+0.015
ares+0.014
ented+0.014
 firmly+0.013
Neg logit contributions
 visit-0.015
 appreciate-0.015
 who-0.014
 coral-0.014
 live-0.014
Tokenuch
Token ID794
Feature activation-3.57e+00

Pos logit contributions
 fists+0.062
aned+0.060
ares+0.055
ented+0.053
 firmly+0.051
Neg logit contributions
 visit-0.109
 appreciate-0.108
 live-0.102
 who-0.102
 farm-0.100
Token!"
Token ID2474
Feature activation-1.65e+00

Pos logit contributions
 fists+0.114
aned+0.113
ares+0.111
ented+0.108
omm+0.102
Neg logit contributions
 visit-0.064
 who-0.062
 appreciate-0.061
 live-0.057
 farm-0.055
Token cried
Token ID16896
Feature activation-2.57e+00

Pos logit contributions
 fists+0.048
aned+0.048
ares+0.046
ented+0.046
omm+0.043
Neg logit contributions
 visit-0.037
 appreciate-0.035
 who-0.034
 live-0.034
 coral-0.031
Token Tim
Token ID5045
Feature activation-1.74e+00

Pos logit contributions
aned+0.091
 fists+0.087
ares+0.086
ented+0.084
uffed+0.080
Neg logit contributions
 visit-0.047
 who-0.043
 live-0.040
 appreciate-0.040
 named-0.038
Tokenmy
Token ID1820
Feature activation-2.33e+00

Pos logit contributions
 fists+0.059
aned+0.059
ares+0.057
ented+0.055
 firmly+0.053
Neg logit contributions
 visit-0.030
 appreciate-0.029
 who-0.028
 live-0.025
 farm-0.024
Token.
Token ID13
Feature activation-6.38e-01

Pos logit contributions
aned+0.083
 fists+0.081
ares+0.081
ented+0.078
omm+0.078
Neg logit contributions
 who-0.035
 visit-0.035
 appreciate-0.030
 live-0.028
 farm-0.026
Token to
Token ID284
Feature activation+1.81e+00

Pos logit contributions
aned+0.045
 fists+0.044
ares+0.042
omm+0.041
ented+0.040
Neg logit contributions
 visit-0.030
 who-0.026
 appreciate-0.026
 live-0.025
 outdoors-0.025
Token the
Token ID262
Feature activation+1.43e+00

Pos logit contributions
 appreciate+0.036
 visit+0.036
 coral+0.033
 who+0.033
 live+0.032
Neg logit contributions
 fists-0.055
aned-0.054
ares-0.052
ented-0.050
 firmly-0.049
Token lake
Token ID13546
Feature activation+1.74e+00

Pos logit contributions
 appreciate+0.023
 visit+0.022
 who+0.020
 live+0.020
 coral+0.019
Neg logit contributions
 fists-0.049
aned-0.049
ares-0.047
ented-0.046
 firmly-0.045
Token.
Token ID13
Feature activation-6.62e-01

Pos logit contributions
 appreciate+0.042
 visit+0.040
 wedding+0.039
Hop+0.039
Buzz+0.038
Neg logit contributions
aned-0.042
 fists-0.041
 firmly-0.039
ares-0.039
ented-0.038
Token "
Token ID366
Feature activation+1.58e+00

Pos logit contributions
 fists+0.020
aned+0.019
ares+0.018
ented+0.018
 firmly+0.017
Neg logit contributions
 appreciate-0.014
 visit-0.014
 who-0.013
 live-0.013
 wedding-0.013
TokenLook
Token ID8567
Feature activation-4.25e+00

Pos logit contributions
arium+0.036
 appreciate+0.036
 coral+0.035
 live+0.035
 farm+0.035
Neg logit contributions
aned-0.038
 fists-0.037
ares-0.036
ented-0.035
nown-0.035
Token Rachel
Token ID15984
Feature activation-1.25e+00

Pos logit contributions
aned+0.124
 fists+0.119
ares+0.111
ented+0.109
 firmly+0.103
Neg logit contributions
 visit-0.099
 who-0.094
 appreciate-0.091
 wedding-0.088
 live-0.087
Token,
Token ID11
Feature activation-1.81e-01

Pos logit contributions
aned+0.034
 fists+0.034
ares+0.032
ented+0.031
 firmly+0.031
Neg logit contributions
 visit-0.030
 appreciate-0.029
 who-0.027
 live-0.027
 coral-0.027
Token the
Token ID262
Feature activation-9.08e-01

Pos logit contributions
 fists+0.004
ares+0.004
 firmly+0.004
ented+0.004
aned+0.004
Neg logit contributions
 appreciate-0.004
 visit-0.004
 farm-0.004
arium-0.004
 wedding-0.004
Token lake
Token ID13546
Feature activation-1.83e+00

Pos logit contributions
 fists+0.031
aned+0.030
ares+0.029
ented+0.028
 firmly+0.028
Neg logit contributions
 appreciate-0.015
 visit-0.015
 who-0.014
 live-0.013
arium-0.013
Token is
Token ID318
Feature activation-5.78e-01

Pos logit contributions
aned+0.047
 fists+0.047
ares+0.044
ented+0.043
 firmly+0.041
Neg logit contributions
 visit-0.046
 appreciate-0.046
 who-0.042
 live-0.042
 wedding-0.042
Token on
Token ID319
Feature activation+1.02e-01

Pos logit contributions
 fists+0.064
aned+0.064
ares+0.059
ented+0.058
omm+0.058
Neg logit contributions
 visit-0.047
 who-0.042
 appreciate-0.041
 live-0.041
 outdoors-0.038
Token a
Token ID257
Feature activation+4.03e-01

Pos logit contributions
 visit+0.002
 appreciate+0.002
 who+0.002
 wedding+0.002
 farm+0.002
Neg logit contributions
aned-0.003
 fists-0.003
ares-0.003
ented-0.003
 firmly-0.003
Token ride
Token ID6594
Feature activation+3.86e-02

Pos logit contributions
 appreciate+0.006
 visit+0.006
 coral+0.005
 live+0.005
 who+0.005
Neg logit contributions
 fists-0.014
aned-0.014
ares-0.014
ented-0.013
 firmly-0.013
Token.
Token ID13
Feature activation-9.87e-01

Pos logit contributions
 visit+0.001
 appreciate+0.001
 who+0.001
 live+0.001
 wedding+0.001
Neg logit contributions
 fists-0.001
aned-0.001
ares-0.001
ented-0.001
 firmly-0.001
Token But
Token ID887
Feature activation-1.76e+00

Pos logit contributions
aned+0.031
 fists+0.031
ares+0.030
ented+0.028
ula+0.027
Neg logit contributions
 visit-0.020
 appreciate-0.019
 who-0.019
 farm-0.018
 live-0.017
Token then
Token ID788
Feature activation-3.69e+00

Pos logit contributions
aned+0.058
 fists+0.057
ares+0.054
ented+0.052
ula+0.050
Neg logit contributions
 visit-0.036
 appreciate-0.034
 who-0.034
 live-0.032
 wedding-0.031
Token an
Token ID281
Feature activation-1.11e+00

Pos logit contributions
aned+0.130
 fists+0.123
ares+0.122
ented+0.116
ula+0.111
Neg logit contributions
 visit-0.073
 appreciate-0.065
 who-0.065
 live-0.064
 wedding-0.060
Token idea
Token ID2126
Feature activation-3.02e+00

Pos logit contributions
 fists+0.031
aned+0.030
ares+0.028
uffed+0.028
ented+0.027
Neg logit contributions
 visit-0.027
 appreciate-0.026
 who-0.025
 farm-0.025
 wedding-0.025
Token came
Token ID1625
Feature activation-1.42e+00

Pos logit contributions
 fists+0.092
aned+0.089
ented+0.083
ares+0.082
omm+0.081
Neg logit contributions
 visit-0.068
 who-0.065
 live-0.064
 appreciate-0.061
 named-0.057
Token to
Token ID284
Feature activation-5.11e-02

Pos logit contributions
aned+0.048
 fists+0.048
ares+0.045
ented+0.045
 firmly+0.043
Neg logit contributions
 visit-0.027
 appreciate-0.024
 who-0.023
 live-0.022
 outdoors-0.021
Token her
Token ID607
Feature activation+6.02e-01

Pos logit contributions
 fists+0.001
aned+0.001
ares+0.001
 firmly+0.001
ented+0.001
Neg logit contributions
 coral-0.001
 appreciate-0.001
arium-0.001
 who-0.001
 reef-0.001