TOP ACTIVATIONS
MAX = 6.601

, there was a fancy wedding . The bride and groom
, Max , to the carn ival . Everywhere they looked
the little girl to a special place . At the special
Good bye , Sara . Thank you for being my friend
a time there was a magical bridge . It was very
night , little bird . Thank you for helping me .
Tim my to a very special place . Daddy showed Tim
Once there was a famous holiday coming up . Everyone was
and Sam went on a saf ari with their mom and
had been invited to a special fire work show . All
had been invited to a special party . He couldn 't
! It was a fancy wedding with lots of flowers and
That was fun ! Thank you for helping me have
and Daniel had a big festival to go to . They
made me so happy . Thank you for restoring my life
he was going to a special party . He was so
to cry but then a magical thing happened . A big
always what they seem . Thank you for being brave and
end of our story ! Thank you for listening . <|endoftext|>
Dear Sara , Thank you for your lovely letter

MIN ACTIVATIONS
MIN = -6.786

into pieces . Ben and Mia are very sad . They
and breaks . Sam and Mia are shocked . They look
and pulls . Tim and Mia are scared . They let
no lock . Tom and Mia are scared and sad .
had hamm ers , screw drivers , pl iers , and
the tube . Ben and Mia let go of the tube
its wheels . Ben and Mia are sad and scared .
scissors break . Tom and Jen are sad .
. He hits Tim and Jen with it . Tim and
. He pushes Tim and Mia off the toy and sits
it with holes of different sizes . I will make it
eleven , twelve , thirteen , fourteen , fifteen , sixteen
into pieces . Tom and Mia are shocked and sad .
Cars , trucks , buses , and bikes . They were
with it . Tim and Jen are hurt and scared .
shapes . They can make towers , houses , cars and
cars of different colors and sizes . He likes to make
is flat . Tim and Sue are sad . They drop
pots , coins , paintings , and statues . They learn
cars of different colors and sizes . They make a line

INTERVAL 3.255 - 6.601
CONTAINS 0.625%

even longer friendship with him now . <|endoftext|> One day ,
her friends went home , happy and proud of themselves for
, there was a little band . The band was made
, there was a playful puppy named Max . Max loved
again soon and was happy he had such an attractive pair

INTERVAL -0.092 - 3.255
CONTAINS 52.413%

remind everyone to be careful and to always ask for help
The farmer is nice . He gives Tom and
forgiving . <|endoftext|> L ily and Tom were bored . The
boy was so excited . He thanked his mother and she
. He gave Ben a kiss on the cheek . Ben

INTERVAL -3.439 - -0.092
CONTAINS 46.411%

lost the game ." <|endoftext|> L ily and Ben are friends
decide to play together and share their toys . They find
was caught in a hole . Tim my helped Ricky get
. Mia saw many trees , flowers , and birds .
The bird nodded and said , " Yes , yes

INTERVAL -6.786 - -3.439
CONTAINS 0.551%

a woman . Tim and Sam pull the doll out of
happy . <|endoftext|> Tim and Mia liked to play with the
Sam hurt himself and made Tom cry . They were very
had ever been . <|endoftext|> J ill was a three year
listen . She p inches Ben 's hand hard . Ben
Token,
Token ID11
Feature activation-8.42e-01

Pos logit contributions
 levers+0.020
 brushes+0.017
 swirl+0.016
uits+0.016
 switches+0.016
Neg logit contributions
eros-0.016
over-0.016
isher-0.016
 Amen-0.015
ter-0.015
Token there
Token ID612
Feature activation-6.87e-01

Pos logit contributions
 levers+0.015
 brushes+0.014
Ma+0.014
 swirl+0.013
 ABC+0.013
Neg logit contributions
isher-0.019
eros-0.018
 Amen-0.018
over-0.017
bye-0.017
Token was
Token ID373
Feature activation+3.07e-01

Pos logit contributions
 levers+0.015
 brushes+0.013
uits+0.013
 blush+0.012
 swirl+0.012
Neg logit contributions
eros-0.014
isher-0.014
over-0.013
 Amen-0.013
mer-0.012
Token a
Token ID257
Feature activation+4.36e-01

Pos logit contributions
isher+0.008
eros+0.008
over+0.007
 Amen+0.007
mer+0.007
Neg logit contributions
 levers-0.005
 brushes-0.004
uits-0.004
 swirl-0.004
 ABC-0.004
Token fancy
Token ID14996
Feature activation+3.06e+00

Pos logit contributions
isher+0.011
eros+0.011
over+0.010
 Amen+0.010
ised+0.010
Neg logit contributions
 levers-0.007
 brushes-0.006
 swirl-0.006
 ABC-0.006
Ma-0.006
Token wedding
Token ID10614
Feature activation+6.13e+00

Pos logit contributions
isher+0.065
jected+0.063
 Amen+0.062
ised+0.062
well+0.060
Neg logit contributions
 levers-0.055
 ABC-0.054
 brushes-0.054
 swirl-0.053
 marks-0.050
Token.
Token ID13
Feature activation-2.35e-01

Pos logit contributions
isher+0.157
ised+0.139
eros+0.133
jected+0.132
aciously+0.130
Neg logit contributions
 ABC-0.095
 brushes-0.089
 big-0.086
 swirl-0.085
 names-0.085
Token The
Token ID383
Feature activation+4.66e-01

Pos logit contributions
 levers+0.005
 brushes+0.004
uits+0.004
 swirl+0.004
 ABC+0.004
Neg logit contributions
isher-0.005
eros-0.005
over-0.005
 Amen-0.005
mer-0.004
Token bride
Token ID26619
Feature activation+1.21e+00

Pos logit contributions
isher+0.012
eros+0.011
over+0.011
mer+0.011
ised+0.011
Neg logit contributions
 levers-0.007
 brushes-0.007
 ABC-0.007
 swirl-0.006
 names-0.006
Token and
Token ID290
Feature activation-6.54e-01

Pos logit contributions
isher+0.028
eros+0.027
over+0.026
 Amen+0.026
mer+0.024
Neg logit contributions
 levers-0.022
 brushes-0.020
 ABC-0.019
 swirl-0.019
 marks-0.019
Token groom
Token ID32443
Feature activation+7.44e-01

Pos logit contributions
 levers+0.012
 brushes+0.010
 swirl+0.010
 ABC+0.010
uits+0.010
Neg logit contributions
isher-0.016
eros-0.015
over-0.015
 Amen-0.014
mer-0.014
Token,
Token ID11
Feature activation+4.92e-01

Pos logit contributions
isher+0.044
eros+0.042
over+0.041
 Amen+0.040
mer+0.038
Neg logit contributions
 levers-0.044
 brushes-0.039
uits-0.038
 swirl-0.038
 ABC-0.037
Token Max
Token ID5436
Feature activation-9.31e-01

Pos logit contributions
isher+0.010
over+0.010
eros+0.010
 Amen+0.010
mer+0.009
Neg logit contributions
 levers-0.010
 brushes-0.009
uits-0.008
 ABC-0.008
 swirl-0.008
Token,
Token ID11
Feature activation-1.27e+00

Pos logit contributions
 levers+0.013
 brushes+0.011
uits+0.011
 names+0.010
 swirl+0.010
Neg logit contributions
isher-0.026
eros-0.024
 Amen-0.024
over-0.023
ised-0.023
Token to
Token ID284
Feature activation+1.79e+00

Pos logit contributions
 levers+0.025
 brushes+0.023
uits+0.022
 swirl+0.021
 ABC+0.021
Neg logit contributions
isher-0.028
eros-0.027
over-0.026
 Amen-0.025
mer-0.024
Token the
Token ID262
Feature activation+9.18e-01

Pos logit contributions
isher+0.048
eros+0.047
over+0.044
mer+0.044
 Amen+0.044
Neg logit contributions
 levers-0.028
 brushes-0.025
 swirl-0.025
uits-0.023
 names-0.023
Token carn
Token ID18466
Feature activation+5.97e+00

Pos logit contributions
isher+0.018
eros+0.017
over+0.017
 Amen+0.017
mer+0.016
Neg logit contributions
 levers-0.020
 brushes-0.018
 swirl-0.018
 ABC-0.018
 names-0.017
Tokenival
Token ID2473
Feature activation+2.55e+00

Pos logit contributions
ter+0.158
eros+0.155
 Amen+0.153
isher+0.152
gy+0.140
Neg logit contributions
uits-0.081
 brushes-0.076
 ABC-0.075
 desks-0.070
cases-0.068
Token.
Token ID13
Feature activation-1.25e+00

Pos logit contributions
isher+0.071
 Amen+0.068
eros+0.066
jected+0.062
over+0.060
Neg logit contributions
 levers-0.038
uits-0.033
 ABC-0.033
 brushes-0.033
 numbers-0.032
Token Everywhere
Token ID48201
Feature activation-4.12e-01

Pos logit contributions
 levers+0.029
 brushes+0.027
 swirl+0.027
 marks+0.026
uits+0.026
Neg logit contributions
 Amen-0.020
eros-0.020
over-0.019
isher-0.019
penter-0.019
Token they
Token ID484
Feature activation-1.18e+00

Pos logit contributions
 levers+0.008
 brushes+0.007
 ABC+0.006
uits+0.006
 switches+0.006
Neg logit contributions
isher-0.010
eros-0.009
over-0.009
 Amen-0.009
mer-0.008
Token looked
Token ID3114
Feature activation-4.95e-01

Pos logit contributions
 levers+0.021
 brushes+0.019
 ABC+0.017
 swirl+0.017
 switches+0.017
Neg logit contributions
eros-0.028
over-0.028
isher-0.027
 Amen-0.027
edly-0.025
Token the
Token ID262
Feature activation-5.21e-01

Pos logit contributions
isher+0.053
eros+0.051
over+0.050
 Amen+0.049
mer+0.046
Neg logit contributions
 levers-0.045
 brushes-0.040
uits-0.039
 swirl-0.038
 ABC-0.038
Token little
Token ID1310
Feature activation+9.94e-01

Pos logit contributions
 levers+0.011
uits+0.010
Ma+0.010
 widen+0.010
 blush+0.009
Neg logit contributions
isher-0.010
eros-0.009
over-0.009
ter-0.009
mer-0.009
Token girl
Token ID2576
Feature activation-5.80e-01

Pos logit contributions
 Amen+0.015
isher+0.015
eros+0.015
over+0.014
jected+0.013
Neg logit contributions
 levers-0.026
 brushes-0.024
 swirl-0.023
 marks-0.023
 switches-0.022
Token to
Token ID284
Feature activation+1.57e+00

Pos logit contributions
 levers+0.011
 brushes+0.010
uits+0.009
 swirl+0.009
Ma+0.009
Neg logit contributions
isher-0.013
eros-0.012
over-0.012
 Amen-0.012
mer-0.011
Token a
Token ID257
Feature activation+1.49e+00

Pos logit contributions
isher+0.042
eros+0.041
over+0.039
 Amen+0.038
mer+0.038
Neg logit contributions
 levers-0.024
 brushes-0.021
 swirl-0.020
uits-0.020
 ABC-0.019
Token special
Token ID2041
Feature activation+5.94e+00

Pos logit contributions
isher+0.041
eros+0.040
over+0.038
 Amen+0.037
ter+0.037
Neg logit contributions
 levers-0.021
 brushes-0.020
 ABC-0.018
 swirl-0.018
 names-0.017
Token place
Token ID1295
Feature activation+2.78e+00

Pos logit contributions
jected+0.136
agged+0.133
isher+0.133
eros+0.130
 Amen+0.122
Neg logit contributions
 brushes-0.102
 swirl-0.098
 ABC-0.098
 names-0.096
 paints-0.094
Token.
Token ID13
Feature activation-3.69e-01

Pos logit contributions
isher+0.061
eros+0.060
over+0.057
 Amen+0.057
mer+0.054
Neg logit contributions
 levers-0.055
 brushes-0.049
uits-0.047
 swirl-0.046
 ABC-0.046
Token At
Token ID1629
Feature activation+2.06e+00

Pos logit contributions
 levers+0.009
 marks+0.008
uits+0.007
 brushes+0.007
Ma+0.007
Neg logit contributions
isher-0.006
eros-0.006
over-0.006
 Amen-0.006
 Now-0.006
Token the
Token ID262
Feature activation+4.85e-01

Pos logit contributions
isher+0.063
over+0.061
eros+0.060
mer+0.059
 Amen+0.057
Neg logit contributions
 levers-0.023
 brushes-0.022
uits-0.020
 swirl-0.019
Ma-0.019
Token special
Token ID2041
Feature activation+2.79e+00

Pos logit contributions
isher+0.009
eros+0.009
over+0.009
 Amen+0.008
mer+0.008
Neg logit contributions
 levers-0.011
 brushes-0.010
uits-0.010
 swirl-0.010
 ABC-0.009
TokenGood
Token ID10248
Feature activation+4.75e+00

Pos logit contributions
isher+0.063
eros+0.057
 reunited+0.055
ishing+0.053
penter+0.052
Neg logit contributions
Ma-0.049
 levers-0.048
 swirl-0.046
 names-0.045
La-0.044
Tokenbye
Token ID16390
Feature activation+1.84e+00

Pos logit contributions
isher+0.072
ised+0.062
handed+0.062
eros+0.060
penter+0.059
Neg logit contributions
 names-0.126
 marks-0.119
 ABC-0.114
 levers-0.114
 swirl-0.112
Token,
Token ID11
Feature activation+2.45e-02

Pos logit contributions
isher+0.043
eros+0.041
over+0.040
 Amen+0.040
mer+0.038
Neg logit contributions
 levers-0.034
 brushes-0.030
uits-0.028
 swirl-0.028
 ABC-0.028
Token Sara
Token ID24799
Feature activation-1.02e+00

Pos logit contributions
isher+0.001
 Amen+0.001
over+0.001
eros+0.001
date+0.001
Neg logit contributions
 levers-0.000
 swirl-0.000
 brushes-0.000
 numbers-0.000
Ma-0.000
Token.
Token ID13
Feature activation+2.33e+00

Pos logit contributions
 levers+0.013
 marks+0.012
 brushes+0.012
Ma+0.011
 swirl+0.011
Neg logit contributions
isher-0.029
eros-0.026
 Amen-0.026
ised-0.026
date-0.025
Token Thank
Token ID6952
Feature activation+5.87e+00

Pos logit contributions
isher+0.053
ised+0.048
ishing+0.046
mer+0.045
 reunited+0.044
Neg logit contributions
 names-0.041
Ma-0.039
 levers-0.038
 ABC-0.038
 Ma-0.038
Token you
Token ID345
Feature activation+1.12e+00

Pos logit contributions
isher+0.151
penter+0.139
jack+0.131
boat+0.125
bank+0.124
Neg logit contributions
Ma-0.090
 names-0.088
 marks-0.081
La-0.081
 are-0.079
Token for
Token ID329
Feature activation+2.58e+00

Pos logit contributions
isher+0.019
eros+0.019
over+0.019
 Amen+0.018
mer+0.017
Neg logit contributions
 levers-0.027
 brushes-0.025
 swirl-0.023
uits-0.023
 switches-0.023
Token being
Token ID852
Feature activation+3.02e+00

Pos logit contributions
isher+0.082
mer+0.078
ised+0.072
over+0.070
ome+0.068
Neg logit contributions
 swirl-0.031
 numbers-0.029
 th-0.029
Ma-0.028
 levers-0.028
Token my
Token ID616
Feature activation+2.01e+00

Pos logit contributions
isher+0.079
eros+0.073
mer+0.068
 Amen+0.068
jack+0.068
Neg logit contributions
 levers-0.044
Ma-0.041
 names-0.041
 swirl-0.040
 brushes-0.039
Token friend
Token ID1545
Feature activation+1.39e+00

Pos logit contributions
isher+0.032
eros+0.031
over+0.030
 Amen+0.029
mer+0.027
Neg logit contributions
 levers-0.051
 brushes-0.047
uits-0.045
 swirl-0.045
 ABC-0.045
Token a
Token ID257
Feature activation+1.93e+00

Pos logit contributions
isher+0.099
eros+0.092
mer+0.087
 Amen+0.087
over+0.084
Neg logit contributions
 levers-0.035
 swirl-0.031
 marks-0.030
 brushes-0.030
Ma-0.030
Token time
Token ID640
Feature activation+4.13e-01

Pos logit contributions
isher+0.051
eros+0.049
over+0.047
 Amen+0.047
mer+0.045
Neg logit contributions
 levers-0.030
 brushes-0.026
uits-0.024
 swirl-0.024
 ABC-0.024
Token there
Token ID612
Feature activation+1.56e+00

Pos logit contributions
isher+0.010
eros+0.009
 Amen+0.009
over+0.009
mer+0.008
Neg logit contributions
 levers-0.008
 brushes-0.007
uits-0.007
 swirl-0.007
Ma-0.006
Token was
Token ID373
Feature activation+1.61e+00

Pos logit contributions
isher+0.039
eros+0.038
 Amen+0.037
over+0.036
mer+0.035
Neg logit contributions
 levers-0.025
 brushes-0.022
uits-0.021
 swirl-0.021
Ma-0.021
Token a
Token ID257
Feature activation+9.24e-01

Pos logit contributions
over+0.034
isher+0.033
 Amen+0.032
eros+0.032
date+0.030
Neg logit contributions
 levers-0.033
 brushes-0.029
uits-0.027
 ABC-0.027
 swirl-0.027
Token magical
Token ID10883
Feature activation+5.86e+00

Pos logit contributions
isher+0.023
eros+0.021
over+0.020
 Amen+0.020
ised+0.019
Neg logit contributions
 levers-0.016
 brushes-0.014
 swirl-0.014
 ABC-0.014
Ma-0.013
Token bridge
Token ID7696
Feature activation+3.32e+00

Pos logit contributions
isher+0.127
jected+0.120
agged+0.116
eros+0.116
 Amen+0.115
Neg logit contributions
 levers-0.104
 swirl-0.103
 brushes-0.100
 magn-0.096
 ABC-0.095
Token.
Token ID13
Feature activation+7.24e-01

Pos logit contributions
isher+0.083
eros+0.079
 Amen+0.079
over+0.073
ised+0.070
Neg logit contributions
 levers-0.056
 brushes-0.049
uits-0.048
 swirl-0.048
 marks-0.046
Token It
Token ID632
Feature activation+1.59e+00

Pos logit contributions
isher+0.019
eros+0.017
mer+0.017
ishing+0.016
over+0.016
Neg logit contributions
 levers-0.012
 brushes-0.011
Ma-0.010
uits-0.010
 swirl-0.010
Token was
Token ID373
Feature activation-2.24e-01

Pos logit contributions
isher+0.045
eros+0.043
over+0.042
 Amen+0.040
date+0.039
Neg logit contributions
 levers-0.023
 brushes-0.020
 swirl-0.019
 switches-0.018
Ma-0.018
Token very
Token ID845
Feature activation+4.04e-01

Pos logit contributions
 levers+0.004
 brushes+0.004
 ABC+0.004
 blush+0.004
uits+0.004
Neg logit contributions
isher-0.005
over-0.004
eros-0.004
 Amen-0.004
boat-0.004
Tokennight
Token ID3847
Feature activation+3.43e+00

Pos logit contributions
isher+0.080
handed+0.072
ised+0.070
eros+0.066
date+0.066
Neg logit contributions
 names-0.107
 marks-0.104
 ABC-0.102
 swirl-0.100
 levers-0.099
Token,
Token ID11
Feature activation+5.33e-01

Pos logit contributions
isher+0.095
ised+0.086
eros+0.085
jected+0.082
Deal+0.080
Neg logit contributions
 levers-0.045
 swirl-0.042
 ABC-0.041
 names-0.040
Ma-0.039
Token little
Token ID1310
Feature activation+8.85e-01

Pos logit contributions
isher+0.014
mer+0.013
over+0.013
eros+0.013
edly+0.013
Neg logit contributions
 levers-0.008
 swirl-0.008
 ABC-0.007
 brushes-0.007
 switches-0.007
Token bird
Token ID6512
Feature activation+1.94e+00

Pos logit contributions
isher+0.020
over+0.019
eros+0.019
edly+0.019
mer+0.018
Neg logit contributions
 levers-0.015
 swirl-0.015
 marks-0.014
 brushes-0.014
 numbers-0.013
Token.
Token ID13
Feature activation+3.08e+00

Pos logit contributions
isher+0.056
 gol+0.051
ised+0.050
eros+0.049
agged+0.048
Neg logit contributions
 swirl-0.020
 marks-0.019
Ma-0.018
 levers-0.018
 ABC-0.018
Token Thank
Token ID6952
Feature activation+5.86e+00

Pos logit contributions
isher+0.076
mer+0.067
ishing+0.067
over+0.067
ised+0.066
Neg logit contributions
Ma-0.049
 ABC-0.049
 levers-0.046
 names-0.046
 Ma-0.046
Token you
Token ID345
Feature activation+1.17e+00

Pos logit contributions
isher+0.167
penter+0.144
mer+0.140
bank+0.140
 gol+0.140
Neg logit contributions
Ma-0.074
La-0.063
 are-0.062
-0.061
 names-0.060
Token for
Token ID329
Feature activation+2.63e+00

Pos logit contributions
isher+0.024
eros+0.022
over+0.021
 Amen+0.020
mer+0.020
Neg logit contributions
 levers-0.025
uits-0.022
 brushes-0.022
Ma-0.022
 ABC-0.022
Token helping
Token ID5742
Feature activation+5.47e-01

Pos logit contributions
mer+0.088
isher+0.086
ised+0.075
ome+0.075
over+0.073
Neg logit contributions
 th-0.030
 swirl-0.028
 come-0.027
 not-0.026
 big-0.025
Token me
Token ID502
Feature activation-7.82e-01

Pos logit contributions
isher+0.010
eros+0.009
over+0.009
 Amen+0.009
mer+0.008
Neg logit contributions
 levers-0.013
 brushes-0.012
 swirl-0.012
 ABC-0.012
 marks-0.011
Token.
Token ID13
Feature activation+2.95e+00

Pos logit contributions
 levers+0.012
 swirl+0.012
 marks+0.011
uits+0.011
 ABC+0.011
Neg logit contributions
isher-0.020
eros-0.019
over-0.018
mer-0.017
 gol-0.017
Token Tim
Token ID5045
Feature activation-2.12e+00

Pos logit contributions
isher+0.069
eros+0.067
over+0.064
 Amen+0.064
mer+0.061
Neg logit contributions
 levers-0.053
 brushes-0.047
uits-0.044
 swirl-0.044
 ABC-0.044
Tokenmy
Token ID1820
Feature activation-1.25e+00

Pos logit contributions
 levers+0.034
 brushes+0.030
uits+0.028
 swirl+0.028
 ABC+0.027
Neg logit contributions
isher-0.054
eros-0.053
over-0.051
 Amen-0.051
mer-0.049
Token to
Token ID284
Feature activation+1.59e+00

Pos logit contributions
 levers+0.023
 brushes+0.020
uits+0.019
 swirl+0.019
 ABC+0.019
Neg logit contributions
isher-0.029
eros-0.028
over-0.027
 Amen-0.027
mer-0.026
Token a
Token ID257
Feature activation+1.99e+00

Pos logit contributions
isher+0.043
eros+0.042
over+0.040
 Amen+0.039
mer+0.039
Neg logit contributions
 levers-0.024
 brushes-0.021
 swirl-0.020
uits-0.020
 ABC-0.019
Token very
Token ID845
Feature activation+2.12e+00

Pos logit contributions
isher+0.052
eros+0.050
over+0.048
ter+0.047
 Amen+0.047
Neg logit contributions
 levers-0.030
 brushes-0.028
 swirl-0.027
 ABC-0.027
uits-0.026
Token special
Token ID2041
Feature activation+5.83e+00

Pos logit contributions
eros+0.059
isher+0.059
ter+0.055
 Amen+0.055
over+0.053
Neg logit contributions
 levers-0.029
 brushes-0.026
 ABC-0.024
 swirl-0.023
uits-0.023
Token place
Token ID1295
Feature activation+2.61e+00

Pos logit contributions
jected+0.125
isher+0.124
eros+0.122
agged+0.120
over+0.114
Neg logit contributions
 swirl-0.102
 ABC-0.102
 brushes-0.100
 levers-0.100
 names-0.097
Token.
Token ID13
Feature activation-9.15e-01

Pos logit contributions
isher+0.059
eros+0.058
 Amen+0.056
over+0.055
mer+0.052
Neg logit contributions
 levers-0.050
 brushes-0.044
uits-0.043
 swirl-0.041
 marks-0.041
Token Daddy
Token ID26926
Feature activation-3.12e-01

Pos logit contributions
 levers+0.024
Ma+0.022
 brushes+0.021
 blush+0.021
uits+0.021
Neg logit contributions
isher-0.013
eros-0.012
 Amen-0.012
over-0.012
 Now-0.011
Token showed
Token ID3751
Feature activation+1.15e+00

Pos logit contributions
 levers+0.006
 brushes+0.005
uits+0.005
 swirl+0.005
 ABC+0.005
Neg logit contributions
isher-0.007
eros-0.007
over-0.007
 Amen-0.006
mer-0.006
Token Tim
Token ID5045
Feature activation-2.93e+00

Pos logit contributions
isher+0.020
eros+0.019
over+0.017
ter+0.017
 Amen+0.017
Neg logit contributions
 levers-0.028
 brushes-0.025
uits-0.025
Ma-0.025
 ABC-0.025
TokenOnce
Token ID7454
Feature activation-1.17e+00

Pos logit contributions
isher+0.076
eros+0.070
 Amen+0.067
over+0.066
penter+0.063
Neg logit contributions
 levers-0.055
 brushes-0.049
uits-0.048
 swirl-0.047
 ABC-0.047
Token there
Token ID612
Feature activation-1.15e+00

Pos logit contributions
 levers+0.021
 swirl+0.018
 brushes+0.017
 switches+0.017
 blush+0.016
Neg logit contributions
isher-0.027
eros-0.027
over-0.026
 Amen-0.025
ised-0.025
Token was
Token ID373
Feature activation+1.21e-01

Pos logit contributions
 levers+0.026
 brushes+0.022
uits+0.022
 swirl+0.021
Ma+0.021
Neg logit contributions
isher-0.022
eros-0.022
over-0.021
mer-0.020
ter-0.020
Token a
Token ID257
Feature activation+9.61e-01

Pos logit contributions
over+0.002
isher+0.002
 Amen+0.002
eros+0.002
ter+0.002
Neg logit contributions
 levers-0.003
 brushes-0.002
uits-0.002
 ABC-0.002
 switches-0.002
Token famous
Token ID5863
Feature activation+4.00e+00

Pos logit contributions
isher+0.023
eros+0.022
over+0.021
 Amen+0.021
ised+0.020
Neg logit contributions
 levers-0.017
 brushes-0.015
 swirl-0.015
 ABC-0.015
Ma-0.014
Token holiday
Token ID9912
Feature activation+5.82e+00

Pos logit contributions
isher+0.087
ised+0.081
 Amen+0.081
jected+0.079
over+0.078
Neg logit contributions
 levers-0.073
 swirl-0.071
 ABC-0.070
 brushes-0.070
 numbers-0.066
Token coming
Token ID2406
Feature activation+1.77e+00

Pos logit contributions
isher+0.171
 Amen+0.160
eros+0.156
jected+0.147
edly+0.146
Neg logit contributions
 brushes-0.062
 levers-0.062
 ABC-0.058
 swirl-0.054
 numbers-0.054
Token up
Token ID510
Feature activation+1.56e+00

Pos logit contributions
isher+0.039
eros+0.038
 Amen+0.036
over+0.035
mer+0.034
Neg logit contributions
 levers-0.035
 brushes-0.031
uits-0.031
 ABC-0.030
 names-0.029
Token.
Token ID13
Feature activation-8.76e-01

Pos logit contributions
isher+0.035
eros+0.033
 Amen+0.031
over+0.031
mer+0.029
Neg logit contributions
 levers-0.031
 brushes-0.028
uits-0.027
 swirl-0.026
 ABC-0.026
Token Everyone
Token ID11075
Feature activation-1.92e+00

Pos logit contributions
 levers+0.018
 brushes+0.016
uits+0.015
 swirl+0.015
 ABC+0.015
Neg logit contributions
isher-0.019
eros-0.018
over-0.017
 Amen-0.017
mer-0.017
Token was
Token ID373
Feature activation-2.32e-01

Pos logit contributions
 levers+0.038
 brushes+0.035
 swirl+0.033
uits+0.033
 ABC+0.032
Neg logit contributions
isher-0.041
eros-0.040
over-0.039
 Amen-0.038
mer-0.036
Token and
Token ID290
Feature activation+9.45e-01

Pos logit contributions
 levers+0.045
uits+0.038
 swirl+0.037
 brushes+0.037
 switches+0.037
Neg logit contributions
isher-0.044
over-0.044
eros-0.044
 Amen-0.041
mer-0.040
Token Sam
Token ID3409
Feature activation-3.28e+00

Pos logit contributions
isher+0.025
eros+0.024
over+0.023
 Amen+0.023
mer+0.023
Neg logit contributions
 levers-0.015
 brushes-0.013
 swirl-0.012
uits-0.012
Ma-0.012
Token went
Token ID1816
Feature activation+2.37e+00

Pos logit contributions
 levers+0.070
uits+0.059
 switches+0.058
 ABC+0.058
 brushes+0.058
Neg logit contributions
isher-0.066
over-0.064
eros-0.063
 Amen-0.059
bye-0.059
Token on
Token ID319
Feature activation-5.94e-01

Pos logit contributions
isher+0.066
eros+0.061
 Amen+0.060
mer+0.060
over+0.059
Neg logit contributions
 levers-0.033
 brushes-0.031
uits-0.030
 names-0.029
 ABC-0.028
Token a
Token ID257
Feature activation+7.71e-01

Pos logit contributions
 levers+0.012
 brushes+0.010
 swirl+0.010
uits+0.010
Ma+0.010
Neg logit contributions
eros-0.013
over-0.013
isher-0.012
 Amen-0.012
ised-0.012
Token saf
Token ID1932
Feature activation+5.78e+00

Pos logit contributions
isher+0.022
eros+0.021
over+0.021
 Amen+0.020
ter+0.020
Neg logit contributions
 levers-0.010
 brushes-0.009
 swirl-0.008
uits-0.008
 ABC-0.008
Tokenari
Token ID2743
Feature activation+4.30e+00

Pos logit contributions
isher+0.083
 Amen+0.077
over+0.070
eros+0.068
ter+0.066
Neg logit contributions
 levers-0.154
uits-0.150
 brushes-0.145
 ABC-0.144
 names-0.141
Token with
Token ID351
Feature activation+1.43e+00

Pos logit contributions
isher+0.126
 Amen+0.115
eros+0.114
jected+0.109
eday+0.106
Neg logit contributions
 levers-0.058
uits-0.050
 brushes-0.050
 marks-0.048
 swirl-0.047
Token their
Token ID511
Feature activation+4.08e-01

Pos logit contributions
isher+0.036
eros+0.034
over+0.033
 Amen+0.033
mer+0.032
Neg logit contributions
 levers-0.025
 brushes-0.022
uits-0.021
Ma-0.021
 swirl-0.020
Token mom
Token ID1995
Feature activation-2.55e-02

Pos logit contributions
isher+0.010
eros+0.010
over+0.010
 Amen+0.010
mer+0.009
Neg logit contributions
 levers-0.007
 brushes-0.006
uits-0.006
 swirl-0.005
 ABC-0.005
Token and
Token ID290
Feature activation+1.14e+00

Pos logit contributions
 levers+0.001
 brushes+0.000
uits+0.000
 swirl+0.000
Ma+0.000
Neg logit contributions
isher-0.001
eros-0.001
over-0.001
 Amen-0.001
ter-0.000
Token had
Token ID550
Feature activation+1.15e+00

Pos logit contributions
isher+0.018
eros+0.017
over+0.016
 Amen+0.016
mer+0.016
Neg logit contributions
 levers-0.023
uits-0.020
 ABC-0.020
 brushes-0.020
Ma-0.020
Token been
Token ID587
Feature activation+1.39e+00

Pos logit contributions
isher+0.019
over+0.019
eros+0.019
 Amen+0.018
 reunited+0.018
Neg logit contributions
 levers-0.027
 brushes-0.023
uits-0.023
 ABC-0.023
 swirl-0.023
Token invited
Token ID9392
Feature activation+3.06e+00

Pos logit contributions
isher+0.033
eros+0.032
 Amen+0.031
over+0.029
ised+0.029
Neg logit contributions
 levers-0.024
 brushes-0.022
 swirl-0.021
 ABC-0.021
Ma-0.021
Token to
Token ID284
Feature activation+1.71e+00

Pos logit contributions
over+0.053
eros+0.049
date+0.048
isher+0.048
 reunited+0.048
Neg logit contributions
 levers-0.075
 brushes-0.066
 switches-0.062
 spills-0.061
 swirl-0.061
Token a
Token ID257
Feature activation+1.31e+00

Pos logit contributions
isher+0.040
eros+0.039
over+0.037
 Amen+0.037
mer+0.035
Neg logit contributions
 levers-0.031
 brushes-0.028
uits-0.026
 swirl-0.026
 ABC-0.026
Token special
Token ID2041
Feature activation+5.75e+00

Pos logit contributions
isher+0.027
eros+0.025
over+0.024
 Amen+0.024
mer+0.023
Neg logit contributions
 levers-0.028
 brushes-0.025
 swirl-0.024
uits-0.024
 ABC-0.024
Token fire
Token ID2046
Feature activation+3.01e+00

Pos logit contributions
isher+0.113
eros+0.104
jected+0.103
over+0.099
 Amen+0.097
Neg logit contributions
 levers-0.119
 ABC-0.115
 swirl-0.115
 brushes-0.114
 names-0.110
Tokenwork
Token ID1818
Feature activation+3.42e+00

Pos logit contributions
isher+0.065
 Amen+0.061
eros+0.061
over+0.060
ised+0.058
Neg logit contributions
 levers-0.059
 names-0.051
uits-0.050
 brushes-0.050
 swirl-0.049
Token show
Token ID905
Feature activation+2.48e+00

Pos logit contributions
isher+0.080
eros+0.077
 Amen+0.074
over+0.071
ised+0.071
Neg logit contributions
 levers-0.061
 swirl-0.054
 brushes-0.054
uits-0.053
 ABC-0.052
Token.
Token ID13
Feature activation+7.40e-02

Pos logit contributions
isher+0.051
eros+0.049
over+0.049
 Amen+0.046
mer+0.045
Neg logit contributions
 levers-0.051
 brushes-0.046
 swirl-0.044
uits-0.043
 ABC-0.043
Token All
Token ID1439
Feature activation-9.36e-01

Pos logit contributions
isher+0.002
eros+0.001
over+0.001
 Amen+0.001
mer+0.001
Neg logit contributions
 levers-0.002
 brushes-0.001
uits-0.001
 swirl-0.001
 ABC-0.001
Token had
Token ID550
Feature activation+4.58e-01

Pos logit contributions
isher+0.022
eros+0.021
over+0.020
 Amen+0.020
mer+0.019
Neg logit contributions
 levers-0.017
 brushes-0.015
 swirl-0.014
 ABC-0.014
uits-0.014
Token been
Token ID587
Feature activation+9.93e-01

Pos logit contributions
isher+0.010
eros+0.010
over+0.010
 Amen+0.010
 reunited+0.009
Neg logit contributions
 levers-0.009
 brushes-0.008
uits-0.007
 ABC-0.007
Ma-0.007
Token invited
Token ID9392
Feature activation+2.71e+00

Pos logit contributions
isher+0.026
eros+0.025
 Amen+0.025
ised+0.024
jack+0.023
Neg logit contributions
 levers-0.014
 ABC-0.013
 brushes-0.013
 swirl-0.013
 marks-0.013
Token to
Token ID284
Feature activation+1.13e+00

Pos logit contributions
over+0.049
isher+0.048
eros+0.048
date+0.044
 Amen+0.044
Neg logit contributions
 levers-0.063
 brushes-0.058
 swirl-0.054
Ma-0.053
 blush-0.052
Token a
Token ID257
Feature activation+1.21e+00

Pos logit contributions
isher+0.028
eros+0.027
over+0.026
 Amen+0.025
mer+0.025
Neg logit contributions
 levers-0.019
 brushes-0.017
 swirl-0.016
uits-0.016
 ABC-0.016
Token special
Token ID2041
Feature activation+5.74e+00

Pos logit contributions
isher+0.025
eros+0.024
over+0.023
 Amen+0.022
ised+0.021
Neg logit contributions
 levers-0.025
 brushes-0.023
 swirl-0.023
 ABC-0.023
uits-0.022
Token party
Token ID2151
Feature activation+4.14e+00

Pos logit contributions
isher+0.122
jected+0.115
agged+0.112
eros+0.110
ised+0.110
Neg logit contributions
 ABC-0.110
 swirl-0.107
 levers-0.106
 names-0.104
 brushes-0.103
Token.
Token ID13
Feature activation-1.99e-01

Pos logit contributions
isher+0.106
eros+0.103
 Amen+0.099
ised+0.093
jected+0.090
Neg logit contributions
 levers-0.065
uits-0.058
 brushes-0.058
 ABC-0.056
 names-0.056
Token He
Token ID679
Feature activation+1.72e+00

Pos logit contributions
 levers+0.005
 brushes+0.004
 swirl+0.004
uits+0.004
 ABC+0.004
Neg logit contributions
isher-0.004
eros-0.004
over-0.003
 Amen-0.003
mer-0.003
Token couldn
Token ID3521
Feature activation-1.28e+00

Pos logit contributions
isher+0.038
eros+0.036
over+0.035
 Amen+0.034
mer+0.033
Neg logit contributions
 levers-0.034
 brushes-0.031
uits-0.029
 swirl-0.029
 ABC-0.029
Token't
Token ID470
Feature activation-1.94e+00

Pos logit contributions
 levers+0.022
 brushes+0.020
uits+0.019
 swirl+0.019
 ABC+0.018
Neg logit contributions
isher-0.031
eros-0.030
over-0.029
 Amen-0.029
mer-0.027
Token!
Token ID0
Feature activation-3.23e-01

Pos logit contributions
isher+0.105
eros+0.101
 Amen+0.097
jack+0.091
jected+0.091
Neg logit contributions
 levers-0.059
 ABC-0.053
 brushes-0.053
 names-0.052
 numbers-0.051
Token It
Token ID632
Feature activation+2.43e+00

Pos logit contributions
 levers+0.007
 brushes+0.006
 swirl+0.006
uits+0.006
 marks+0.006
Neg logit contributions
isher-0.006
 Amen-0.006
eros-0.006
over-0.006
date-0.005
Token was
Token ID373
Feature activation+1.80e-01

Pos logit contributions
isher+0.067
eros+0.064
over+0.061
 Amen+0.059
ised+0.057
Neg logit contributions
 levers-0.036
 brushes-0.032
 swirl-0.030
 ABC-0.030
 names-0.028
Token a
Token ID257
Feature activation+7.29e-01

Pos logit contributions
isher+0.004
eros+0.004
over+0.004
 Amen+0.004
mer+0.004
Neg logit contributions
 levers-0.003
 brushes-0.003
uits-0.003
 swirl-0.003
Ma-0.003
Token fancy
Token ID14996
Feature activation+3.80e+00

Pos logit contributions
isher+0.022
eros+0.021
ised+0.019
over+0.019
ishing+0.019
Neg logit contributions
 levers-0.009
 ABC-0.008
 brushes-0.008
 swirl-0.008
 names-0.007
Token wedding
Token ID10614
Feature activation+5.72e+00

Pos logit contributions
isher+0.084
jected+0.078
eros+0.076
ised+0.076
jack+0.072
Neg logit contributions
 ABC-0.073
 levers-0.066
 names-0.065
 brushes-0.065
 swirl-0.065
Token with
Token ID351
Feature activation+3.18e-01

Pos logit contributions
isher+0.144
eros+0.131
ised+0.128
jected+0.122
 Amen+0.119
Neg logit contributions
 ABC-0.087
 brushes-0.083
 levers-0.082
 names-0.079
 swirl-0.079
Token lots
Token ID6041
Feature activation-1.24e+00

Pos logit contributions
isher+0.007
eros+0.007
over+0.007
 Amen+0.007
ter+0.006
Neg logit contributions
 levers-0.006
 brushes-0.005
uits-0.005
Ma-0.005
 ABC-0.005
Token of
Token ID286
Feature activation-8.90e-01

Pos logit contributions
 levers+0.029
Ma+0.026
 brushes+0.026
uits+0.025
 ABC+0.025
Neg logit contributions
isher-0.022
eros-0.021
over-0.021
 Amen-0.019
mer-0.019
Token flowers
Token ID12734
Feature activation-1.77e+00

Pos logit contributions
 levers+0.016
 brushes+0.014
uits+0.014
Ma+0.014
 swirl+0.013
Neg logit contributions
isher-0.020
eros-0.020
 Amen-0.020
over-0.020
mer-0.018
Token and
Token ID290
Feature activation-1.08e+00

Pos logit contributions
 levers+0.031
 brushes+0.027
uits+0.026
 swirl+0.026
 ABC+0.025
Neg logit contributions
isher-0.043
eros-0.041
over-0.040
 Amen-0.040
mer-0.038
Token
Token ID241
Feature activation+5.33e-01

Pos logit contributions
isher+0.010
eros+0.010
over+0.009
 Amen+0.009
mer+0.009
Neg logit contributions
 levers-0.011
 brushes-0.010
uits-0.009
 swirl-0.009
 ABC-0.009
TokenThat
Token ID2504
Feature activation+1.95e+00

Pos logit contributions
isher+0.010
eros+0.010
over+0.009
 Amen+0.009
mer+0.009
Neg logit contributions
 levers-0.012
 brushes-0.011
uits-0.010
 swirl-0.010
Ma-0.010
Token was
Token ID373
Feature activation+1.64e+00

Pos logit contributions
isher+0.047
eros+0.046
over+0.045
 Amen+0.044
mer+0.043
Neg logit contributions
 levers-0.033
 brushes-0.029
uits-0.028
 swirl-0.027
 ABC-0.027
Token fun
Token ID1257
Feature activation+5.71e-01

Pos logit contributions
isher+0.035
over+0.034
eros+0.034
 Amen+0.033
ter+0.031
Neg logit contributions
 levers-0.033
 brushes-0.029
uits-0.028
 ABC-0.027
 swirl-0.027
Token!
Token ID0
Feature activation+1.38e+00

Pos logit contributions
isher+0.016
eros+0.015
 Amen+0.014
over+0.014
mer+0.014
Neg logit contributions
 levers-0.008
 brushes-0.007
uits-0.007
 swirl-0.007
 marks-0.007
Token Thank
Token ID6952
Feature activation+5.71e+00

Pos logit contributions
isher+0.031
eros+0.029
over+0.028
mer+0.027
ised+0.027
Neg logit contributions
 levers-0.026
Ma-0.023
 brushes-0.023
uits-0.023
 names-0.022
Token you
Token ID345
Feature activation+9.81e-01

Pos logit contributions
isher+0.142
jack+0.117
mer+0.117
penter+0.117
ishing+0.114
Neg logit contributions
Ma-0.097
 swirl-0.087
 levers-0.085
La-0.085
 Ma-0.082
Token for
Token ID329
Feature activation+2.46e+00

Pos logit contributions
isher+0.022
eros+0.021
over+0.020
 Amen+0.019
mer+0.019
Neg logit contributions
 levers-0.019
 brushes-0.017
uits-0.017
Ma-0.017
 swirl-0.016
Token helping
Token ID5742
Feature activation+7.73e-01

Pos logit contributions
isher+0.076
mer+0.074
ised+0.067
eros+0.066
over+0.065
Neg logit contributions
 swirl-0.028
uits-0.027
 levers-0.027
Ma-0.027
 Ma-0.026
Token me
Token ID502
Feature activation-8.77e-01

Pos logit contributions
isher+0.012
eros+0.012
 Amen+0.011
over+0.011
mer+0.010
Neg logit contributions
 levers-0.020
 brushes-0.018
 swirl-0.018
uits-0.018
 ABC-0.017
Token have
Token ID423
Feature activation+3.20e+00

Pos logit contributions
 levers+0.014
 brushes+0.012
 swirl+0.012
uits+0.012
 marks+0.012
Neg logit contributions
isher-0.023
eros-0.022
 Amen-0.021
over-0.020
mer-0.020
Token and
Token ID290
Feature activation+4.22e-01

Pos logit contributions
 levers+0.022
 brushes+0.019
 marks+0.018
uits+0.017
 swirl+0.017
Neg logit contributions
isher-0.053
eros-0.051
over-0.049
 Amen-0.049
mer-0.048
Token Daniel
Token ID7806
Feature activation-8.32e-01

Pos logit contributions
isher+0.009
eros+0.009
over+0.009
mer+0.008
 Amen+0.008
Neg logit contributions
 levers-0.009
 brushes-0.008
 swirl-0.007
uits-0.007
Ma-0.007
Token had
Token ID550
Feature activation+2.31e+00

Pos logit contributions
 levers+0.014
 brushes+0.012
 marks+0.012
uits+0.012
 names+0.012
Neg logit contributions
isher-0.021
eros-0.020
over-0.019
 Amen-0.019
mer-0.018
Token a
Token ID257
Feature activation+8.11e-01

Pos logit contributions
isher+0.061
eros+0.059
over+0.056
 Amen+0.056
mer+0.055
Neg logit contributions
 levers-0.036
 brushes-0.031
 swirl-0.029
uits-0.029
 ABC-0.029
Token big
Token ID1263
Feature activation+1.50e+00

Pos logit contributions
isher+0.020
eros+0.020
over+0.019
 Amen+0.019
mer+0.018
Neg logit contributions
 levers-0.013
 brushes-0.011
uits-0.011
 swirl-0.011
Ma-0.011
Token festival
Token ID10876
Feature activation+5.70e+00

Pos logit contributions
isher+0.031
eros+0.030
over+0.029
 Amen+0.028
mer+0.027
Neg logit contributions
 levers-0.031
 brushes-0.028
uits-0.027
 swirl-0.027
 ABC-0.027
Token to
Token ID284
Feature activation+2.43e+00

Pos logit contributions
isher+0.165
eros+0.163
 Amen+0.154
jected+0.149
ised+0.149
Neg logit contributions
 levers-0.063
 brushes-0.059
uits-0.057
 swirl-0.055
 names-0.052
Token go
Token ID467
Feature activation+2.92e+00

Pos logit contributions
isher+0.073
eros+0.072
jected+0.064
mer+0.064
ishing+0.062
Neg logit contributions
 names-0.032
 swirl-0.030
uits-0.030
 levers-0.029
 brushes-0.029
Token to
Token ID284
Feature activation+8.60e-01

Pos logit contributions
isher+0.094
eros+0.086
jected+0.084
ised+0.080
mer+0.080
Neg logit contributions
 levers-0.030
uits-0.029
 brushes-0.029
 names-0.027
 ABC-0.026
Token.
Token ID13
Feature activation-2.98e-01

Pos logit contributions
isher+0.027
eros+0.025
jected+0.024
over+0.024
mer+0.024
Neg logit contributions
 levers-0.011
 brushes-0.010
 swirl-0.009
 ABC-0.009
 names-0.009
Token They
Token ID1119
Feature activation-1.20e+00

Pos logit contributions
 levers+0.007
 blush+0.006
 brushes+0.006
 swirl+0.006
 marks+0.006
Neg logit contributions
isher-0.005
 Amen-0.005
eros-0.005
over-0.005
 Now-0.004
Token made
Token ID925
Feature activation-7.84e-01

Pos logit contributions
isher+0.055
eros+0.054
 Amen+0.051
over+0.051
mer+0.049
Neg logit contributions
 levers-0.042
 brushes-0.038
 swirl-0.036
uits-0.036
 marks-0.036
Token me
Token ID502
Feature activation-1.39e+00

Pos logit contributions
 levers+0.015
 brushes+0.014
 swirl+0.013
uits+0.013
 ABC+0.013
Neg logit contributions
isher-0.017
eros-0.017
over-0.016
 Amen-0.016
mer-0.015
Token so
Token ID523
Feature activation-4.50e-01

Pos logit contributions
 levers+0.027
 brushes+0.024
uits+0.023
 swirl+0.022
 ABC+0.022
Neg logit contributions
isher-0.031
eros-0.030
over-0.029
 Amen-0.029
mer-0.027
Token happy
Token ID3772
Feature activation+2.91e+00

Pos logit contributions
 levers+0.007
 brushes+0.006
 swirl+0.006
 marks+0.006
 ABC+0.006
Neg logit contributions
isher-0.012
eros-0.012
over-0.011
 Amen-0.011
date-0.011
Token.
Token ID13
Feature activation+2.18e+00

Pos logit contributions
isher+0.072
eros+0.065
 Amen+0.064
over+0.063
mer+0.061
Neg logit contributions
 levers-0.050
 swirl-0.045
 marks-0.044
 brushes-0.044
 ABC-0.043
Token Thank
Token ID6952
Feature activation+5.68e+00

Pos logit contributions
isher+0.048
over+0.044
mer+0.044
ised+0.043
eros+0.043
Neg logit contributions
 levers-0.039
 ABC-0.038
 names-0.038
Ma-0.037
 brushes-0.037
Token you
Token ID345
Feature activation+7.62e-01

Pos logit contributions
isher+0.158
penter+0.139
jack+0.133
bank+0.132
mer+0.131
Neg logit contributions
Ma-0.075
 swirl-0.068
 names-0.068
 numbers-0.066
La-0.065
Token for
Token ID329
Feature activation+2.25e+00

Pos logit contributions
isher+0.015
eros+0.014
over+0.013
 Amen+0.013
mer+0.012
Neg logit contributions
 levers-0.017
 brushes-0.015
uits-0.015
 swirl-0.015
 ABC-0.015
Token restoring
Token ID25646
Feature activation+9.31e-01

Pos logit contributions
mer+0.069
isher+0.068
over+0.062
ider+0.060
eros+0.060
Neg logit contributions
 swirl-0.030
 numbers-0.027
 marks-0.025
 th-0.024
Ma-0.023
Token my
Token ID616
Feature activation+1.30e-01

Pos logit contributions
isher+0.019
eros+0.018
 Amen+0.018
over+0.017
mer+0.017
Neg logit contributions
 levers-0.020
 brushes-0.018
 swirl-0.017
 marks-0.017
 ABC-0.017
Token life
Token ID1204
Feature activation+1.54e+00

Pos logit contributions
isher+0.003
over+0.003
 Amen+0.003
eros+0.003
olph+0.003
Neg logit contributions
 levers-0.002
 marks-0.002
 ABC-0.002
 names-0.002
 swirl-0.002
Token he
Token ID339
Feature activation+8.98e-01

Pos logit contributions
isher+0.003
over+0.003
eros+0.003
ter+0.003
 Amen+0.003
Neg logit contributions
 levers-0.004
 brushes-0.003
uits-0.003
Ma-0.003
 magn-0.003
Token was
Token ID373
Feature activation+5.98e-01

Pos logit contributions
isher+0.019
eros+0.019
over+0.018
 Amen+0.018
mer+0.017
Neg logit contributions
 levers-0.018
 brushes-0.016
uits-0.016
 swirl-0.015
Ma-0.015
Token going
Token ID1016
Feature activation+2.04e+00

Pos logit contributions
isher+0.013
eros+0.013
over+0.012
 Amen+0.012
mer+0.012
Neg logit contributions
 levers-0.012
 brushes-0.010
uits-0.010
 swirl-0.010
 ABC-0.010
Token to
Token ID284
Feature activation+2.62e-01

Pos logit contributions
isher+0.052
eros+0.051
 Amen+0.049
over+0.049
mer+0.047
Neg logit contributions
 levers-0.034
 brushes-0.029
uits-0.028
 swirl-0.027
 ABC-0.027
Token a
Token ID257
Feature activation+1.39e+00

Pos logit contributions
isher+0.006
eros+0.006
over+0.006
 Amen+0.006
mer+0.005
Neg logit contributions
 levers-0.005
 brushes-0.004
uits-0.004
 swirl-0.004
 ABC-0.004
Token special
Token ID2041
Feature activation+5.66e+00

Pos logit contributions
isher+0.031
eros+0.030
over+0.029
 Amen+0.028
ised+0.027
Neg logit contributions
 levers-0.026
 brushes-0.024
 swirl-0.024
 ABC-0.024
Ma-0.023
Token party
Token ID2151
Feature activation+4.29e+00

Pos logit contributions
agged+0.125
isher+0.125
jected+0.121
eros+0.119
apped+0.114
Neg logit contributions
 ABC-0.099
 swirl-0.099
 levers-0.095
 brushes-0.093
 numbers-0.090
Token.
Token ID13
Feature activation-1.77e-01

Pos logit contributions
isher+0.118
eros+0.114
 Amen+0.109
ised+0.104
jected+0.100
Neg logit contributions
 levers-0.061
uits-0.054
 marks-0.054
 brushes-0.052
 swirl-0.052
Token He
Token ID679
Feature activation+1.06e+00

Pos logit contributions
 levers+0.004
 brushes+0.004
 swirl+0.004
 switches+0.004
 blush+0.004
Neg logit contributions
eros-0.003
over-0.003
isher-0.003
 Amen-0.003
 Now-0.003
Token was
Token ID373
Feature activation-1.75e-01

Pos logit contributions
isher+0.024
eros+0.023
over+0.022
 Amen+0.022
mer+0.021
Neg logit contributions
 levers-0.021
 brushes-0.019
 swirl-0.017
uits-0.017
 ABC-0.017
Token so
Token ID523
Feature activation-2.49e-01

Pos logit contributions
 levers+0.003
 brushes+0.003
 swirl+0.002
 ABC+0.002
uits+0.002
Neg logit contributions
isher-0.004
eros-0.004
over-0.004
 Amen-0.004
mer-0.004
Token to
Token ID284
Feature activation-2.72e-01

Pos logit contributions
 levers+0.018
 brushes+0.016
uits+0.016
Ma+0.015
 swirl+0.015
Neg logit contributions
over-0.015
eros-0.014
 Amen-0.014
isher-0.014
 reunited-0.014
Token cry
Token ID3960
Feature activation+1.40e-01

Pos logit contributions
 levers+0.005
 brushes+0.004
uits+0.004
Ma+0.004
 switches+0.004
Neg logit contributions
 Amen-0.006
 reunited-0.006
isher-0.006
over-0.006
eros-0.006
Token but
Token ID475
Feature activation-1.23e+00

Pos logit contributions
isher+0.003
over+0.003
eros+0.003
 Amen+0.003
mer+0.003
Neg logit contributions
 levers-0.003
 brushes-0.003
uits-0.002
Ma-0.002
 swirl-0.002
Token then
Token ID788
Feature activation-4.14e-01

Pos logit contributions
 levers+0.022
 brushes+0.020
 swirl+0.019
 blush+0.018
Ma+0.018
Neg logit contributions
isher-0.030
eros-0.029
 Amen-0.028
over-0.027
mer-0.027
Token a
Token ID257
Feature activation+1.86e+00

Pos logit contributions
 levers+0.007
 brushes+0.006
uits+0.006
 ABC+0.006
 swirl+0.006
Neg logit contributions
isher-0.010
eros-0.009
over-0.009
 Amen-0.009
mer-0.009
Token magical
Token ID10883
Feature activation+5.64e+00

Pos logit contributions
isher+0.051
eros+0.048
over+0.046
eday+0.046
ishing+0.044
Neg logit contributions
 levers-0.029
 swirl-0.026
 brushes-0.024
 ABC-0.023
 numbers-0.023
Token thing
Token ID1517
Feature activation+2.52e+00

Pos logit contributions
isher+0.138
eday+0.127
eros+0.125
jected+0.124
Deal+0.123
Neg logit contributions
 swirl-0.091
 levers-0.091
 brushes-0.084
 magn-0.083
 marks-0.082
Token happened
Token ID3022
Feature activation+1.53e+00

Pos logit contributions
isher+0.060
eros+0.058
over+0.056
 Amen+0.055
mer+0.054
Neg logit contributions
 levers-0.045
 brushes-0.039
uits-0.038
 ABC-0.037
 swirl-0.037
Token.
Token ID13
Feature activation-5.42e-01

Pos logit contributions
isher+0.037
eros+0.036
over+0.034
 Amen+0.034
mer+0.032
Neg logit contributions
 levers-0.027
 brushes-0.023
uits-0.023
 marks-0.023
 swirl-0.023
Token A
Token ID317
Feature activation+5.03e-01

Pos logit contributions
 levers+0.010
 brushes+0.009
 swirl+0.008
Ma+0.008
 ABC+0.008
Neg logit contributions
isher-0.014
eros-0.013
over-0.012
mer-0.012
 Amen-0.012
Token big
Token ID1263
Feature activation+1.03e+00

Pos logit contributions
isher+0.012
eros+0.012
over+0.011
 Amen+0.011
eday+0.011
Neg logit contributions
 levers-0.009
 swirl-0.008
 brushes-0.008
 ABC-0.008
 marks-0.007
Token always
Token ID1464
Feature activation+1.00e-02

Pos logit contributions
 levers+0.052
 brushes+0.042
 swirl+0.042
 marks+0.041
 switches+0.041
Neg logit contributions
isher-0.089
eros-0.088
over-0.084
 Amen-0.082
ugg-0.081
Token what
Token ID644
Feature activation-9.92e-01

Pos logit contributions
isher+0.000
eros+0.000
over+0.000
 Amen+0.000
mer+0.000
Neg logit contributions
 levers-0.000
 brushes-0.000
uits-0.000
 swirl-0.000
 marks-0.000
Token they
Token ID484
Feature activation-8.26e-02

Pos logit contributions
 levers+0.025
uits+0.023
Ma+0.022
 brushes+0.022
 swirl+0.022
Neg logit contributions
isher-0.015
eros-0.015
over-0.014
 Amen-0.014
mer-0.013
Token seem
Token ID1283
Feature activation-2.59e+00

Pos logit contributions
 levers+0.001
 brushes+0.001
uits+0.001
 swirl+0.001
 ABC+0.001
Neg logit contributions
isher-0.002
eros-0.002
over-0.002
 Amen-0.002
mer-0.002
Token.
Token ID13
Feature activation+1.01e+00

Pos logit contributions
 levers+0.052
Ma+0.050
 brushes+0.047
uits+0.046
 blush+0.045
Neg logit contributions
isher-0.050
over-0.049
eros-0.049
mer-0.048
 Amen-0.048
Token Thank
Token ID6952
Feature activation+5.63e+00

Pos logit contributions
isher+0.025
eros+0.023
over+0.022
mer+0.022
ishing+0.021
Neg logit contributions
 levers-0.018
 names-0.016
 brushes-0.016
 switches-0.016
Ma-0.016
Token you
Token ID345
Feature activation+3.28e-01

Pos logit contributions
isher+0.158
penter+0.142
jack+0.140
boat+0.137
ase+0.133
Neg logit contributions
 names-0.066
Ma-0.064
La-0.058
 numbers-0.057
 anything-0.057
Token for
Token ID329
Feature activation+1.76e+00

Pos logit contributions
isher+0.006
eros+0.006
over+0.005
 Amen+0.005
mer+0.005
Neg logit contributions
 levers-0.008
 brushes-0.007
uits-0.007
 swirl-0.007
 ABC-0.007
Token being
Token ID852
Feature activation+1.93e+00

Pos logit contributions
isher+0.053
mer+0.053
over+0.048
eros+0.047
ase+0.046
Neg logit contributions
 levers-0.023
 numbers-0.021
 swirl-0.021
 marks-0.020
 switches-0.020
Token brave
Token ID14802
Feature activation+5.16e-01

Pos logit contributions
isher+0.054
eros+0.051
ugg+0.049
ase+0.047
mer+0.047
Neg logit contributions
 levers-0.026
 names-0.022
 brushes-0.021
 switches-0.021
 swirl-0.021
Token and
Token ID290
Feature activation+1.57e+00

Pos logit contributions
isher+0.014
eros+0.014
 Amen+0.014
over+0.013
boat+0.013
Neg logit contributions
 levers-0.007
 brushes-0.006
 marks-0.006
 names-0.006
uits-0.006
Token end
Token ID886
Feature activation+2.27e+00

Pos logit contributions
isher+0.029
eros+0.028
over+0.028
 Amen+0.027
mer+0.026
Neg logit contributions
 levers-0.019
 brushes-0.017
 swirl-0.016
 ABC-0.016
 names-0.016
Token of
Token ID286
Feature activation+1.35e+00

Pos logit contributions
isher+0.051
eros+0.049
 Amen+0.047
over+0.047
mer+0.044
Neg logit contributions
 levers-0.044
 brushes-0.039
uits-0.038
 swirl-0.037
Ma-0.037
Token our
Token ID674
Feature activation+9.37e-01

Pos logit contributions
isher+0.044
ider+0.042
eros+0.040
mer+0.040
ager+0.040
Neg logit contributions
 levers-0.011
 swirl-0.010
uits-0.009
 numbers-0.009
Ma-0.009
Token story
Token ID1621
Feature activation+1.71e+00

Pos logit contributions
isher+0.020
 Amen+0.019
eros+0.019
over+0.018
boat+0.018
Neg logit contributions
 levers-0.019
 brushes-0.018
 ABC-0.017
 names-0.017
 marks-0.017
Token!
Token ID0
Feature activation+2.98e+00

Pos logit contributions
isher+0.041
eros+0.039
 Amen+0.038
over+0.036
mer+0.035
Neg logit contributions
 levers-0.031
 brushes-0.028
uits-0.027
 swirl-0.026
 ABC-0.026
Token Thank
Token ID6952
Feature activation+5.63e+00

Pos logit contributions
isher+0.080
eros+0.074
over+0.071
mer+0.070
 Amen+0.068
Neg logit contributions
 levers-0.045
Ma-0.041
 brushes-0.039
uits-0.039
 ABC-0.038
Token you
Token ID345
Feature activation+8.54e-01

Pos logit contributions
isher+0.137
mer+0.111
eros+0.109
jack+0.109
penter+0.109
Neg logit contributions
Ma-0.099
 swirl-0.094
 names-0.090
 numbers-0.090
 levers-0.089
Token for
Token ID329
Feature activation+2.56e+00

Pos logit contributions
isher+0.017
eros+0.016
over+0.015
 Amen+0.015
mer+0.014
Neg logit contributions
 levers-0.019
 brushes-0.017
uits-0.017
Ma-0.016
 swirl-0.016
Token listening
Token ID8680
Feature activation+9.62e-01

Pos logit contributions
isher+0.079
mer+0.078
ider+0.070
eros+0.070
over+0.070
Neg logit contributions
 swirl-0.028
 numbers-0.027
 levers-0.026
Ma-0.025
 Ma-0.025
Token.
Token ID13
Feature activation+2.96e+00

Pos logit contributions
isher+0.023
eros+0.023
over+0.022
 Amen+0.022
mer+0.021
Neg logit contributions
 levers-0.017
 brushes-0.015
uits-0.014
 swirl-0.014
 ABC-0.014
Token<|endoftext|>
Token ID50256
Feature activation+3.55e+00

Pos logit contributions
isher+0.088
over+0.078
mer+0.077
ishing+0.077
eros+0.077
Neg logit contributions
 levers-0.036
Ma-0.035
 ABC-0.032
 brushes-0.031
uits-0.030
TokenDear
Token ID20266
Feature activation+2.99e+00

Pos logit contributions
isher+0.038
eros+0.037
over+0.035
 Amen+0.035
mer+0.033
Neg logit contributions
 levers-0.043
 brushes-0.039
uits-0.037
 swirl-0.037
Ma-0.037
Token Sara
Token ID24799
Feature activation-1.02e+00

Pos logit contributions
isher+0.076
eros+0.073
over+0.071
 Amen+0.070
mer+0.068
Neg logit contributions
 levers-0.049
 brushes-0.043
uits-0.041
 swirl-0.040
 ABC-0.040
Token,
Token ID11
Feature activation+4.28e-01

Pos logit contributions
 levers+0.021
 brushes+0.019
 swirl+0.018
uits+0.018
 switches+0.017
Neg logit contributions
eros-0.021
isher-0.021
over-0.021
 Amen-0.020
mer-0.019
Token
Token ID198
Feature activation+1.08e+00

Pos logit contributions
isher+0.009
eros+0.008
 Amen+0.008
over+0.008
mer+0.008
Neg logit contributions
 levers-0.009
 brushes-0.008
uits-0.008
 swirl-0.008
 ABC-0.008
Token
Token ID198
Feature activation+1.71e+00

Pos logit contributions
isher+0.028
eros+0.026
over+0.025
mer+0.025
 Amen+0.024
Neg logit contributions
 levers-0.018
Ma-0.017
 brushes-0.016
uits-0.016
 ABC-0.015
TokenThank
Token ID10449
Feature activation+5.62e+00

Pos logit contributions
isher+0.041
eros+0.038
over+0.035
mer+0.035
 Amen+0.035
Neg logit contributions
 levers-0.032
Ma-0.030
 brushes-0.029
uits-0.028
 ABC-0.027
Token you
Token ID345
Feature activation+4.70e-01

Pos logit contributions
isher+0.133
penter+0.118
 gol+0.116
bank+0.115
boat+0.114
Neg logit contributions
Ma-0.100
La-0.088
 blush-0.087
 brushes-0.086
 levers-0.086
Token for
Token ID329
Feature activation+2.09e+00

Pos logit contributions
eros+0.008
isher+0.008
over+0.008
 Amen+0.008
 reunited+0.007
Neg logit contributions
 levers-0.011
 brushes-0.010
 swirl-0.010
 switches-0.010
uits-0.010
Token your
Token ID534
Feature activation+1.84e+00

Pos logit contributions
mer+0.068
isher+0.067
over+0.062
ised+0.060
eros+0.060
Neg logit contributions
 numbers-0.022
 swirl-0.021
 levers-0.021
Ma-0.019
 brushes-0.019
Token lovely
Token ID14081
Feature activation+1.43e+00

Pos logit contributions
isher+0.040
eros+0.038
over+0.037
mer+0.036
 Amen+0.036
Neg logit contributions
 levers-0.037
 brushes-0.034
 ABC-0.033
 marks-0.032
 swirl-0.032
Token letter
Token ID3850
Feature activation+3.56e+00

Pos logit contributions
isher+0.032
eros+0.030
over+0.029
 Amen+0.029
mer+0.028
Neg logit contributions
 levers-0.028
 brushes-0.026
 marks-0.024
 swirl-0.024
 ABC-0.024
Token into
Token ID656
Feature activation-3.13e+00

Pos logit contributions
 levers+0.050
 brushes+0.047
Ma+0.046
uits+0.045
 ABC+0.045
Neg logit contributions
isher-0.037
eros-0.035
mer-0.033
over-0.033
well-0.032
Token pieces
Token ID5207
Feature activation-2.23e+00

Pos logit contributions
 levers+0.055
 brushes+0.048
uits+0.046
 swirl+0.045
 ABC+0.045
Neg logit contributions
isher-0.076
eros-0.074
over-0.071
 Amen-0.071
mer-0.068
Token.
Token ID13
Feature activation-1.67e+00

Pos logit contributions
 levers+0.044
 brushes+0.039
uits+0.038
 swirl+0.038
 ABC+0.037
Neg logit contributions
isher-0.049
eros-0.047
over-0.045
 Amen-0.045
mer-0.043
Token Ben
Token ID3932
Feature activation-4.53e+00

Pos logit contributions
 levers+0.036
 brushes+0.032
uits+0.031
 swirl+0.030
 ABC+0.030
Neg logit contributions
isher-0.034
eros-0.033
over-0.032
 Amen-0.031
mer-0.030
Token and
Token ID290
Feature activation+2.68e-01

Pos logit contributions
 levers+0.097
uits+0.093
Ma+0.090
 brushes+0.089
 ABC+0.088
Neg logit contributions
eros-0.086
 Now-0.076
over-0.074
isher-0.074
mer-0.074
Token Mia
Token ID32189
Feature activation-6.79e+00

Pos logit contributions
isher+0.008
eros+0.007
over+0.007
 Amen+0.007
mer+0.007
Neg logit contributions
 levers-0.004
 brushes-0.003
 swirl-0.003
uits-0.003
Ma-0.003
Token are
Token ID389
Feature activation-1.43e+00

Pos logit contributions
 levers+0.085
uits+0.073
 ABC+0.071
 brushes+0.071
Ma+0.069
Neg logit contributions
eros-0.183
isher-0.182
over-0.175
 Amen-0.173
ter-0.172
Token very
Token ID845
Feature activation-1.16e+00

Pos logit contributions
 levers+0.027
 brushes+0.024
uits+0.023
 swirl+0.023
 ABC+0.023
Neg logit contributions
isher-0.032
eros-0.031
over-0.030
 Amen-0.030
mer-0.028
Token sad
Token ID6507
Feature activation-4.88e-01

Pos logit contributions
 levers+0.017
 brushes+0.015
 marks+0.014
 sweat+0.013
 swirl+0.013
Neg logit contributions
isher-0.033
eros-0.031
over-0.030
 Amen-0.030
date-0.030
Token.
Token ID13
Feature activation-1.50e+00

Pos logit contributions
 levers+0.009
 brushes+0.007
uits+0.007
 swirl+0.007
 ABC+0.007
Neg logit contributions
isher-0.012
eros-0.012
over-0.011
 Amen-0.011
mer-0.011
Token They
Token ID1119
Feature activation-2.15e+00

Pos logit contributions
 levers+0.035
 brushes+0.032
uits+0.031
 swirl+0.031
 ABC+0.030
Neg logit contributions
isher-0.027
eros-0.026
over-0.025
 Amen-0.025
mer-0.024
Token and
Token ID290
Feature activation-9.23e-01

Pos logit contributions
 levers+0.029
 brushes+0.026
 ABC+0.024
Ma+0.024
uits+0.024
Neg logit contributions
isher-0.031
eros-0.030
over-0.030
 Amen-0.028
mer-0.028
Token breaks
Token ID9457
Feature activation-1.74e+00

Pos logit contributions
 levers+0.016
uits+0.015
 ABC+0.014
 brushes+0.014
Ma+0.014
Neg logit contributions
isher-0.021
eros-0.021
 Amen-0.020
ter-0.019
over-0.019
Token.
Token ID13
Feature activation-1.49e+00

Pos logit contributions
 levers+0.037
 brushes+0.034
uits+0.033
 ABC+0.033
Ma+0.032
Neg logit contributions
isher-0.035
eros-0.034
over-0.032
ter-0.031
mer-0.030
Token Sam
Token ID3409
Feature activation-5.13e+00

Pos logit contributions
 levers+0.032
 brushes+0.028
uits+0.027
 swirl+0.027
 ABC+0.027
Neg logit contributions
isher-0.031
eros-0.030
over-0.029
 Amen-0.028
mer-0.027
Token and
Token ID290
Feature activation+4.61e-02

Pos logit contributions
 levers+0.102
uits+0.100
Ma+0.089
 brushes+0.088
 ABC+0.087
Neg logit contributions
eros-0.106
 alone-0.096
isher-0.094
jected-0.094
ter-0.093
Token Mia
Token ID32189
Feature activation-6.65e+00

Pos logit contributions
isher+0.001
eros+0.001
over+0.001
 Amen+0.001
mer+0.001
Neg logit contributions
 levers-0.001
 brushes-0.001
uits-0.001
 swirl-0.001
 ABC-0.001
Token are
Token ID389
Feature activation-1.36e+00

Pos logit contributions
 levers+0.087
uits+0.075
 ABC+0.071
Ma+0.070
 brushes+0.070
Neg logit contributions
eros-0.175
isher-0.174
over-0.169
ter-0.168
 Amen-0.167
Token shocked
Token ID11472
Feature activation-3.41e-02

Pos logit contributions
 levers+0.027
 brushes+0.024
uits+0.023
 ABC+0.023
Ma+0.022
Neg logit contributions
isher-0.030
eros-0.029
over-0.028
 Amen-0.027
mer-0.026
Token.
Token ID13
Feature activation-1.68e+00

Pos logit contributions
 levers+0.001
 brushes+0.001
uits+0.001
 ABC+0.001
Ma+0.001
Neg logit contributions
isher-0.001
eros-0.001
over-0.001
 Amen-0.001
mer-0.001
Token They
Token ID1119
Feature activation-2.47e+00

Pos logit contributions
 levers+0.041
uits+0.037
 brushes+0.037
 swirl+0.037
 ABC+0.036
Neg logit contributions
eros-0.027
isher-0.026
over-0.025
 Amen-0.025
mer-0.024
Token look
Token ID804
Feature activation-2.42e+00

Pos logit contributions
 levers+0.041
 ABC+0.040
Ma+0.039
uits+0.038
eways+0.034
Neg logit contributions
 Amen-0.051
eros-0.050
isher-0.050
 reunited-0.049
 alone-0.049
Token and
Token ID290
Feature activation-1.73e+00

Pos logit contributions
 levers+0.080
 brushes+0.072
Ma+0.068
 ABC+0.068
uits+0.068
Neg logit contributions
isher-0.091
eros-0.088
over-0.086
 Amen-0.083
mer-0.081
Token pulls
Token ID16194
Feature activation-2.09e+00

Pos logit contributions
 levers+0.028
uits+0.025
 ABC+0.024
 brushes+0.024
Ma+0.024
Neg logit contributions
isher-0.042
eros-0.042
 Amen-0.039
over-0.038
penter-0.037
Token.
Token ID13
Feature activation-1.76e+00

Pos logit contributions
 levers+0.044
 brushes+0.042
 ABC+0.041
uits+0.040
Ma+0.039
Neg logit contributions
isher-0.042
eros-0.040
over-0.037
ter-0.036
mer-0.035
Token Tim
Token ID5045
Feature activation-4.24e+00

Pos logit contributions
 levers+0.038
 brushes+0.034
uits+0.033
 swirl+0.033
 ABC+0.033
Neg logit contributions
isher-0.035
eros-0.034
over-0.032
 Amen-0.032
mer-0.030
Token and
Token ID290
Feature activation-4.55e-01

Pos logit contributions
 levers+0.084
uits+0.077
 brushes+0.073
Ma+0.072
 ABC+0.071
Neg logit contributions
eros-0.091
isher-0.087
 Now-0.079
jected-0.078
mer-0.077
Token Mia
Token ID32189
Feature activation-6.62e+00

Pos logit contributions
 levers+0.008
uits+0.007
 brushes+0.007
 ABC+0.007
 swirl+0.007
Neg logit contributions
eros-0.011
isher-0.010
 Amen-0.010
over-0.009
mer-0.009
Token are
Token ID389
Feature activation-1.20e+00

Pos logit contributions
 levers+0.094
 ABC+0.083
uits+0.081
Ma+0.081
 brushes+0.079
Neg logit contributions
isher-0.167
eros-0.164
 Amen-0.156
over-0.156
well-0.155
Token scared
Token ID12008
Feature activation-1.27e+00

Pos logit contributions
 levers+0.023
 brushes+0.020
uits+0.019
 swirl+0.019
 ABC+0.019
Neg logit contributions
isher-0.027
eros-0.026
over-0.026
 Amen-0.025
mer-0.024
Token.
Token ID13
Feature activation-1.86e+00

Pos logit contributions
 levers+0.025
 brushes+0.022
uits+0.021
 swirl+0.021
 ABC+0.021
Neg logit contributions
isher-0.028
eros-0.027
over-0.026
 Amen-0.026
mer-0.025
Token They
Token ID1119
Feature activation-1.96e+00

Pos logit contributions
 levers+0.049
uits+0.044
 swirl+0.044
 ABC+0.044
 brushes+0.044
Neg logit contributions
eros-0.027
over-0.024
 Amen-0.024
isher-0.024
 Now-0.024
Token let
Token ID1309
Feature activation-6.36e-01

Pos logit contributions
 levers+0.033
 ABC+0.033
Ma+0.032
uits+0.030
 brushes+0.029
Neg logit contributions
 Amen-0.041
isher-0.041
eros-0.040
 hunter-0.039
ar-0.038
Token no
Token ID645
Feature activation-9.90e-01

Pos logit contributions
 levers+0.033
Ma+0.030
uits+0.029
 ABC+0.029
 blush+0.029
Neg logit contributions
isher-0.039
eros-0.037
over-0.036
ter-0.034
 Amen-0.034
Token lock
Token ID5793
Feature activation-1.25e+00

Pos logit contributions
 levers+0.016
 brushes+0.014
uits+0.014
 swirl+0.013
 ABC+0.013
Neg logit contributions
isher-0.025
eros-0.024
over-0.023
 Amen-0.023
mer-0.022
Token.
Token ID13
Feature activation-1.92e+00

Pos logit contributions
 levers+0.026
 brushes+0.023
Ma+0.023
 swirl+0.022
uits+0.022
Neg logit contributions
isher-0.025
eros-0.025
over-0.024
mer-0.022
ter-0.022
Token Tom
Token ID4186
Feature activation-4.58e+00

Pos logit contributions
 levers+0.038
 brushes+0.034
uits+0.032
 ABC+0.032
 swirl+0.032
Neg logit contributions
isher-0.043
eros-0.041
over-0.039
 Amen-0.039
mer-0.038
Token and
Token ID290
Feature activation+4.47e-01

Pos logit contributions
 levers+0.085
 brushes+0.074
uits+0.074
 swirl+0.073
Ma+0.072
Neg logit contributions
eros-0.103
isher-0.102
over-0.097
mer-0.094
 Amen-0.092
Token Mia
Token ID32189
Feature activation-6.61e+00

Pos logit contributions
isher+0.013
over+0.012
eros+0.012
 Amen+0.012
mer+0.011
Neg logit contributions
 levers-0.007
 brushes-0.006
 swirl-0.005
Ma-0.005
 marks-0.005
Token are
Token ID389
Feature activation-1.11e+00

Pos logit contributions
 levers+0.077
uits+0.061
 brushes+0.061
Ma+0.060
 swirl+0.059
Neg logit contributions
isher-0.190
eros-0.187
over-0.183
 Amen-0.181
mer-0.176
Token scared
Token ID12008
Feature activation-1.30e+00

Pos logit contributions
 levers+0.019
 brushes+0.017
 marks+0.016
 swirl+0.016
uits+0.015
Neg logit contributions
isher-0.028
eros-0.027
over-0.026
 Amen-0.026
mer-0.025
Token and
Token ID290
Feature activation-1.69e+00

Pos logit contributions
 levers+0.028
 brushes+0.025
uits+0.024
 swirl+0.024
 ABC+0.023
Neg logit contributions
isher-0.027
eros-0.026
over-0.025
 Amen-0.024
mer-0.023
Token sad
Token ID6507
Feature activation-1.83e-01

Pos logit contributions
 levers+0.032
 brushes+0.028
 marks+0.026
 swirl+0.025
 names+0.025
Neg logit contributions
isher-0.041
eros-0.039
over-0.039
date-0.037
 Amen-0.037
Token.
Token ID13
Feature activation-1.57e+00

Pos logit contributions
 levers+0.003
 brushes+0.003
 marks+0.003
 swirl+0.003
 ABC+0.003
Neg logit contributions
isher-0.005
eros-0.004
over-0.004
 Amen-0.004
mer-0.004
Token had
Token ID550
Feature activation-8.89e-01

Pos logit contributions
 levers+0.028
 brushes+0.025
uits+0.023
 swirl+0.023
 switches+0.022
Neg logit contributions
eros-0.031
isher-0.030
over-0.030
 Amen-0.028
mer-0.027
Token hamm
Token ID25755
Feature activation-3.41e+00

Pos logit contributions
 levers+0.015
 brushes+0.013
uits+0.013
 swirl+0.013
Ma+0.013
Neg logit contributions
isher-0.022
eros-0.021
over-0.020
 Amen-0.020
mer-0.019
Tokeners
Token ID364
Feature activation-3.84e+00

Pos logit contributions
 levers+0.095
 brushes+0.088
Ma+0.088
 swirl+0.086
 blush+0.086
Neg logit contributions
isher-0.047
eros-0.041
over-0.041
mer-0.036
boat-0.036
Token,
Token ID11
Feature activation-4.80e+00

Pos logit contributions
 levers+0.064
 brushes+0.056
uits+0.053
 swirl+0.052
 marks+0.051
Neg logit contributions
isher-0.097
eros-0.095
 Amen-0.093
over-0.090
mer-0.085
Token screw
Token ID9580
Feature activation-3.48e+00

Pos logit contributions
 levers+0.073
Ma+0.069
uits+0.068
 ABC+0.067
 blush+0.065
Neg logit contributions
isher-0.116
eros-0.102
penter-0.101
ised-0.100
over-0.099
Tokendrivers
Token ID36702
Feature activation-6.58e+00

Pos logit contributions
 levers+0.066
 brushes+0.059
Ma+0.059
 swirl+0.057
uits+0.057
Neg logit contributions
isher-0.077
eros-0.074
over-0.071
mer-0.067
penter-0.066
Token,
Token ID11
Feature activation-5.30e+00

Pos logit contributions
 levers+0.130
Ma+0.114
 brushes+0.113
 swirl+0.112
 blush+0.109
Neg logit contributions
isher-0.140
eros-0.134
over-0.133
mer-0.123
penter-0.122
Token pl
Token ID458
Feature activation-1.42e+00

Pos logit contributions
 levers+0.089
Ma+0.082
uits+0.079
 ABC+0.078
 blush+0.078
Neg logit contributions
isher-0.121
eros-0.110
penter-0.107
ter-0.107
over-0.106
Tokeniers
Token ID3183
Feature activation-4.31e+00

Pos logit contributions
 levers+0.032
 brushes+0.029
uits+0.028
 swirl+0.028
 ABC+0.027
Neg logit contributions
isher-0.027
eros-0.026
over-0.025
 Amen-0.025
mer-0.023
Token,
Token ID11
Feature activation-5.77e+00

Pos logit contributions
 levers+0.083
 brushes+0.073
 swirl+0.070
uits+0.070
Ma+0.069
Neg logit contributions
isher-0.096
eros-0.093
over-0.090
 Amen-0.086
mer-0.085
Token and
Token ID290
Feature activation-2.16e+00

Pos logit contributions
 levers+0.100
Ma+0.091
uits+0.090
 blush+0.088
 ABC+0.088
Neg logit contributions
isher-0.128
eros-0.116
ter-0.113
penter-0.112
over-0.111
Token the
Token ID262
Feature activation-1.66e+00

Pos logit contributions
 levers+0.012
 brushes+0.010
 swirl+0.010
uits+0.009
 marks+0.009
Neg logit contributions
isher-0.021
over-0.020
eros-0.020
 Amen-0.020
mer-0.019
Token tube
Token ID12403
Feature activation-9.68e-01

Pos logit contributions
 levers+0.036
 brushes+0.032
uits+0.032
Ma+0.032
 ABC+0.031
Neg logit contributions
isher-0.033
eros-0.031
over-0.030
 Amen-0.029
mer-0.028
Token.
Token ID13
Feature activation-1.10e+00

Pos logit contributions
 levers+0.015
 brushes+0.013
uits+0.012
 swirl+0.012
 marks+0.012
Neg logit contributions
isher-0.026
eros-0.025
 Amen-0.025
over-0.024
mer-0.022
Token Ben
Token ID3932
Feature activation-4.36e+00

Pos logit contributions
 levers+0.024
 brushes+0.021
uits+0.020
 swirl+0.020
 ABC+0.020
Neg logit contributions
isher-0.022
eros-0.021
over-0.021
 Amen-0.020
mer-0.019
Token and
Token ID290
Feature activation+2.14e-01

Pos logit contributions
 levers+0.091
uits+0.083
 brushes+0.083
Ma+0.081
 ABC+0.079
Neg logit contributions
eros-0.087
mer-0.079
isher-0.078
over-0.077
 Now-0.075
Token Mia
Token ID32189
Feature activation-6.56e+00

Pos logit contributions
isher+0.006
eros+0.006
over+0.006
 Amen+0.006
mer+0.005
Neg logit contributions
 levers-0.003
 brushes-0.002
 swirl-0.002
uits-0.002
Ma-0.002
Token let
Token ID1309
Feature activation-6.75e-01

Pos logit contributions
 levers+0.089
 ABC+0.078
 brushes+0.077
uits+0.077
Ma+0.075
Neg logit contributions
eros-0.167
isher-0.164
 Amen-0.159
ter-0.159
mer-0.158
Token go
Token ID467
Feature activation+5.52e-01

Pos logit contributions
 levers+0.016
 brushes+0.015
uits+0.014
 blush+0.014
 ABC+0.014
Neg logit contributions
eros-0.011
over-0.011
ter-0.011
isher-0.011
bye-0.010
Token of
Token ID286
Feature activation-1.20e+00

Pos logit contributions
isher+0.013
eros+0.013
over+0.012
 Amen+0.012
ised+0.012
Neg logit contributions
 levers-0.010
 brushes-0.009
uits-0.009
 swirl-0.008
 marks-0.008
Token the
Token ID262
Feature activation-1.43e+00

Pos logit contributions
 levers+0.023
 brushes+0.020
uits+0.020
Ma+0.020
 ABC+0.020
Neg logit contributions
eros-0.026
isher-0.026
over-0.024
 Amen-0.024
ter-0.023
Token tube
Token ID12403
Feature activation-1.78e+00

Pos logit contributions
 levers+0.027
 brushes+0.024
 swirl+0.023
uits+0.023
 ABC+0.023
Neg logit contributions
isher-0.033
eros-0.032
over-0.031
 Amen-0.030
mer-0.029
Token its
Token ID663
Feature activation-1.16e+00

Pos logit contributions
 levers+0.008
 brushes+0.007
uits+0.007
 ABC+0.007
 swirl+0.007
Neg logit contributions
isher-0.010
eros-0.010
over-0.009
 Amen-0.009
mer-0.009
Token wheels
Token ID13666
Feature activation-3.92e+00

Pos logit contributions
 levers+0.021
uits+0.019
 brushes+0.018
Ma+0.018
 ABC+0.017
Neg logit contributions
eros-0.027
isher-0.026
over-0.024
 Amen-0.024
mer-0.024
Token.
Token ID13
Feature activation-1.60e+00

Pos logit contributions
 levers+0.081
 brushes+0.073
Ma+0.073
 ABC+0.071
uits+0.070
Neg logit contributions
isher-0.078
eros-0.075
over-0.073
boat-0.069
mer-0.068
Token Ben
Token ID3932
Feature activation-4.13e+00

Pos logit contributions
 levers+0.034
 brushes+0.030
uits+0.029
 swirl+0.029
 ABC+0.029
Neg logit contributions
isher-0.033
eros-0.032
over-0.031
 Amen-0.030
mer-0.029
Token and
Token ID290
Feature activation+1.69e-01

Pos logit contributions
 levers+0.091
Ma+0.089
 blush+0.086
uits+0.086
 brushes+0.086
Neg logit contributions
eros-0.071
mer-0.065
 Now-0.063
 hunter-0.061
 alone-0.060
Token Mia
Token ID32189
Feature activation-6.54e+00

Pos logit contributions
isher+0.005
eros+0.005
over+0.004
 Amen+0.004
mer+0.004
Neg logit contributions
 levers-0.002
 brushes-0.002
 swirl-0.002
uits-0.002
Ma-0.002
Token are
Token ID389
Feature activation-1.09e+00

Pos logit contributions
 levers+0.093
 ABC+0.089
 brushes+0.087
Ma+0.087
uits+0.084
Neg logit contributions
eros-0.151
 alone-0.147
isher-0.147
mer-0.146
 Amen-0.145
Token sad
Token ID6507
Feature activation-7.87e-02

Pos logit contributions
 levers+0.023
 brushes+0.022
uits+0.021
Ma+0.021
 ABC+0.021
Neg logit contributions
eros-0.021
over-0.021
isher-0.020
 reunited-0.020
 Amen-0.019
Token and
Token ID290
Feature activation-1.10e+00

Pos logit contributions
 levers+0.002
 brushes+0.001
uits+0.001
 swirl+0.001
 ABC+0.001
Neg logit contributions
isher-0.002
eros-0.002
over-0.002
 Amen-0.002
mer-0.002
Token scared
Token ID12008
Feature activation-4.82e-01

Pos logit contributions
 levers+0.018
 brushes+0.015
 marks+0.014
 swirl+0.013
 names+0.013
Neg logit contributions
isher-0.030
over-0.029
eros-0.029
date-0.027
 Amen-0.027
Token.
Token ID13
Feature activation-1.73e+00

Pos logit contributions
 levers+0.010
 brushes+0.009
uits+0.009
 ABC+0.009
 swirl+0.009
Neg logit contributions
isher-0.010
eros-0.009
over-0.009
 Amen-0.009
mer-0.009
Token scissors
Token ID41786
Feature activation-4.36e+00

Pos logit contributions
 levers+0.024
uits+0.021
Ma+0.020
 brushes+0.019
 ABC+0.019
Neg logit contributions
isher-0.048
eros-0.045
over-0.043
 Amen-0.042
ter-0.041
Token break
Token ID2270
Feature activation-2.89e+00

Pos logit contributions
 levers+0.067
uits+0.060
 ABC+0.060
Ma+0.059
 brushes+0.055
Neg logit contributions
isher-0.102
eros-0.098
well-0.095
over-0.094
mer-0.093
Token.
Token ID13
Feature activation-1.95e+00

Pos logit contributions
 levers+0.060
 ABC+0.059
uits+0.059
 blush+0.058
 brushes+0.057
Neg logit contributions
isher-0.051
mer-0.047
ter-0.047
 together-0.046
eros-0.045
Token Tom
Token ID4186
Feature activation-4.70e+00

Pos logit contributions
 levers+0.045
 brushes+0.039
 ABC+0.039
 swirl+0.039
uits+0.039
Neg logit contributions
isher-0.034
eros-0.033
over-0.032
 Amen-0.030
mer-0.029
Token and
Token ID290
Feature activation-1.51e-01

Pos logit contributions
 levers+0.103
uits+0.100
Ma+0.097
eways+0.095
 ABC+0.095
Neg logit contributions
eros-0.077
 Now-0.073
isher-0.072
well-0.070
jected-0.069
Token Jen
Token ID13364
Feature activation-6.54e+00

Pos logit contributions
 levers+0.002
uits+0.002
 brushes+0.002
 ABC+0.002
 swirl+0.002
Neg logit contributions
isher-0.004
eros-0.004
over-0.004
 Amen-0.004
mer-0.004
Token are
Token ID389
Feature activation-1.22e+00

Pos logit contributions
 levers+0.097
 ABC+0.089
uits+0.088
Ma+0.087
 switches+0.080
Neg logit contributions
isher-0.152
eros-0.147
well-0.145
jected-0.142
 alone-0.141
Token sad
Token ID6507
Feature activation-4.10e-01

Pos logit contributions
 levers+0.025
 brushes+0.023
uits+0.023
 ABC+0.023
Ma+0.023
Neg logit contributions
isher-0.023
eros-0.023
over-0.023
 reunited-0.022
 Amen-0.022
Token.
Token ID13
Feature activation-1.29e+00

Pos logit contributions
 levers+0.008
 brushes+0.007
uits+0.007
 swirl+0.007
 ABC+0.007
Neg logit contributions
isher-0.009
eros-0.009
over-0.008
 Amen-0.008
mer-0.008
Token
Token ID198
Feature activation-1.24e+00

Pos logit contributions
 levers+0.033
 swirl+0.030
uits+0.030
 brushes+0.030
 blush+0.030
Neg logit contributions
eros-0.019
isher-0.018
over-0.018
 Amen-0.017
mer-0.016
Token
Token ID198
Feature activation-2.58e-01

Pos logit contributions
 levers+0.029
 brushes+0.027
 blush+0.026
 swirl+0.026
 ABC+0.025
Neg logit contributions
eros-0.021
 Amen-0.021
isher-0.020
over-0.020
ised-0.018
Token.
Token ID13
Feature activation-1.06e+00

Pos logit contributions
 levers+0.010
 brushes+0.008
uits+0.008
 swirl+0.008
 marks+0.008
Neg logit contributions
isher-0.016
 Amen-0.015
eros-0.015
over-0.015
ised-0.014
Token He
Token ID679
Feature activation-8.71e-01

Pos logit contributions
 levers+0.024
 brushes+0.021
uits+0.021
 swirl+0.020
 ABC+0.020
Neg logit contributions
isher-0.020
eros-0.020
over-0.019
 Amen-0.019
mer-0.018
Token hits
Token ID7127
Feature activation-1.86e+00

Pos logit contributions
 levers+0.015
 ABC+0.015
Ma+0.014
uits+0.014
 swirl+0.013
Neg logit contributions
isher-0.019
eros-0.018
penter-0.017
ar-0.017
 Amen-0.016
Token Tim
Token ID5045
Feature activation-5.26e+00

Pos logit contributions
 levers+0.038
uits+0.037
 ABC+0.036
 brushes+0.035
 widen+0.034
Neg logit contributions
isher-0.035
eros-0.034
ter-0.032
boat-0.029
over-0.029
Token and
Token ID290
Feature activation-1.32e+00

Pos logit contributions
 levers+0.110
 brushes+0.100
uits+0.098
Ma+0.093
 swirl+0.093
Neg logit contributions
isher-0.107
eros-0.105
over-0.100
 Amen-0.095
ter-0.095
Token Jen
Token ID13364
Feature activation-6.47e+00

Pos logit contributions
 levers+0.021
uits+0.021
 ABC+0.020
 brushes+0.018
Ma+0.018
Neg logit contributions
isher-0.031
eros-0.030
 Amen-0.028
ter-0.027
 Now-0.027
Token with
Token ID351
Feature activation-1.30e+00

Pos logit contributions
 levers+0.134
uits+0.124
 brushes+0.121
 ABC+0.120
Ma+0.119
Neg logit contributions
isher-0.123
eros-0.122
over-0.114
well-0.112
jected-0.110
Token it
Token ID340
Feature activation-1.23e+00

Pos logit contributions
 levers+0.029
 ABC+0.028
uits+0.026
 brushes+0.026
Ma+0.026
Neg logit contributions
isher-0.023
eros-0.021
over-0.020
 Amen-0.019
boat-0.019
Token.
Token ID13
Feature activation-1.82e+00

Pos logit contributions
 levers+0.028
 brushes+0.025
Ma+0.025
uits+0.025
 ABC+0.025
Neg logit contributions
isher-0.022
eros-0.021
over-0.020
mer-0.019
ter-0.019
Token Tim
Token ID5045
Feature activation-4.45e+00

Pos logit contributions
 levers+0.043
 brushes+0.038
 ABC+0.038
uits+0.038
 swirl+0.038
Neg logit contributions
eros-0.031
isher-0.030
over-0.028
 Amen-0.028
 Now-0.027
Token and
Token ID290
Feature activation-2.42e-01

Pos logit contributions
uits+0.082
 levers+0.082
Ma+0.072
eways+0.072
 ABC+0.071
Neg logit contributions
eros-0.094
isher-0.087
 alone-0.086
jected-0.086
 Now-0.085
Token.
Token ID13
Feature activation-1.16e+00

Pos logit contributions
 levers+0.034
 brushes+0.030
uits+0.029
 swirl+0.029
 ABC+0.028
Neg logit contributions
isher-0.035
eros-0.034
over-0.033
 Amen-0.033
mer-0.031
Token He
Token ID679
Feature activation-6.26e-01

Pos logit contributions
 levers+0.029
 brushes+0.027
uits+0.026
 swirl+0.026
 ABC+0.026
Neg logit contributions
isher-0.019
eros-0.018
over-0.017
 Amen-0.017
mer-0.016
Token pushes
Token ID20070
Feature activation-1.53e+00

Pos logit contributions
 levers+0.013
uits+0.012
Ma+0.012
 ABC+0.011
 blush+0.011
Neg logit contributions
eros-0.012
isher-0.011
 hunter-0.011
 Now-0.011
 Amen-0.010
Token Tim
Token ID5045
Feature activation-5.14e+00

Pos logit contributions
 levers+0.031
 brushes+0.029
 ABC+0.028
uits+0.028
 swirl+0.027
Neg logit contributions
isher-0.032
eros-0.031
over-0.030
mer-0.028
ter-0.028
Token and
Token ID290
Feature activation-1.16e+00

Pos logit contributions
 levers+0.104
 brushes+0.094
uits+0.091
 swirl+0.089
Ma+0.089
Neg logit contributions
isher-0.106
eros-0.104
over-0.101
ter-0.095
boat-0.094
Token Mia
Token ID32189
Feature activation-6.45e+00

Pos logit contributions
 levers+0.020
uits+0.017
 brushes+0.017
 ABC+0.016
Ma+0.016
Neg logit contributions
isher-0.028
eros-0.028
 Amen-0.026
over-0.025
mer-0.025
Token off
Token ID572
Feature activation-1.86e+00

Pos logit contributions
 levers+0.148
 brushes+0.136
Ma+0.135
 ABC+0.134
uits+0.133
Neg logit contributions
isher-0.108
eros-0.101
over-0.100
 alone-0.096
well-0.096
Token the
Token ID262
Feature activation-1.20e+00

Pos logit contributions
 levers+0.034
 brushes+0.030
uits+0.028
 ABC+0.028
 swirl+0.028
Neg logit contributions
isher-0.043
eros-0.042
over-0.041
 Amen-0.040
mer-0.039
Token toy
Token ID13373
Feature activation-2.85e-01

Pos logit contributions
 levers+0.020
 brushes+0.017
Ma+0.017
uits+0.017
 swirl+0.016
Neg logit contributions
isher-0.030
eros-0.029
over-0.027
 Amen-0.027
mer-0.027
Token and
Token ID290
Feature activation-1.32e+00

Pos logit contributions
 levers+0.005
 marks+0.004
 swirl+0.004
 brushes+0.004
uits+0.004
Neg logit contributions
 Amen-0.007
isher-0.007
over-0.007
eros-0.007
ised-0.007
Token sits
Token ID10718
Feature activation+3.63e-01

Pos logit contributions
 levers+0.021
uits+0.018
 brushes+0.018
 ABC+0.017
Ma+0.017
Neg logit contributions
isher-0.034
eros-0.033
 Amen-0.031
over-0.031
mer-0.030
Token it
Token ID340
Feature activation-1.47e+00

Pos logit contributions
 levers+0.038
 brushes+0.034
uits+0.032
 swirl+0.032
 ABC+0.032
Neg logit contributions
isher-0.038
eros-0.037
over-0.036
 Amen-0.035
mer-0.034
Token with
Token ID351
Feature activation-2.61e-01

Pos logit contributions
 levers+0.028
 brushes+0.024
uits+0.024
Ma+0.023
 ABC+0.023
Neg logit contributions
isher-0.032
eros-0.031
over-0.030
 Amen-0.030
ter-0.029
Token holes
Token ID10421
Feature activation-4.58e+00

Pos logit contributions
 levers+0.005
 brushes+0.005
 swirl+0.005
uits+0.004
 marks+0.004
Neg logit contributions
isher-0.006
eros-0.005
over-0.005
 Amen-0.005
mer-0.005
Token of
Token ID286
Feature activation-1.94e+00

Pos logit contributions
 levers+0.085
 brushes+0.075
uits+0.071
 swirl+0.071
 ABC+0.071
Neg logit contributions
isher-0.105
eros-0.102
over-0.099
 Amen-0.096
mer-0.094
Token different
Token ID1180
Feature activation-2.25e+00

Pos logit contributions
 levers+0.039
 brushes+0.035
 swirl+0.034
 marks+0.033
uits+0.033
Neg logit contributions
isher-0.042
eros-0.040
over-0.040
 Amen-0.039
mer-0.038
Token sizes
Token ID10620
Feature activation-6.44e+00

Pos logit contributions
 levers+0.035
 brushes+0.030
uits+0.030
Ma+0.030
 ABC+0.029
Neg logit contributions
isher-0.058
eros-0.056
over-0.054
mer-0.053
 Amen-0.051
Token.
Token ID13
Feature activation+1.88e-01

Pos logit contributions
 levers+0.125
 brushes+0.111
uits+0.106
Ma+0.105
 swirl+0.105
Neg logit contributions
isher-0.142
eros-0.137
over-0.133
 Amen-0.129
mer-0.126
Token I
Token ID314
Feature activation+7.76e-02

Pos logit contributions
isher+0.004
eros+0.003
over+0.003
 Amen+0.003
mer+0.003
Neg logit contributions
 levers-0.004
 brushes-0.004
 swirl-0.004
uits-0.004
 ABC-0.004
Token will
Token ID481
Feature activation-2.54e-01

Pos logit contributions
eros+0.002
isher+0.002
over+0.002
 Amen+0.002
ter+0.002
Neg logit contributions
 levers-0.001
 brushes-0.001
 names-0.001
 swirl-0.001
 marks-0.001
Token make
Token ID787
Feature activation-2.24e+00

Pos logit contributions
 levers+0.004
 brushes+0.004
 swirl+0.004
 marks+0.003
uits+0.003
Neg logit contributions
isher-0.007
eros-0.006
over-0.006
 Amen-0.006
mer-0.006
Token it
Token ID340
Feature activation-1.74e+00

Pos logit contributions
 levers+0.045
 brushes+0.040
uits+0.039
 swirl+0.038
 ABC+0.037
Neg logit contributions
isher-0.048
eros-0.047
over-0.045
 Amen-0.044
mer-0.042
Token eleven
Token ID22216
Feature activation-2.94e+00

Pos logit contributions
 levers+0.081
uits+0.072
 brushes+0.071
 ABC+0.069
 switches+0.067
Neg logit contributions
isher-0.080
eros-0.078
 Amen-0.074
over-0.073
ter-0.073
Token,
Token ID11
Feature activation-4.88e+00

Pos logit contributions
 levers+0.067
uits+0.060
Ma+0.059
 blush+0.058
 sweat+0.057
Neg logit contributions
isher-0.053
eros-0.051
over-0.048
ised-0.046
mer-0.044
Token twelve
Token ID14104
Feature activation-2.68e+00

Pos logit contributions
 levers+0.087
uits+0.077
 brushes+0.074
Ma+0.071
 ABC+0.071
Neg logit contributions
isher-0.107
eros-0.105
 Amen-0.101
over-0.098
penter-0.097
Token,
Token ID11
Feature activation-5.20e+00

Pos logit contributions
 levers+0.059
uits+0.053
Ma+0.052
 brushes+0.050
 blush+0.049
Neg logit contributions
isher-0.050
eros-0.048
over-0.046
mer-0.044
ised-0.043
Token thirteen
Token ID28306
Feature activation-2.48e+00

Pos logit contributions
 levers+0.089
uits+0.078
 brushes+0.074
Ma+0.072
 ABC+0.072
Neg logit contributions
isher-0.117
eros-0.116
 Amen-0.110
over-0.108
penter-0.108
Token,
Token ID11
Feature activation-6.41e+00

Pos logit contributions
 levers+0.058
uits+0.052
Ma+0.050
 switches+0.050
 brushes+0.050
Neg logit contributions
isher-0.043
over-0.042
eros-0.042
mer-0.038
ised-0.037
Token fourteen
Token ID29167
Feature activation-3.93e+00

Pos logit contributions
 levers+0.101
uits+0.083
 ABC+0.081
 brushes+0.081
 switches+0.080
Neg logit contributions
isher-0.157
eros-0.153
ter-0.144
 Now-0.142
penter-0.140
Token,
Token ID11
Feature activation-5.81e+00

Pos logit contributions
uits+0.101
 levers+0.101
Ma+0.092
eways+0.091
 ABC+0.090
Neg logit contributions
eros-0.043
 course-0.043
isher-0.042
ised-0.041
 together-0.039
Token fifteen
Token ID17280
Feature activation-4.36e+00

Pos logit contributions
 levers+0.099
uits+0.091
 brushes+0.083
 switches+0.080
 ABC+0.080
Neg logit contributions
isher-0.127
eros-0.127
 Amen-0.121
ter-0.118
penter-0.117
Token,
Token ID11
Feature activation-5.89e+00

Pos logit contributions
 levers+0.098
uits+0.089
Ma+0.083
 switches+0.083
 brushes+0.082
Neg logit contributions
isher-0.077
eros-0.074
over-0.074
mer-0.068
ised-0.068
Token sixteen
Token ID27913
Feature activation-4.29e+00

Pos logit contributions
 levers+0.089
uits+0.076
 brushes+0.075
 switches+0.071
 ABC+0.070
Neg logit contributions
isher-0.146
eros-0.145
 Amen-0.139
over-0.135
penter-0.134
Token into
Token ID656
Feature activation-3.49e+00

Pos logit contributions
 levers+0.035
 brushes+0.033
uits+0.032
 ABC+0.032
 blush+0.031
Neg logit contributions
isher-0.037
eros-0.036
over-0.034
ter-0.034
mer-0.032
Token pieces
Token ID5207
Feature activation-2.22e+00

Pos logit contributions
 levers+0.065
 brushes+0.059
uits+0.058
 ABC+0.055
 blush+0.055
Neg logit contributions
isher-0.076
eros-0.075
over-0.072
 Amen-0.068
mer-0.068
Token.
Token ID13
Feature activation-1.17e+00

Pos logit contributions
 levers+0.047
 brushes+0.043
 ABC+0.041
Ma+0.041
uits+0.041
Neg logit contributions
isher-0.045
eros-0.043
over-0.042
 Amen-0.040
mer-0.039
Token Tom
Token ID4186
Feature activation-4.28e+00

Pos logit contributions
 levers+0.023
 brushes+0.020
uits+0.020
 swirl+0.020
 ABC+0.019
Neg logit contributions
isher-0.025
eros-0.025
over-0.024
 Amen-0.023
mer-0.022
Token and
Token ID290
Feature activation+6.69e-01

Pos logit contributions
uits+0.099
 levers+0.097
Ma+0.091
eways+0.089
 brushes+0.087
Neg logit contributions
eros-0.068
 Now-0.063
 alone-0.061
jected-0.059
 hunter-0.054
Token Mia
Token ID32189
Feature activation-6.38e+00

Pos logit contributions
isher+0.017
eros+0.017
over+0.016
 Amen+0.016
mer+0.016
Neg logit contributions
 levers-0.011
 brushes-0.009
uits-0.009
 swirl-0.008
 ABC-0.008
Token are
Token ID389
Feature activation-1.48e+00

Pos logit contributions
 levers+0.097
uits+0.095
 ABC+0.092
Ma+0.089
 brushes+0.084
Neg logit contributions
 alone-0.138
eros-0.137
well-0.135
jected-0.135
isher-0.134
Token shocked
Token ID11472
Feature activation+3.36e-01

Pos logit contributions
 levers+0.031
 brushes+0.029
uits+0.028
Ma+0.028
 ABC+0.027
Neg logit contributions
eros-0.028
isher-0.028
over-0.028
 reunited-0.027
 Amen-0.026
Token and
Token ID290
Feature activation-1.08e+00

Pos logit contributions
isher+0.008
eros+0.008
over+0.008
 Amen+0.007
mer+0.007
Neg logit contributions
 levers-0.006
 brushes-0.005
uits-0.005
 ABC-0.005
 swirl-0.005
Token sad
Token ID6507
Feature activation+3.92e-01

Pos logit contributions
 levers+0.019
 brushes+0.017
uits+0.016
 swirl+0.016
 ABC+0.016
Neg logit contributions
isher-0.026
eros-0.025
over-0.024
 Amen-0.024
mer-0.023
Token.
Token ID13
Feature activation-1.02e+00

Pos logit contributions
isher+0.010
eros+0.009
 Amen+0.009
over+0.009
boat+0.009
Neg logit contributions
 levers-0.007
 brushes-0.006
 marks-0.006
 swirl-0.006
 ABC-0.005
Token Cars
Token ID25277
Feature activation-3.79e+00

Pos logit contributions
 levers+0.023
 brushes+0.021
uits+0.020
 swirl+0.020
 ABC+0.020
Neg logit contributions
isher-0.024
eros-0.023
over-0.022
 Amen-0.022
mer-0.020
Token,
Token ID11
Feature activation-5.18e+00

Pos logit contributions
 levers+0.070
Ma+0.068
 brushes+0.065
 ABC+0.062
 blush+0.061
Neg logit contributions
isher-0.077
eros-0.075
boat-0.073
over-0.073
penter-0.072
Token trucks
Token ID13960
Feature activation-4.22e+00

Pos logit contributions
Ma+0.094
 blush+0.087
 ABC+0.086
 magn+0.084
 fingertips+0.084
Neg logit contributions
 hunter-0.092
isher-0.092
penter-0.089
eros-0.088
boat-0.085
Token,
Token ID11
Feature activation-5.85e+00

Pos logit contributions
 levers+0.075
Ma+0.068
 brushes+0.068
 ABC+0.064
 swirl+0.064
Neg logit contributions
isher-0.094
eros-0.092
over-0.088
mer-0.085
boat-0.085
Token buses
Token ID16893
Feature activation-3.51e+00

Pos logit contributions
Ma+0.109
 blush+0.103
 ABC+0.100
 levers+0.099
 fingertips+0.097
Neg logit contributions
 hunter-0.103
isher-0.101
eros-0.099
penter-0.098
ter-0.096
Token,
Token ID11
Feature activation-6.36e+00

Pos logit contributions
 levers+0.066
 brushes+0.060
Ma+0.059
uits+0.057
 ABC+0.056
Neg logit contributions
isher-0.076
eros-0.074
over-0.072
mer-0.068
 Amen-0.068
Token and
Token ID290
Feature activation-2.99e+00

Pos logit contributions
Ma+0.139
 blush+0.132
 levers+0.129
 ABC+0.128
 fingertips+0.124
Neg logit contributions
 hunter-0.092
isher-0.091
eros-0.090
ter-0.090
penter-0.086
Token bikes
Token ID16715
Feature activation-1.43e+00

Pos logit contributions
 levers+0.049
Ma+0.049
uits+0.047
 brushes+0.046
 ABC+0.046
Neg logit contributions
isher-0.063
 Amen-0.059
eros-0.059
 hunter-0.058
boat-0.057
Token.
Token ID13
Feature activation-1.45e+00

Pos logit contributions
 levers+0.028
 brushes+0.025
uits+0.024
 swirl+0.024
 ABC+0.023
Neg logit contributions
isher-0.031
eros-0.030
over-0.029
 Amen-0.029
mer-0.028
Token They
Token ID1119
Feature activation-2.52e+00

Pos logit contributions
 levers+0.032
 brushes+0.029
uits+0.028
 swirl+0.028
 ABC+0.027
Neg logit contributions
isher-0.029
eros-0.028
over-0.027
 Amen-0.026
mer-0.025
Token were
Token ID547
Feature activation-1.50e+00

Pos logit contributions
 levers+0.046
 brushes+0.041
 ABC+0.040
Ma+0.039
uits+0.039
Neg logit contributions
isher-0.055
eros-0.052
 Amen-0.051
over-0.050
boat-0.050
Token with
Token ID351
Feature activation-1.30e+00

Pos logit contributions
 levers+0.134
uits+0.124
 brushes+0.121
 ABC+0.120
Ma+0.119
Neg logit contributions
isher-0.123
eros-0.122
over-0.114
well-0.112
jected-0.110
Token it
Token ID340
Feature activation-1.23e+00

Pos logit contributions
 levers+0.029
 ABC+0.028
uits+0.026
 brushes+0.026
Ma+0.026
Neg logit contributions
isher-0.023
eros-0.021
over-0.020
 Amen-0.019
boat-0.019
Token.
Token ID13
Feature activation-1.82e+00

Pos logit contributions
 levers+0.028
 brushes+0.025
Ma+0.025
uits+0.025
 ABC+0.025
Neg logit contributions
isher-0.022
eros-0.021
over-0.020
mer-0.019
ter-0.019
Token Tim
Token ID5045
Feature activation-4.45e+00

Pos logit contributions
 levers+0.043
 brushes+0.038
 ABC+0.038
uits+0.038
 swirl+0.038
Neg logit contributions
eros-0.031
isher-0.030
over-0.028
 Amen-0.028
 Now-0.027
Token and
Token ID290
Feature activation-2.42e-01

Pos logit contributions
uits+0.082
 levers+0.082
Ma+0.072
eways+0.072
 ABC+0.071
Neg logit contributions
eros-0.094
isher-0.087
 alone-0.086
jected-0.086
 Now-0.085
Token Jen
Token ID13364
Feature activation-6.36e+00

Pos logit contributions
 levers+0.004
uits+0.003
 ABC+0.003
 brushes+0.003
 swirl+0.003
Neg logit contributions
eros-0.006
isher-0.006
 Amen-0.006
ter-0.005
over-0.005
Token are
Token ID389
Feature activation-1.01e+00

Pos logit contributions
 levers+0.092
uits+0.086
 ABC+0.085
Ma+0.083
 switches+0.075
Neg logit contributions
isher-0.147
eros-0.145
 alone-0.145
jected-0.141
well-0.141
Token hurt
Token ID5938
Feature activation-1.26e+00

Pos logit contributions
 levers+0.021
 brushes+0.018
uits+0.018
 ABC+0.018
Ma+0.018
Neg logit contributions
isher-0.021
eros-0.020
over-0.020
 Amen-0.019
 reunited-0.018
Token and
Token ID290
Feature activation-1.48e+00

Pos logit contributions
 levers+0.025
 brushes+0.022
uits+0.021
 swirl+0.021
 ABC+0.020
Neg logit contributions
isher-0.028
eros-0.027
over-0.026
 Amen-0.026
mer-0.025
Token scared
Token ID12008
Feature activation-1.01e+00

Pos logit contributions
 levers+0.024
 brushes+0.022
 marks+0.020
 swirl+0.019
 blush+0.019
Neg logit contributions
isher-0.039
eros-0.037
over-0.037
 Amen-0.035
date-0.035
Token.
Token ID13
Feature activation-1.48e+00

Pos logit contributions
 levers+0.023
 brushes+0.021
uits+0.020
 ABC+0.020
Ma+0.020
Neg logit contributions
isher-0.019
eros-0.018
over-0.018
 Amen-0.017
ter-0.017
Token shapes
Token ID15268
Feature activation-4.66e+00

Pos logit contributions
 levers+0.028
Ma+0.023
uits+0.023
 brushes+0.021
 ABC+0.020
Neg logit contributions
isher-0.077
eros-0.074
 Amen-0.073
over-0.073
mer-0.071
Token.
Token ID13
Feature activation-7.67e-01

Pos logit contributions
 levers+0.092
 brushes+0.082
uits+0.078
 swirl+0.078
 ABC+0.076
Neg logit contributions
isher-0.102
eros-0.099
over-0.096
 Amen-0.095
mer-0.090
Token They
Token ID1119
Feature activation-2.64e+00

Pos logit contributions
 levers+0.016
 brushes+0.014
uits+0.014
 swirl+0.014
Ma+0.014
Neg logit contributions
isher-0.015
eros-0.015
over-0.015
 Amen-0.015
mer-0.014
Token can
Token ID460
Feature activation-2.94e+00

Pos logit contributions
 levers+0.049
Ma+0.043
 ABC+0.042
uits+0.042
 brushes+0.040
Neg logit contributions
isher-0.059
 Amen-0.056
eros-0.053
mer-0.052
penter-0.052
Token make
Token ID787
Feature activation-3.85e+00

Pos logit contributions
 levers+0.047
 brushes+0.040
uits+0.039
 ABC+0.038
 swirl+0.038
Neg logit contributions
isher-0.075
eros-0.072
 Amen-0.070
over-0.070
mer-0.067
Token towers
Token ID18028
Feature activation-6.35e+00

Pos logit contributions
 levers+0.070
uits+0.065
 blush+0.061
 magn+0.060
Ma+0.060
Neg logit contributions
isher-0.080
eros-0.077
 together-0.072
over-0.072
penter-0.072
Token,
Token ID11
Feature activation-5.13e+00

Pos logit contributions
 levers+0.144
uits+0.123
Ma+0.123
 brushes+0.120
 switches+0.120
Neg logit contributions
isher-0.104
over-0.103
eros-0.101
 together-0.100
penter-0.100
Token houses
Token ID7777
Feature activation-5.67e+00

Pos logit contributions
 levers+0.085
uits+0.080
Ma+0.077
 magn+0.073
 brushes+0.072
Neg logit contributions
isher-0.108
 Amen-0.105
eros-0.103
penter-0.103
ter-0.100
Token,
Token ID11
Feature activation-5.43e+00

Pos logit contributions
 levers+0.107
 brushes+0.094
uits+0.090
Ma+0.089
 swirl+0.088
Neg logit contributions
isher-0.127
eros-0.124
over-0.120
 Amen-0.117
mer-0.113
Token cars
Token ID5006
Feature activation-4.99e+00

Pos logit contributions
 levers+0.099
uits+0.091
Ma+0.089
 magn+0.082
 brushes+0.082
Neg logit contributions
isher-0.109
eros-0.104
ter-0.103
penter-0.102
 Amen-0.100
Token and
Token ID290
Feature activation-3.46e+00

Pos logit contributions
 levers+0.085
 brushes+0.075
uits+0.071
 swirl+0.071
 ABC+0.069
Neg logit contributions
isher-0.124
eros-0.120
 Amen-0.118
over-0.117
mer-0.110
Token cars
Token ID5006
Feature activation-3.86e+00

Pos logit contributions
 levers+0.059
Ma+0.059
 widen+0.052
uits+0.052
 blush+0.052
Neg logit contributions
isher-0.061
eros-0.058
over-0.054
penter-0.053
ised-0.053
Token of
Token ID286
Feature activation-2.63e+00

Pos logit contributions
 levers+0.062
 brushes+0.055
uits+0.052
 marks+0.050
 ABC+0.050
Neg logit contributions
isher-0.100
eros-0.097
 Amen-0.096
over-0.093
mer-0.089
Token different
Token ID1180
Feature activation-1.81e+00

Pos logit contributions
 levers+0.045
 brushes+0.039
Ma+0.038
uits+0.038
 swirl+0.037
Neg logit contributions
isher-0.063
eros-0.061
over-0.058
 Amen-0.058
mer-0.056
Token colors
Token ID7577
Feature activation-4.77e+00

Pos logit contributions
 levers+0.028
Ma+0.025
uits+0.024
 blush+0.023
 swirl+0.023
Neg logit contributions
isher-0.046
eros-0.044
over-0.042
mer-0.042
ised-0.041
Token and
Token ID290
Feature activation-2.57e+00

Pos logit contributions
 levers+0.088
 brushes+0.077
Ma+0.076
uits+0.074
 swirl+0.073
Neg logit contributions
isher-0.108
eros-0.104
over-0.102
 Amen-0.097
boat-0.096
Token sizes
Token ID10620
Feature activation-6.35e+00

Pos logit contributions
 levers+0.032
uits+0.027
Ma+0.026
 brushes+0.026
 ABC+0.024
Neg logit contributions
isher-0.071
eros-0.070
 Amen-0.068
over-0.067
mer-0.065
Token.
Token ID13
Feature activation-8.19e-01

Pos logit contributions
 levers+0.119
 brushes+0.106
uits+0.101
 swirl+0.100
 marks+0.098
Neg logit contributions
isher-0.146
eros-0.142
 Amen-0.138
over-0.137
mer-0.129
Token He
Token ID679
Feature activation-5.23e-01

Pos logit contributions
 levers+0.018
 brushes+0.016
uits+0.015
 ABC+0.015
Ma+0.015
Neg logit contributions
isher-0.017
eros-0.016
over-0.016
 Amen-0.015
mer-0.015
Token likes
Token ID7832
Feature activation-7.42e-01

Pos logit contributions
 levers+0.010
uits+0.009
Ma+0.009
 brushes+0.008
 swirl+0.008
Neg logit contributions
isher-0.011
eros-0.011
 Amen-0.011
penter-0.010
over-0.010
Token to
Token ID284
Feature activation-1.93e+00

Pos logit contributions
 levers+0.016
uits+0.014
Ma+0.014
 widen+0.014
 blush+0.013
Neg logit contributions
isher-0.014
eros-0.014
olph-0.012
 gol-0.012
ter-0.012
Token make
Token ID787
Feature activation-3.05e+00

Pos logit contributions
 levers+0.032
 brushes+0.028
 swirl+0.027
uits+0.026
 ABC+0.026
Neg logit contributions
isher-0.051
eros-0.049
over-0.049
 Amen-0.046
mer-0.045
Token is
Token ID318
Feature activation-1.55e+00

Pos logit contributions
 levers+0.015
uits+0.013
Ma+0.013
 brushes+0.013
 ABC+0.013
Neg logit contributions
eros-0.022
isher-0.022
mer-0.020
over-0.020
 Amen-0.020
Token flat
Token ID6228
Feature activation-1.82e+00

Pos logit contributions
 levers+0.028
 brushes+0.024
 ABC+0.024
Ma+0.024
uits+0.024
Neg logit contributions
isher-0.035
eros-0.034
over-0.034
 Amen-0.033
 reunited-0.032
Token.
Token ID13
Feature activation-1.44e+00

Pos logit contributions
 levers+0.031
 brushes+0.027
uits+0.025
 swirl+0.025
 ABC+0.025
Neg logit contributions
isher-0.045
eros-0.044
over-0.043
 Amen-0.043
mer-0.040
Token Tim
Token ID5045
Feature activation-4.39e+00

Pos logit contributions
 levers+0.028
 brushes+0.025
uits+0.024
 ABC+0.024
 swirl+0.024
Neg logit contributions
isher-0.033
eros-0.031
over-0.030
 Amen-0.029
mer-0.029
Token and
Token ID290
Feature activation-1.20e-02

Pos logit contributions
 levers+0.088
uits+0.077
 brushes+0.076
Ma+0.075
 ABC+0.074
Neg logit contributions
eros-0.094
isher-0.092
over-0.087
mer-0.085
ter-0.083
Token Sue
Token ID26089
Feature activation-6.33e+00

Pos logit contributions
 levers+0.000
 brushes+0.000
uits+0.000
 swirl+0.000
 ABC+0.000
Neg logit contributions
isher-0.000
eros-0.000
over-0.000
 Amen-0.000
mer-0.000
Token are
Token ID389
Feature activation-1.58e+00

Pos logit contributions
 levers+0.093
uits+0.083
Ma+0.082
 ABC+0.080
 brushes+0.078
Neg logit contributions
eros-0.153
isher-0.152
over-0.149
 reunited-0.147
mer-0.147
Token sad
Token ID6507
Feature activation-3.73e-01

Pos logit contributions
 levers+0.029
 brushes+0.025
 swirl+0.024
uits+0.024
 marks+0.024
Neg logit contributions
isher-0.038
eros-0.036
over-0.035
 Amen-0.035
mer-0.033
Token.
Token ID13
Feature activation-1.44e+00

Pos logit contributions
 levers+0.007
 brushes+0.007
uits+0.006
 swirl+0.006
 ABC+0.006
Neg logit contributions
isher-0.008
eros-0.008
over-0.008
 Amen-0.008
mer-0.007
Token They
Token ID1119
Feature activation-2.09e+00

Pos logit contributions
 levers+0.035
 brushes+0.032
uits+0.032
 swirl+0.032
Ma+0.031
Neg logit contributions
eros-0.024
isher-0.023
over-0.023
 Amen-0.022
mer-0.021
Token drop
Token ID4268
Feature activation-2.06e+00

Pos logit contributions
 levers+0.037
Ma+0.035
 ABC+0.034
uits+0.034
 brushes+0.032
Neg logit contributions
 Amen-0.044
isher-0.043
eros-0.043
 hunter-0.041
 reunited-0.041
Token pots
Token ID32195
Feature activation-5.22e+00

Pos logit contributions
Ma+0.077
 levers+0.075
uits+0.072
 brushes+0.069
 ABC+0.069
Neg logit contributions
eros-0.098
isher-0.097
 hunter-0.094
penter-0.090
over-0.089
Token,
Token ID11
Feature activation-5.97e+00

Pos logit contributions
 levers+0.108
 brushes+0.097
Ma+0.095
 ABC+0.092
 swirl+0.092
Neg logit contributions
isher-0.104
eros-0.103
over-0.101
mer-0.093
ter-0.092
Token coins
Token ID10796
Feature activation-2.37e+00

Pos logit contributions
Ma+0.098
 levers+0.091
uits+0.090
 ABC+0.088
 downward+0.087
Neg logit contributions
isher-0.125
eros-0.121
 hunter-0.115
mer-0.112
ar-0.111
Token,
Token ID11
Feature activation-6.21e+00

Pos logit contributions
 levers+0.045
 brushes+0.040
uits+0.038
 swirl+0.038
Ma+0.038
Neg logit contributions
isher-0.052
eros-0.051
over-0.050
 Amen-0.048
mer-0.047
Token paintings
Token ID21641
Feature activation-4.50e+00

Pos logit contributions
 levers+0.107
Ma+0.107
uits+0.099
 ABC+0.097
 downward+0.095
Neg logit contributions
isher-0.126
eros-0.123
over-0.114
 hunter-0.113
ter-0.112
Token,
Token ID11
Feature activation-6.33e+00

Pos logit contributions
 levers+0.097
Ma+0.090
 brushes+0.086
 ABC+0.084
uits+0.083
Neg logit contributions
isher-0.080
eros-0.080
over-0.080
mer-0.071
penter-0.071
Token and
Token ID290
Feature activation-2.61e+00

Pos logit contributions
 levers+0.119
Ma+0.115
uits+0.108
 brushes+0.105
 ABC+0.104
Neg logit contributions
eros-0.118
isher-0.118
over-0.111
ter-0.108
 hunter-0.106
Token statues
Token ID25827
Feature activation-3.26e+00

Pos logit contributions
 levers+0.041
Ma+0.038
uits+0.038
 brushes+0.036
 ABC+0.036
Neg logit contributions
isher-0.060
eros-0.058
 Amen-0.057
over-0.056
 hunter-0.053
Token.
Token ID13
Feature activation-1.80e+00

Pos logit contributions
 levers+0.071
 brushes+0.063
Ma+0.063
uits+0.061
 ABC+0.061
Neg logit contributions
isher-0.062
eros-0.060
over-0.059
mer-0.055
 Amen-0.054
Token They
Token ID1119
Feature activation-2.49e+00

Pos logit contributions
 levers+0.045
 swirl+0.040
 ABC+0.040
 brushes+0.040
uits+0.040
Neg logit contributions
isher-0.028
over-0.027
eros-0.027
 Amen-0.025
mer-0.024
Token learn
Token ID2193
Feature activation-1.91e+00

Pos logit contributions
 levers+0.040
Ma+0.035
 ABC+0.035
 brushes+0.034
uits+0.034
Neg logit contributions
isher-0.057
 Amen-0.056
eros-0.054
penter-0.052
mer-0.052
Token cars
Token ID5006
Feature activation-3.54e+00

Pos logit contributions
 levers+0.044
Ma+0.042
 blush+0.039
 widen+0.038
uits+0.038
Neg logit contributions
isher-0.048
eros-0.045
over-0.042
penter-0.042
ised-0.042
Token of
Token ID286
Feature activation-2.35e+00

Pos logit contributions
 levers+0.058
 brushes+0.052
uits+0.049
 marks+0.047
 swirl+0.047
Neg logit contributions
isher-0.090
eros-0.087
 Amen-0.086
over-0.084
mer-0.080
Token different
Token ID1180
Feature activation-1.58e+00

Pos logit contributions
 levers+0.041
 brushes+0.036
Ma+0.035
uits+0.035
 ABC+0.034
Neg logit contributions
isher-0.054
eros-0.052
over-0.050
 Amen-0.049
mer-0.048
Token colors
Token ID7577
Feature activation-4.39e+00

Pos logit contributions
 levers+0.026
Ma+0.023
 blush+0.022
uits+0.022
 brushes+0.022
Neg logit contributions
isher-0.039
eros-0.036
over-0.035
mer-0.035
ised-0.034
Token and
Token ID290
Feature activation-2.05e+00

Pos logit contributions
 levers+0.080
 brushes+0.069
Ma+0.068
uits+0.066
 ABC+0.066
Neg logit contributions
isher-0.101
eros-0.097
over-0.095
 Amen-0.091
mer-0.090
Token sizes
Token ID10620
Feature activation-6.32e+00

Pos logit contributions
 levers+0.024
 brushes+0.019
uits+0.019
Ma+0.019
 ABC+0.018
Neg logit contributions
isher-0.059
eros-0.057
 Amen-0.056
over-0.056
mer-0.054
Token.
Token ID13
Feature activation-1.39e+00

Pos logit contributions
 levers+0.119
 brushes+0.106
uits+0.101
 swirl+0.100
 ABC+0.098
Neg logit contributions
isher-0.144
eros-0.141
over-0.136
 Amen-0.136
mer-0.127
Token They
Token ID1119
Feature activation-2.55e+00

Pos logit contributions
 levers+0.029
 brushes+0.026
uits+0.025
 swirl+0.024
 ABC+0.024
Neg logit contributions
isher-0.030
eros-0.028
over-0.027
 Amen-0.027
mer-0.026
Token make
Token ID787
Feature activation-3.15e+00

Pos logit contributions
 levers+0.042
Ma+0.037
 ABC+0.036
uits+0.036
 brushes+0.035
Neg logit contributions
isher-0.060
 Amen-0.057
eros-0.056
penter-0.055
mer-0.054
Token a
Token ID257
Feature activation-2.31e+00

Pos logit contributions
 levers+0.057
uits+0.051
 blush+0.050
 brushes+0.050
 magn+0.050
Neg logit contributions
isher-0.066
eros-0.064
over-0.061
penter-0.060
 reunited-0.059
Token line
Token ID1627
Feature activation-1.68e+00

Pos logit contributions
 levers+0.039
 brushes+0.035
uits+0.034
 blush+0.032
Ma+0.032
Neg logit contributions
isher-0.054
eros-0.053
 Amen-0.052
over-0.051
 hunter-0.048
Token even
Token ID772
Feature activation+1.64e+00

Pos logit contributions
 levers+0.032
 brushes+0.028
uits+0.028
Ma+0.028
 swirl+0.028
Neg logit contributions
isher-0.026
 Amen-0.024
eros-0.024
over-0.024
penter-0.022
Token longer
Token ID2392
Feature activation+6.73e-01

Pos logit contributions
eros+0.038
isher+0.037
over+0.035
 Amen+0.035
mer+0.033
Neg logit contributions
 levers-0.032
 brushes-0.029
 swirl-0.026
 marks-0.026
 ABC-0.026
Token friendship
Token ID14738
Feature activation+1.04e+00

Pos logit contributions
isher+0.015
eros+0.015
 Amen+0.014
over+0.014
mer+0.013
Neg logit contributions
 levers-0.013
 brushes-0.012
uits-0.011
 swirl-0.011
 ABC-0.011
Token with
Token ID351
Feature activation+8.49e-01

Pos logit contributions
isher+0.024
eros+0.023
 Amen+0.023
over+0.022
mer+0.021
Neg logit contributions
 levers-0.019
 brushes-0.017
uits-0.016
 swirl-0.016
 ABC-0.016
Token him
Token ID683
Feature activation+4.10e-01

Pos logit contributions
isher+0.020
eros+0.020
over+0.019
 Amen+0.019
mer+0.018
Neg logit contributions
 levers-0.015
 brushes-0.013
uits-0.013
 swirl-0.012
 ABC-0.012
Token now
Token ID783
Feature activation+3.27e+00

Pos logit contributions
isher+0.010
eros+0.009
 Amen+0.009
over+0.009
mer+0.008
Neg logit contributions
 levers-0.008
 brushes-0.007
uits-0.006
 ABC-0.006
 swirl-0.006
Token.
Token ID13
Feature activation+1.85e+00

Pos logit contributions
isher+0.094
eros+0.087
 Amen+0.085
ugg+0.077
mer+0.077
Neg logit contributions
 levers-0.047
 marks-0.040
 blush-0.039
 brushes-0.038
 swirl-0.038
Token<|endoftext|>
Token ID50256
Feature activation+3.26e+00

Pos logit contributions
isher+0.047
eros+0.045
over+0.043
mer+0.042
 Amen+0.041
Neg logit contributions
 levers-0.030
 brushes-0.028
Ma-0.026
uits-0.026
 swirl-0.026
TokenOne
Token ID3198
Feature activation+1.31e+00

Pos logit contributions
isher+0.079
eros+0.074
over+0.071
 Amen+0.071
mer+0.068
Neg logit contributions
 levers-0.057
 brushes-0.051
uits-0.049
 swirl-0.049
 ABC-0.049
Token day
Token ID1110
Feature activation+6.66e-01

Pos logit contributions
isher+0.018
eros+0.017
 Amen+0.016
over+0.015
mer+0.014
Neg logit contributions
 levers-0.036
 brushes-0.035
 swirl-0.033
uits-0.033
 ABC-0.033
Token,
Token ID11
Feature activation-5.50e-01

Pos logit contributions
isher+0.014
over+0.013
eros+0.013
 Amen+0.013
mer+0.012
Neg logit contributions
 levers-0.014
 brushes-0.012
 swirl-0.012
uits-0.012
 ABC-0.012
Token her
Token ID607
Feature activation+1.27e+00

Pos logit contributions
isher+0.013
over+0.012
eros+0.012
mer+0.011
 Amen+0.011
Neg logit contributions
 levers-0.007
 brushes-0.005
Ma-0.005
 swirl-0.005
 ABC-0.005
Token friends
Token ID2460
Feature activation-1.82e+00

Pos logit contributions
isher+0.020
eros+0.020
over+0.019
 Amen+0.018
mer+0.017
Neg logit contributions
 levers-0.033
 brushes-0.030
uits-0.029
 swirl-0.029
Ma-0.029
Token went
Token ID1816
Feature activation+1.78e+00

Pos logit contributions
 levers+0.028
uits+0.024
 brushes+0.024
 swirl+0.024
 blush+0.023
Neg logit contributions
isher-0.049
eros-0.048
over-0.046
 Amen-0.046
mer-0.043
Token home
Token ID1363
Feature activation+1.02e+00

Pos logit contributions
isher+0.039
eros+0.034
 Amen+0.034
jected+0.032
ised+0.032
Neg logit contributions
 levers-0.038
uits-0.037
 brushes-0.034
 names-0.034
 swirl-0.033
Token,
Token ID11
Feature activation-1.25e+00

Pos logit contributions
isher+0.029
eros+0.027
 Amen+0.026
over+0.025
boat+0.024
Neg logit contributions
 levers-0.015
uits-0.014
 brushes-0.013
 swirl-0.013
 ABC-0.013
Token happy
Token ID3772
Feature activation+3.43e+00

Pos logit contributions
 levers+0.024
 brushes+0.021
uits+0.020
 swirl+0.020
 ABC+0.020
Neg logit contributions
isher-0.029
eros-0.028
over-0.027
 Amen-0.026
mer-0.025
Token and
Token ID290
Feature activation+1.17e+00

Pos logit contributions
isher+0.095
 Amen+0.088
eros+0.085
over+0.083
boat+0.081
Neg logit contributions
 levers-0.051
 brushes-0.045
 swirl-0.045
 marks-0.045
 ABC-0.043
Token proud
Token ID6613
Feature activation+2.48e+00

Pos logit contributions
isher+0.031
eros+0.029
 Amen+0.026
over+0.026
ised+0.025
Neg logit contributions
 levers-0.020
 brushes-0.018
 swirl-0.017
uits-0.017
 blush-0.017
Token of
Token ID286
Feature activation+1.29e+00

Pos logit contributions
isher+0.068
 Amen+0.066
eros+0.063
boat+0.060
over+0.059
Neg logit contributions
 levers-0.035
 swirl-0.033
 marks-0.032
 brushes-0.031
 names-0.030
Token themselves
Token ID2405
Feature activation-6.42e-01

Pos logit contributions
isher+0.042
mer+0.040
boat+0.039
eros+0.038
ager+0.037
Neg logit contributions
 levers-0.012
 swirl-0.012
 laughs-0.011
 brushes-0.011
 numbers-0.011
Token for
Token ID329
Feature activation+1.02e+00

Pos logit contributions
 levers+0.011
uits+0.009
 swirl+0.009
 marks+0.009
 brushes+0.009
Neg logit contributions
isher-0.016
eros-0.015
 Amen-0.015
over-0.014
mer-0.014
Token,
Token ID11
Feature activation-7.02e-01

Pos logit contributions
 levers+0.024
 brushes+0.021
 swirl+0.021
 marks+0.020
 switches+0.020
Neg logit contributions
eros-0.016
over-0.015
isher-0.014
 Amen-0.014
ar-0.014
Token there
Token ID612
Feature activation-3.31e-01

Pos logit contributions
 levers+0.016
 brushes+0.015
uits+0.014
 swirl+0.014
 ABC+0.014
Neg logit contributions
isher-0.013
eros-0.012
over-0.012
 Amen-0.011
mer-0.011
Token was
Token ID373
Feature activation+2.00e-01

Pos logit contributions
 levers+0.008
 brushes+0.007
uits+0.007
 blush+0.007
 screens+0.007
Neg logit contributions
eros-0.006
isher-0.005
over-0.005
ter-0.005
date-0.005
Token a
Token ID257
Feature activation+4.87e-01

Pos logit contributions
over+0.004
isher+0.004
eros+0.004
 Amen+0.004
ter+0.004
Neg logit contributions
 levers-0.004
 brushes-0.004
uits-0.003
 ABC-0.003
 switches-0.003
Token little
Token ID1310
Feature activation+2.31e+00

Pos logit contributions
isher+0.012
eros+0.011
over+0.011
 Amen+0.011
ised+0.010
Neg logit contributions
 levers-0.008
 brushes-0.007
 swirl-0.007
 ABC-0.007
Ma-0.007
Token band
Token ID4097
Feature activation+3.51e+00

Pos logit contributions
isher+0.042
jected+0.039
edly+0.039
 Amen+0.039
eday+0.039
Neg logit contributions
 levers-0.050
 brushes-0.048
 swirl-0.046
 paints-0.043
 blush-0.043
Token.
Token ID13
Feature activation-2.60e-01

Pos logit contributions
isher+0.075
ised+0.061
eros+0.058
ishing+0.058
eday+0.057
Neg logit contributions
 ABC-0.068
 levers-0.068
 swirl-0.065
 marks-0.064
uits-0.063
Token The
Token ID383
Feature activation-5.26e-01

Pos logit contributions
 levers+0.006
 brushes+0.005
uits+0.005
 swirl+0.005
 ABC+0.005
Neg logit contributions
isher-0.005
eros-0.005
over-0.005
 Amen-0.005
mer-0.004
Token band
Token ID4097
Feature activation+2.30e+00

Pos logit contributions
 levers+0.015
 brushes+0.014
 swirl+0.013
 ABC+0.013
 marks+0.013
Neg logit contributions
isher-0.007
eros-0.007
over-0.006
 Amen-0.006
mer-0.006
Token was
Token ID373
Feature activation-2.57e-01

Pos logit contributions
isher+0.061
eros+0.055
 Amen+0.052
ishing+0.052
ised+0.051
Neg logit contributions
 levers-0.034
 brushes-0.034
 ABC-0.033
uits-0.030
 marks-0.030
Token made
Token ID925
Feature activation-1.27e+00

Pos logit contributions
 levers+0.003
 brushes+0.003
 swirl+0.003
 ABC+0.003
 marks+0.003
Neg logit contributions
isher-0.007
eros-0.007
over-0.007
mer-0.007
 Amen-0.007
Token,
Token ID11
Feature activation-5.98e-01

Pos logit contributions
 levers+0.020
 brushes+0.017
 swirl+0.017
 switches+0.016
 blush+0.016
Neg logit contributions
eros-0.014
over-0.014
isher-0.013
 Amen-0.013
ar-0.012
Token there
Token ID612
Feature activation-7.79e-01

Pos logit contributions
 levers+0.011
 brushes+0.010
Ma+0.010
 ABC+0.009
 swirl+0.009
Neg logit contributions
isher-0.014
eros-0.013
 Amen-0.012
over-0.012
bye-0.012
Token was
Token ID373
Feature activation+1.95e-01

Pos logit contributions
 levers+0.019
 brushes+0.016
uits+0.016
 blush+0.016
 screens+0.015
Neg logit contributions
eros-0.014
isher-0.013
over-0.013
 Amen-0.012
mer-0.012
Token a
Token ID257
Feature activation+2.24e-01

Pos logit contributions
isher+0.005
eros+0.005
over+0.005
 Amen+0.005
mer+0.004
Neg logit contributions
 levers-0.003
 brushes-0.003
uits-0.003
 swirl-0.003
 ABC-0.003
Token playful
Token ID34264
Feature activation+2.14e+00

Pos logit contributions
isher+0.005
eros+0.005
over+0.005
 Amen+0.005
ised+0.005
Neg logit contributions
 levers-0.004
 brushes-0.003
 swirl-0.003
 ABC-0.003
Ma-0.003
Token puppy
Token ID26188
Feature activation+3.47e+00

Pos logit contributions
isher+0.049
 Amen+0.045
ised+0.045
jected+0.044
well+0.044
Neg logit contributions
 levers-0.037
 swirl-0.036
 ABC-0.036
 brushes-0.035
 names-0.034
Token named
Token ID3706
Feature activation+1.40e+00

Pos logit contributions
isher+0.071
ised+0.059
eday+0.055
over+0.055
ishing+0.053
Neg logit contributions
 levers-0.070
 ABC-0.068
 swirl-0.068
 brushes-0.067
 marks-0.066
Token Max
Token ID5436
Feature activation-1.27e+00

Pos logit contributions
isher+0.028
eros+0.026
over+0.026
 Amen+0.025
mer+0.024
Neg logit contributions
 levers-0.031
 brushes-0.028
uits-0.027
 swirl-0.027
 ABC-0.026
Token.
Token ID13
Feature activation-9.89e-01

Pos logit contributions
 levers+0.022
 brushes+0.019
 swirl+0.018
uits+0.018
 marks+0.018
Neg logit contributions
isher-0.031
eros-0.030
over-0.029
 Amen-0.028
mer-0.027
Token Max
Token ID5436
Feature activation-2.31e+00

Pos logit contributions
 levers+0.023
 brushes+0.021
uits+0.020
 swirl+0.020
Ma+0.019
Neg logit contributions
eros-0.018
isher-0.017
 Amen-0.017
over-0.017
penter-0.016
Token loved
Token ID6151
Feature activation+1.48e+00

Pos logit contributions
 levers+0.055
 brushes+0.049
uits+0.048
Ma+0.047
 swirl+0.047
Neg logit contributions
eros-0.041
isher-0.040
 Amen-0.039
over-0.039
mer-0.036
Token again
Token ID757
Feature activation+2.76e+00

Pos logit contributions
 levers+0.040
 brushes+0.036
uits+0.034
 swirl+0.034
 ABC+0.034
Neg logit contributions
isher-0.035
eros-0.034
over-0.033
 Amen-0.032
mer-0.031
Token soon
Token ID2582
Feature activation+1.56e+00

Pos logit contributions
isher+0.071
eros+0.069
 Amen+0.066
over+0.061
jected+0.060
Neg logit contributions
 levers-0.045
 brushes-0.039
 swirl-0.038
uits-0.038
 marks-0.038
Token and
Token ID290
Feature activation+1.53e+00

Pos logit contributions
isher+0.040
eros+0.038
 Amen+0.037
over+0.035
mer+0.034
Neg logit contributions
 levers-0.026
 brushes-0.022
uits-0.022
 marks-0.022
 swirl-0.022
Token was
Token ID373
Feature activation+1.73e+00

Pos logit contributions
eros+0.038
isher+0.038
over+0.038
 Amen+0.036
mer+0.035
Neg logit contributions
 levers-0.026
 brushes-0.024
 swirl-0.023
 marks-0.022
 blush-0.022
Token happy
Token ID3772
Feature activation+3.38e+00

Pos logit contributions
isher+0.044
eros+0.043
mer+0.040
over+0.038
 Amen+0.038
Neg logit contributions
 levers-0.027
 swirl-0.025
uits-0.025
 brushes-0.024
Ma-0.024
Token he
Token ID339
Feature activation+3.56e+00

Pos logit contributions
isher+0.081
eros+0.078
 Amen+0.075
over+0.074
mer+0.071
Neg logit contributions
 levers-0.060
 swirl-0.053
 brushes-0.053
 marks-0.051
uits-0.051
Token had
Token ID550
Feature activation+3.00e+00

Pos logit contributions
isher+0.103
eros+0.100
 Amen+0.097
over+0.092
ised+0.092
Neg logit contributions
 levers-0.044
 swirl-0.035
 brushes-0.035
 smelled-0.035
 marks-0.033
Token such
Token ID884
Feature activation+3.73e-01

Pos logit contributions
eros+0.072
isher+0.071
 Amen+0.071
jack+0.064
mer+0.063
Neg logit contributions
 levers-0.053
 brushes-0.049
 swirl-0.048
uits-0.047
 marks-0.047
Token an
Token ID281
Feature activation-8.03e-01

Pos logit contributions
isher+0.011
eros+0.011
mer+0.010
over+0.010
 Amen+0.010
Neg logit contributions
 levers-0.005
 brushes-0.004
 swirl-0.004
 names-0.004
 marks-0.004
Token attractive
Token ID10966
Feature activation+2.12e+00

Pos logit contributions
 levers+0.016
 brushes+0.014
uits+0.014
 swirl+0.014
Ma+0.014
Neg logit contributions
isher-0.018
eros-0.017
over-0.016
 Amen-0.016
mer-0.015
Token pair
Token ID5166
Feature activation+1.66e+00

Pos logit contributions
isher+0.039
eros+0.038
over+0.036
 Amen+0.035
mer+0.034
Neg logit contributions
 levers-0.049
 brushes-0.045
uits-0.043
 swirl-0.043
 ABC-0.042
Token remind
Token ID7101
Feature activation+1.78e+00

Pos logit contributions
isher+0.039
eros+0.038
over+0.037
 Amen+0.035
mer+0.035
Neg logit contributions
 levers-0.021
 brushes-0.019
 swirl-0.018
uits-0.017
 names-0.017
Token everyone
Token ID2506
Feature activation-1.40e+00

Pos logit contributions
isher+0.049
 Amen+0.047
mer+0.047
eros+0.046
over+0.045
Neg logit contributions
 levers-0.025
 brushes-0.021
 marks-0.020
 numbers-0.020
 swirl-0.020
Token to
Token ID284
Feature activation+9.84e-01

Pos logit contributions
 levers+0.030
 brushes+0.027
uits+0.026
Ma+0.026
 swirl+0.025
Neg logit contributions
isher-0.027
eros-0.027
over-0.026
 Amen-0.026
mer-0.024
Token be
Token ID307
Feature activation+1.75e+00

Pos logit contributions
isher+0.028
eros+0.027
mer+0.025
over+0.025
ider+0.023
Neg logit contributions
 levers-0.014
 swirl-0.014
 brushes-0.014
uits-0.013
 names-0.013
Token careful
Token ID8161
Feature activation-1.34e+00

Pos logit contributions
isher+0.044
eros+0.044
ugg+0.039
mer+0.038
olph+0.038
Neg logit contributions
 levers-0.027
 swirl-0.026
 brushes-0.025
uits-0.025
 marks-0.024
Token and
Token ID290
Feature activation+9.29e-01

Pos logit contributions
 levers+0.025
 brushes+0.022
uits+0.021
 swirl+0.021
 ABC+0.021
Neg logit contributions
isher-0.031
eros-0.030
over-0.028
 Amen-0.028
mer-0.027
Token to
Token ID284
Feature activation+2.32e-01

Pos logit contributions
isher+0.026
eros+0.025
over+0.024
ase+0.024
date+0.023
Neg logit contributions
 levers-0.015
 brushes-0.014
 swirl-0.012
 names-0.012
 realize-0.012
Token always
Token ID1464
Feature activation+2.75e+00

Pos logit contributions
isher+0.007
eros+0.006
over+0.006
mer+0.006
ase+0.006
Neg logit contributions
 levers-0.003
 swirl-0.003
 brushes-0.003
 names-0.003
 realize-0.003
Token ask
Token ID1265
Feature activation+1.60e+00

Pos logit contributions
isher+0.082
eros+0.080
ase+0.073
over+0.073
mer+0.071
Neg logit contributions
 levers-0.038
 brushes-0.034
 swirl-0.033
 names-0.032
 marks-0.030
Token for
Token ID329
Feature activation+1.70e+00

Pos logit contributions
isher+0.036
eros+0.034
over+0.033
 Amen+0.033
mer+0.031
Neg logit contributions
 levers-0.031
 brushes-0.027
uits-0.026
 swirl-0.026
 ABC-0.026
Token help
Token ID1037
Feature activation-2.99e-01

Pos logit contributions
isher+0.043
eros+0.042
mer+0.041
over+0.041
 Amen+0.039
Neg logit contributions
 levers-0.030
 brushes-0.026
 swirl-0.025
 numbers-0.025
 marks-0.025
Token
Token ID198
Feature activation-9.67e-01

Pos logit contributions
 levers+0.013
 brushes+0.012
uits+0.012
 swirl+0.012
 ABC+0.011
Neg logit contributions
isher-0.011
eros-0.010
over-0.010
 Amen-0.010
mer-0.009
Token
Token ID198
Feature activation-5.12e-02

Pos logit contributions
 levers+0.024
 brushes+0.022
 blush+0.021
 swirl+0.021
 switches+0.020
Neg logit contributions
eros-0.016
 Amen-0.015
over-0.015
isher-0.014
 Now-0.014
TokenThe
Token ID464
Feature activation+6.85e-01

Pos logit contributions
 levers+0.001
 brushes+0.001
uits+0.001
 swirl+0.001
 ABC+0.001
Neg logit contributions
isher-0.001
eros-0.001
over-0.001
 Amen-0.001
mer-0.001
Token farmer
Token ID18739
Feature activation+6.10e-01

Pos logit contributions
isher+0.016
over+0.014
ised+0.014
eros+0.014
date+0.014
Neg logit contributions
 levers-0.014
 marks-0.012
 numbers-0.012
 brushes-0.012
 names-0.012
Token is
Token ID318
Feature activation+9.82e-01

Pos logit contributions
isher+0.017
over+0.017
eros+0.016
 Amen+0.016
ised+0.016
Neg logit contributions
 levers-0.008
 brushes-0.007
 marks-0.006
 swirl-0.006
 ABC-0.006
Token nice
Token ID3621
Feature activation+2.20e+00

Pos logit contributions
isher+0.027
eros+0.025
over+0.024
mer+0.024
 Amen+0.024
Neg logit contributions
 levers-0.015
 brushes-0.013
uits-0.012
 swirl-0.012
 marks-0.012
Token.
Token ID13
Feature activation+4.39e-01

Pos logit contributions
isher+0.061
 Amen+0.058
eros+0.058
ised+0.056
over+0.055
Neg logit contributions
 levers-0.031
 marks-0.028
 brushes-0.026
 names-0.026
 numbers-0.025
Token He
Token ID679
Feature activation+1.90e+00

Pos logit contributions
isher+0.008
eros+0.008
over+0.008
 Amen+0.007
mer+0.007
Neg logit contributions
 levers-0.010
 brushes-0.009
uits-0.009
 ABC-0.009
 swirl-0.009
Token gives
Token ID3607
Feature activation+2.62e+00

Pos logit contributions
isher+0.045
eros+0.045
 Amen+0.043
over+0.042
mer+0.041
Neg logit contributions
 levers-0.033
 brushes-0.028
uits-0.027
Ma-0.027
 swirl-0.027
Token Tom
Token ID4186
Feature activation-3.65e+00

Pos logit contributions
isher+0.063
eros+0.061
over+0.059
 Amen+0.059
mer+0.056
Neg logit contributions
 levers-0.047
 brushes-0.041
uits-0.039
 swirl-0.038
 ABC-0.038
Token and
Token ID290
Feature activation+3.24e-01

Pos logit contributions
 levers+0.069
 brushes+0.059
uits+0.057
 swirl+0.057
 switches+0.056
Neg logit contributions
isher-0.083
eros-0.082
over-0.079
 Amen-0.075
ter-0.073
Token forgiving
Token ID43486
Feature activation+3.12e-02

Pos logit contributions
isher+0.014
eros+0.014
over+0.014
ase+0.014
date+0.013
Neg logit contributions
 levers-0.008
 brushes-0.008
 names-0.008
 numbers-0.008
 swirl-0.007
Token.
Token ID13
Feature activation+9.09e-01

Pos logit contributions
isher+0.001
eros+0.001
over+0.001
 Amen+0.001
mer+0.001
Neg logit contributions
 levers-0.001
 brushes-0.001
uits-0.001
 swirl-0.001
 ABC-0.001
Token<|endoftext|>
Token ID50256
Feature activation+3.39e+00

Pos logit contributions
isher+0.020
eros+0.018
mer+0.018
over+0.018
 reunited+0.017
Neg logit contributions
 levers-0.018
 ABC-0.016
 names-0.016
 brushes-0.016
Ma-0.016
TokenL
Token ID43
Feature activation-1.49e+00

Pos logit contributions
isher+0.078
eros+0.073
 Amen+0.070
over+0.069
mer+0.066
Neg logit contributions
 levers-0.064
 brushes-0.057
 ABC-0.056
uits-0.055
 swirl-0.055
Tokenily
Token ID813
Feature activation-1.33e+00

Pos logit contributions
 levers+0.035
 brushes+0.030
 swirl+0.029
 switches+0.029
uits+0.028
Neg logit contributions
isher-0.029
eros-0.028
over-0.027
 Amen-0.025
 reunited-0.024
Token and
Token ID290
Feature activation+1.02e+00

Pos logit contributions
 levers+0.022
 brushes+0.019
uits+0.018
 swirl+0.018
 ABC+0.018
Neg logit contributions
isher-0.033
eros-0.032
over-0.031
 Amen-0.031
mer-0.029
Token Tom
Token ID4186
Feature activation-2.39e+00

Pos logit contributions
isher+0.027
eros+0.026
over+0.025
mer+0.025
 Amen+0.025
Neg logit contributions
 levers-0.016
 brushes-0.014
 swirl-0.013
uits-0.013
Ma-0.012
Token were
Token ID547
Feature activation+1.25e+00

Pos logit contributions
 levers+0.048
 brushes+0.041
uits+0.041
 swirl+0.040
 ABC+0.040
Neg logit contributions
isher-0.052
eros-0.050
over-0.048
 Amen-0.047
mer-0.046
Token bored
Token ID17533
Feature activation-4.63e-02

Pos logit contributions
isher+0.032
mer+0.030
eros+0.030
boat+0.029
fire+0.028
Neg logit contributions
 brushes-0.019
 levers-0.019
uits-0.018
 names-0.018
 ABC-0.018
Token.
Token ID13
Feature activation-4.46e-01

Pos logit contributions
 levers+0.001
 brushes+0.001
 marks+0.001
 swirl+0.001
 ABC+0.001
Neg logit contributions
eros-0.001
isher-0.001
 Amen-0.001
over-0.001
mer-0.001
Token The
Token ID383
Feature activation+1.16e+00

Pos logit contributions
 levers+0.008
 brushes+0.008
uits+0.007
 names+0.007
 ABC+0.007
Neg logit contributions
isher-0.010
eros-0.010
over-0.009
 Amen-0.009
ter-0.009
Token boy
Token ID2933
Feature activation+1.11e-01

Pos logit contributions
 levers+0.005
 brushes+0.005
 marks+0.005
 ABC+0.005
 swirl+0.005
Neg logit contributions
isher-0.004
eros-0.003
 Amen-0.003
over-0.003
ar-0.003
Token was
Token ID373
Feature activation+6.38e-01

Pos logit contributions
isher+0.003
 Amen+0.003
over+0.003
eros+0.003
date+0.003
Neg logit contributions
 levers-0.002
 brushes-0.001
 swirl-0.001
 marks-0.001
 ABC-0.001
Token so
Token ID523
Feature activation+9.28e-02

Pos logit contributions
isher+0.018
eros+0.017
mer+0.016
over+0.016
 Amen+0.015
Neg logit contributions
 levers-0.009
 swirl-0.008
 brushes-0.008
uits-0.008
Ma-0.008
Token excited
Token ID6568
Feature activation+1.57e+00

Pos logit contributions
isher+0.003
eros+0.002
 Amen+0.002
over+0.002
mer+0.002
Neg logit contributions
 levers-0.001
 brushes-0.001
 swirl-0.001
 sweat-0.001
Ma-0.001
Token.
Token ID13
Feature activation+6.78e-01

Pos logit contributions
isher+0.040
 Amen+0.038
eros+0.038
over+0.036
mer+0.035
Neg logit contributions
 levers-0.026
 brushes-0.023
 marks-0.022
uits-0.022
 swirl-0.022
Token He
Token ID679
Feature activation+2.42e+00

Pos logit contributions
isher+0.016
eros+0.015
over+0.015
 Amen+0.015
mer+0.014
Neg logit contributions
 levers-0.013
 brushes-0.012
 ABC-0.011
 names-0.011
Ma-0.011
Token thanked
Token ID26280
Feature activation+1.82e+00

Pos logit contributions
isher+0.054
eros+0.051
over+0.051
 Amen+0.049
mer+0.046
Neg logit contributions
 levers-0.049
 brushes-0.044
 swirl-0.042
uits-0.042
Ma-0.040
Token his
Token ID465
Feature activation+2.28e+00

Pos logit contributions
isher+0.047
eros+0.045
over+0.045
 Amen+0.043
mer+0.043
Neg logit contributions
 levers-0.029
 brushes-0.025
 swirl-0.024
uits-0.024
Ma-0.024
Token mother
Token ID2802
Feature activation+9.63e-01

Pos logit contributions
eros+0.048
isher+0.048
 Amen+0.045
over+0.044
mer+0.042
Neg logit contributions
 levers-0.046
 brushes-0.042
uits-0.041
 blush-0.039
 swirl-0.038
Token and
Token ID290
Feature activation+2.40e+00

Pos logit contributions
isher+0.025
eros+0.024
over+0.023
 Amen+0.023
mer+0.022
Neg logit contributions
 levers-0.015
 brushes-0.013
uits-0.013
 ABC-0.013
 swirl-0.013
Token she
Token ID673
Feature activation+3.42e+00

Pos logit contributions
isher+0.062
over+0.062
eros+0.060
mer+0.058
 Amen+0.058
Neg logit contributions
 levers-0.040
 brushes-0.036
 swirl-0.035
Ma-0.034
uits-0.032
Token.
Token ID13
Feature activation-2.28e-02

Pos logit contributions
 levers+0.013
 brushes+0.011
 swirl+0.011
 marks+0.011
uits+0.011
Neg logit contributions
isher-0.018
eros-0.017
 Amen-0.016
over-0.016
ised-0.015
Token He
Token ID679
Feature activation+1.55e+00

Pos logit contributions
 levers+0.000
 brushes+0.000
uits+0.000
 swirl+0.000
Ma+0.000
Neg logit contributions
isher-0.001
eros-0.000
over-0.000
 Amen-0.000
mer-0.000
Token gave
Token ID2921
Feature activation+2.01e+00

Pos logit contributions
isher+0.031
eros+0.030
over+0.028
 Amen+0.028
mer+0.027
Neg logit contributions
 levers-0.034
 brushes-0.030
uits-0.029
 ABC-0.029
 swirl-0.029
Token Ben
Token ID3932
Feature activation-3.62e+00

Pos logit contributions
isher+0.048
eros+0.047
over+0.046
 Amen+0.045
mer+0.043
Neg logit contributions
 levers-0.036
 brushes-0.031
uits-0.030
 swirl-0.030
 ABC-0.029
Token a
Token ID257
Feature activation-6.25e-01

Pos logit contributions
 levers+0.071
 brushes+0.062
uits+0.059
 switches+0.059
 swirl+0.059
Neg logit contributions
isher-0.080
eros-0.078
over-0.075
 Amen-0.072
 reunited-0.070
Token kiss
Token ID9245
Feature activation+7.97e-01

Pos logit contributions
 levers+0.012
 switches+0.010
Ma+0.010
 brushes+0.010
 ABC+0.010
Neg logit contributions
isher-0.013
eros-0.013
 Amen-0.012
boat-0.012
over-0.012
Token on
Token ID319
Feature activation-1.77e+00

Pos logit contributions
isher+0.022
eros+0.021
ised+0.021
 Amen+0.021
over+0.020
Neg logit contributions
 levers-0.011
 marks-0.009
 swirl-0.009
uits-0.009
 brushes-0.009
Token the
Token ID262
Feature activation-4.13e-01

Pos logit contributions
 levers+0.033
 brushes+0.029
uits+0.028
 swirl+0.028
 ABC+0.027
Neg logit contributions
isher-0.041
eros-0.040
over-0.039
 Amen-0.038
mer-0.036
Token cheek
Token ID19353
Feature activation-6.70e-01

Pos logit contributions
 levers+0.009
 brushes+0.008
uits+0.008
Ma+0.008
 ABC+0.008
Neg logit contributions
isher-0.008
eros-0.008
over-0.007
 Amen-0.007
mer-0.007
Token.
Token ID13
Feature activation-1.78e-01

Pos logit contributions
 levers+0.012
 brushes+0.011
uits+0.010
 swirl+0.010
 marks+0.010
Neg logit contributions
isher-0.016
eros-0.015
 Amen-0.015
over-0.015
mer-0.014
Token Ben
Token ID3932
Feature activation-1.89e+00

Pos logit contributions
 levers+0.004
 brushes+0.003
uits+0.003
 swirl+0.003
 ABC+0.003
Neg logit contributions
isher-0.004
eros-0.004
over-0.004
 Amen-0.003
mer-0.003
Token lost
Token ID2626
Feature activation-8.96e-01

Pos logit contributions
 levers+0.010
 brushes+0.009
 marks+0.008
uits+0.007
 swirl+0.007
Neg logit contributions
isher-0.028
eros-0.027
over-0.027
 Amen-0.027
mer-0.025
Token the
Token ID262
Feature activation-2.24e-01

Pos logit contributions
 levers+0.021
 brushes+0.019
uits+0.019
 swirl+0.018
 ABC+0.018
Neg logit contributions
isher-0.016
eros-0.016
over-0.015
 Amen-0.014
ter-0.014
Token game
Token ID983
Feature activation-6.65e-01

Pos logit contributions
 levers+0.004
 brushes+0.004
uits+0.004
 swirl+0.004
 ABC+0.004
Neg logit contributions
isher-0.005
eros-0.005
over-0.005
 Amen-0.005
mer-0.004
Token."
Token ID526
Feature activation-8.18e-01

Pos logit contributions
 levers+0.013
 brushes+0.011
uits+0.011
 swirl+0.011
 marks+0.011
Neg logit contributions
isher-0.015
eros-0.015
 Amen-0.014
over-0.014
ised-0.013
Token<|endoftext|>
Token ID50256
Feature activation+3.51e+00

Pos logit contributions
 levers+0.019
 brushes+0.017
 swirl+0.016
uits+0.016
 ABC+0.016
Neg logit contributions
eros-0.015
isher-0.015
over-0.015
 Amen-0.014
mer-0.013
TokenL
Token ID43
Feature activation-1.41e+00

Pos logit contributions
isher+0.084
eros+0.077
 Amen+0.075
over+0.074
penter+0.072
Neg logit contributions
 levers-0.062
 brushes-0.056
 marks-0.055
 ABC-0.054
 swirl-0.054
Tokenily
Token ID813
Feature activation-2.55e+00

Pos logit contributions
 levers+0.028
 brushes+0.024
 swirl+0.024
 ABC+0.023
 switches+0.023
Neg logit contributions
isher-0.032
eros-0.031
over-0.030
 Amen-0.027
 reunited-0.027
Token and
Token ID290
Feature activation+7.02e-01

Pos logit contributions
 levers+0.046
 brushes+0.038
uits+0.038
 swirl+0.038
Ma+0.038
Neg logit contributions
isher-0.060
eros-0.058
over-0.056
 Amen-0.054
mer-0.053
Token Ben
Token ID3932
Feature activation-2.94e+00

Pos logit contributions
isher+0.017
eros+0.017
over+0.016
 Amen+0.016
mer+0.015
Neg logit contributions
 levers-0.012
 brushes-0.011
uits-0.010
 swirl-0.010
 ABC-0.010
Token are
Token ID389
Feature activation+9.54e-01

Pos logit contributions
 levers+0.056
Ma+0.049
 ABC+0.049
uits+0.047
 swirl+0.047
Neg logit contributions
isher-0.064
eros-0.059
over-0.059
 reunited-0.057
mer-0.057
Token friends
Token ID2460
Feature activation+4.27e-02

Pos logit contributions
isher+0.023
eros+0.022
mer+0.022
boat+0.021
fire+0.020
Neg logit contributions
 brushes-0.016
 levers-0.016
uits-0.015
 marks-0.015
 names-0.015
Token decide
Token ID5409
Feature activation-4.80e-01

Pos logit contributions
 levers+0.012
 ABC+0.010
Ma+0.010
uits+0.010
 switches+0.010
Neg logit contributions
isher-0.014
 Amen-0.014
eros-0.013
 reunited-0.013
penter-0.013
Token to
Token ID284
Feature activation+1.55e+00

Pos logit contributions
 levers+0.010
 brushes+0.008
Ma+0.008
uits+0.008
 swirl+0.008
Neg logit contributions
isher-0.010
eros-0.010
 Amen-0.009
over-0.009
ter-0.009
Token play
Token ID711
Feature activation-1.90e-01

Pos logit contributions
isher+0.041
eros+0.040
over+0.040
mer+0.038
ised+0.035
Neg logit contributions
 brushes-0.024
 levers-0.024
 swirl-0.024
 blush-0.022
 names-0.022
Token together
Token ID1978
Feature activation-2.65e-01

Pos logit contributions
 levers+0.004
 brushes+0.003
 swirl+0.003
 marks+0.003
 blush+0.003
Neg logit contributions
isher-0.004
eros-0.004
 Amen-0.004
boat-0.004
over-0.004
Token and
Token ID290
Feature activation+1.54e+00

Pos logit contributions
 levers+0.004
 brushes+0.004
 swirl+0.004
 ABC+0.004
uits+0.004
Neg logit contributions
isher-0.007
eros-0.007
 Amen-0.006
over-0.006
boat-0.006
Token share
Token ID2648
Feature activation-4.49e-01

Pos logit contributions
isher+0.045
eros+0.044
over+0.042
mer+0.040
ised+0.040
Neg logit contributions
 levers-0.022
 brushes-0.021
 blush-0.020
 swirl-0.020
 names-0.018
Token their
Token ID511
Feature activation-1.51e+00

Pos logit contributions
 levers+0.010
Ma+0.009
uits+0.009
 brushes+0.009
 switches+0.009
Neg logit contributions
isher-0.008
eros-0.008
over-0.008
 Amen-0.007
ised-0.007
Token toys
Token ID14958
Feature activation-2.64e+00

Pos logit contributions
 levers+0.025
 brushes+0.023
 ABC+0.021
 swirl+0.021
 marks+0.021
Neg logit contributions
isher-0.038
over-0.037
eros-0.037
 Amen-0.036
mer-0.035
Token.
Token ID13
Feature activation-5.48e-02

Pos logit contributions
 levers+0.042
 brushes+0.039
 swirl+0.037
uits+0.037
 marks+0.037
Neg logit contributions
isher-0.067
eros-0.066
 Amen-0.064
over-0.062
date-0.057
Token They
Token ID1119
Feature activation-9.95e-01

Pos logit contributions
 levers+0.001
 brushes+0.001
 swirl+0.001
uits+0.001
 ABC+0.001
Neg logit contributions
isher-0.001
eros-0.001
over-0.001
 Amen-0.001
mer-0.001
Token find
Token ID1064
Feature activation+7.13e-01

Pos logit contributions
 levers+0.016
 brushes+0.013
Ma+0.013
uits+0.013
 ABC+0.013
Neg logit contributions
isher-0.024
 Amen-0.024
eros-0.023
over-0.022
mer-0.022
Token was
Token ID373
Feature activation-9.65e-01

Pos logit contributions
 levers+0.015
 brushes+0.013
uits+0.013
 ABC+0.013
Ma+0.013
Neg logit contributions
isher-0.017
eros-0.017
over-0.016
mer-0.015
boat-0.015
Token caught
Token ID4978
Feature activation-6.85e-01

Pos logit contributions
 levers+0.018
 brushes+0.016
 swirl+0.015
uits+0.015
 ABC+0.015
Neg logit contributions
isher-0.022
eros-0.022
over-0.021
 Amen-0.021
mer-0.020
Token in
Token ID287
Feature activation-1.72e+00

Pos logit contributions
 levers+0.014
 brushes+0.013
 swirl+0.012
uits+0.012
 marks+0.012
Neg logit contributions
isher-0.014
eros-0.014
 Amen-0.013
over-0.013
mer-0.012
Token a
Token ID257
Feature activation-1.35e+00

Pos logit contributions
 levers+0.031
 brushes+0.028
uits+0.027
 ABC+0.026
 swirl+0.026
Neg logit contributions
isher-0.040
eros-0.039
over-0.038
 Amen-0.037
mer-0.036
Token hole
Token ID7604
Feature activation-8.83e-02

Pos logit contributions
 levers+0.025
 brushes+0.022
 swirl+0.021
uits+0.021
 ABC+0.020
Neg logit contributions
isher-0.031
eros-0.031
over-0.029
 Amen-0.029
mer-0.028
Token.
Token ID13
Feature activation-3.35e-01

Pos logit contributions
 levers+0.002
 brushes+0.001
uits+0.001
 swirl+0.001
 marks+0.001
Neg logit contributions
isher-0.002
eros-0.002
 Amen-0.002
over-0.002
mer-0.002
Token Tim
Token ID5045
Feature activation-2.60e+00

Pos logit contributions
 levers+0.007
 brushes+0.006
uits+0.006
 swirl+0.006
Ma+0.006
Neg logit contributions
isher-0.007
eros-0.007
over-0.007
 Amen-0.007
mer-0.006
Tokenmy
Token ID1820
Feature activation-1.21e+00

Pos logit contributions
 levers+0.046
 brushes+0.040
uits+0.038
 swirl+0.038
 ABC+0.038
Neg logit contributions
isher-0.062
eros-0.061
over-0.059
 Amen-0.058
mer-0.055
Token helped
Token ID4193
Feature activation+4.12e-02

Pos logit contributions
 levers+0.020
 brushes+0.018
 swirl+0.017
 marks+0.017
Ma+0.016
Neg logit contributions
isher-0.031
eros-0.029
over-0.029
 Amen-0.029
mer-0.027
Token Ricky
Token ID31668
Feature activation-3.06e+00

Pos logit contributions
isher+0.001
eros+0.001
over+0.001
 Amen+0.001
mer+0.001
Neg logit contributions
 levers-0.001
 brushes-0.001
uits-0.001
 ABC-0.001
 blush-0.001
Token get
Token ID651
Feature activation-8.70e-01

Pos logit contributions
 levers+0.050
 brushes+0.043
 swirl+0.041
uits+0.041
 ABC+0.040
Neg logit contributions
isher-0.078
eros-0.076
over-0.074
 Amen-0.073
mer-0.070
Token.
Token ID13
Feature activation-5.30e-01

Pos logit contributions
isher+0.053
eros+0.048
 Amen+0.047
over+0.044
ised+0.043
Neg logit contributions
 brushes-0.033
 levers-0.033
uits-0.031
 names-0.030
 marks-0.029
Token Mia
Token ID32189
Feature activation-2.46e+00

Pos logit contributions
 levers+0.013
 switches+0.011
 screens+0.011
 ABC+0.011
uits+0.011
Neg logit contributions
 Now-0.009
apped-0.009
over-0.008
eros-0.008
 Amen-0.008
Token saw
Token ID2497
Feature activation-6.02e-01

Pos logit contributions
 levers+0.057
uits+0.050
 swirl+0.050
 brushes+0.049
Ma+0.048
Neg logit contributions
isher-0.044
eros-0.043
over-0.041
mer-0.040
 Amen-0.040
Token many
Token ID867
Feature activation-1.19e+00

Pos logit contributions
 levers+0.014
uits+0.012
 ABC+0.012
 brushes+0.012
 widen+0.012
Neg logit contributions
eros-0.010
ter-0.010
isher-0.010
 reunited-0.009
over-0.009
Token trees
Token ID7150
Feature activation-2.56e+00

Pos logit contributions
 levers+0.028
uits+0.027
Ma+0.026
 blush+0.024
 fingertips+0.024
Neg logit contributions
eros-0.019
ised-0.018
isher-0.018
over-0.018
 hunter-0.017
Token,
Token ID11
Feature activation-2.86e+00

Pos logit contributions
 levers+0.047
 brushes+0.041
uits+0.039
 swirl+0.038
Ma+0.038
Neg logit contributions
isher-0.059
eros-0.058
over-0.056
 Amen-0.055
mer-0.053
Token flowers
Token ID12734
Feature activation-2.79e+00

Pos logit contributions
 levers+0.058
Ma+0.052
uits+0.050
 ABC+0.049
 fingertips+0.049
Neg logit contributions
 alone-0.054
ter-0.053
over-0.047
mer-0.047
 hunter-0.047
Token,
Token ID11
Feature activation-3.80e+00

Pos logit contributions
 levers+0.054
 brushes+0.047
uits+0.045
 ABC+0.044
 swirl+0.044
Neg logit contributions
isher-0.062
eros-0.061
over-0.059
 Amen-0.057
mer-0.055
Token and
Token ID290
Feature activation-1.69e+00

Pos logit contributions
 levers+0.098
Ma+0.087
uits+0.085
 fingertips+0.085
 switches+0.084
Neg logit contributions
ter-0.055
 alone-0.050
 hunter-0.046
 together-0.045
eros-0.044
Token birds
Token ID10087
Feature activation-1.54e+00

Pos logit contributions
 levers+0.031
uits+0.029
Ma+0.027
 ABC+0.027
 brushes+0.026
Neg logit contributions
isher-0.033
ter-0.033
 Amen-0.032
eros-0.032
over-0.032
Token.
Token ID13
Feature activation-9.41e-01

Pos logit contributions
 levers+0.023
 brushes+0.020
 swirl+0.020
 marks+0.020
 blush+0.019
Neg logit contributions
isher-0.044
eros-0.040
 Amen-0.039
over-0.038
mer-0.037
Token
Token ID198
Feature activation+3.41e-01

Pos logit contributions
 levers+0.012
 brushes+0.011
uits+0.010
 swirl+0.010
 ABC+0.010
Neg logit contributions
isher-0.012
eros-0.012
over-0.011
 Amen-0.011
mer-0.011
TokenThe
Token ID464
Feature activation-4.29e-01

Pos logit contributions
isher+0.010
eros+0.009
over+0.009
 Amen+0.009
mer+0.009
Neg logit contributions
 levers-0.005
 brushes-0.004
Ma-0.004
 swirl-0.004
uits-0.004
Token bird
Token ID6512
Feature activation+1.85e+00

Pos logit contributions
 levers+0.008
 brushes+0.008
 marks+0.008
 swirl+0.008
 ABC+0.007
Neg logit contributions
isher-0.010
over-0.010
mer-0.009
date-0.009
 Amen-0.009
Token nodded
Token ID14464
Feature activation-4.72e-02

Pos logit contributions
isher+0.047
over+0.045
eros+0.043
 Amen+0.042
date+0.040
Neg logit contributions
 levers-0.030
 swirl-0.029
 brushes-0.028
 blush-0.027
 marks-0.027
Token and
Token ID290
Feature activation+1.75e+00

Pos logit contributions
 levers+0.001
 brushes+0.001
 swirl+0.001
uits+0.001
 marks+0.001
Neg logit contributions
isher-0.001
eros-0.001
over-0.001
 Amen-0.001
mer-0.001
Token said
Token ID531
Feature activation-1.34e+00

Pos logit contributions
over+0.047
isher+0.047
 Amen+0.045
date+0.044
eros+0.044
Neg logit contributions
 levers-0.029
 brushes-0.027
 swirl-0.027
 blush-0.024
Ma-0.023
Token,
Token ID11
Feature activation-1.78e+00

Pos logit contributions
 levers+0.023
 brushes+0.021
 swirl+0.020
uits+0.020
 ABC+0.019
Neg logit contributions
isher-0.033
eros-0.031
over-0.031
 Amen-0.030
mer-0.029
Token "
Token ID366
Feature activation+1.02e+00

Pos logit contributions
 levers+0.028
 brushes+0.024
 swirl+0.023
uits+0.023
 ABC+0.022
Neg logit contributions
isher-0.048
eros-0.045
over-0.045
 Amen-0.043
mer-0.042
TokenYes
Token ID5297
Feature activation-1.32e+00

Pos logit contributions
isher+0.025
eros+0.024
 reunited+0.023
over+0.023
ishing+0.022
Neg logit contributions
 levers-0.018
 brushes-0.016
 swirl-0.016
Ma-0.016
 blush-0.015
Token,
Token ID11
Feature activation-1.69e+00

Pos logit contributions
 levers+0.033
 brushes+0.030
 switches+0.028
 ABC+0.028
uits+0.028
Neg logit contributions
eros-0.023
isher-0.023
over-0.021
ter-0.021
ar-0.020
Token yes
Token ID3763
Feature activation-3.17e-01

Pos logit contributions
 levers+0.039
 brushes+0.036
 swirl+0.034
uits+0.034
 ABC+0.034
Neg logit contributions
isher-0.031
eros-0.030
over-0.029
 Amen-0.028
mer-0.027
Token a
Token ID257
Feature activation-1.00e+00

Pos logit contributions
 levers+0.020
uits+0.018
 brushes+0.017
Ma+0.017
 ABC+0.017
Neg logit contributions
isher-0.026
eros-0.025
over-0.024
 Amen-0.023
ter-0.023
Token woman
Token ID2415
Feature activation+7.91e-01

Pos logit contributions
 levers+0.020
 brushes+0.018
uits+0.018
Ma+0.017
 ABC+0.017
Neg logit contributions
isher-0.021
eros-0.021
over-0.020
 Amen-0.020
mer-0.019
Token.
Token ID13
Feature activation-6.02e-01

Pos logit contributions
isher+0.020
eros+0.019
ised+0.018
 Amen+0.018
over+0.017
Neg logit contributions
 levers-0.013
 brushes-0.012
 blush-0.011
 swirl-0.011
 marks-0.011
Token Tim
Token ID5045
Feature activation-3.09e+00

Pos logit contributions
 levers+0.013
 brushes+0.011
uits+0.011
 swirl+0.011
 marks+0.011
Neg logit contributions
eros-0.012
isher-0.011
 Amen-0.011
over-0.011
mer-0.010
Token and
Token ID290
Feature activation-3.32e-01

Pos logit contributions
 levers+0.058
uits+0.050
 brushes+0.047
 swirl+0.047
Ma+0.046
Neg logit contributions
eros-0.070
isher-0.070
 Amen-0.065
over-0.064
mer-0.064
Token Sam
Token ID3409
Feature activation-4.97e+00

Pos logit contributions
 levers+0.006
uits+0.005
 brushes+0.005
 ABC+0.005
 swirl+0.005
Neg logit contributions
isher-0.007
eros-0.007
 Amen-0.007
over-0.007
ter-0.007
Token pull
Token ID2834
Feature activation-2.30e+00

Pos logit contributions
 levers+0.078
Ma+0.068
uits+0.066
 ABC+0.066
 brushes+0.063
Neg logit contributions
isher-0.117
eros-0.116
 Amen-0.115
mer-0.113
over-0.111
Token the
Token ID262
Feature activation-2.13e+00

Pos logit contributions
 levers+0.046
uits+0.044
 ABC+0.043
 brushes+0.043
Ma+0.043
Neg logit contributions
isher-0.042
over-0.041
eros-0.040
ter-0.037
mer-0.037
Token doll
Token ID3654
Feature activation-2.08e+00

Pos logit contributions
 levers+0.041
uits+0.038
Ma+0.036
 brushes+0.035
 swirl+0.034
Neg logit contributions
isher-0.046
eros-0.045
over-0.042
 Amen-0.041
ter-0.040
Token out
Token ID503
Feature activation-2.24e+00

Pos logit contributions
 levers+0.044
 brushes+0.039
uits+0.039
Ma+0.038
 ABC+0.038
Neg logit contributions
isher-0.041
eros-0.039
over-0.039
 Amen-0.037
mer-0.037
Token of
Token ID286
Feature activation+2.78e-01

Pos logit contributions
 levers+0.053
 brushes+0.049
 ABC+0.049
uits+0.047
 blush+0.047
Neg logit contributions
isher-0.035
over-0.033
eros-0.032
mer-0.031
ised-0.030
Token happy
Token ID3772
Feature activation+1.76e+00

Pos logit contributions
isher+0.001
eros+0.001
over+0.001
 Amen+0.001
mer+0.001
Neg logit contributions
 levers-0.001
 brushes-0.001
uits-0.001
 ABC-0.001
 swirl-0.001
Token.
Token ID13
Feature activation-1.60e-01

Pos logit contributions
isher+0.044
eros+0.041
 Amen+0.040
over+0.040
boat+0.038
Neg logit contributions
 levers-0.031
 brushes-0.028
 swirl-0.027
 marks-0.026
 ABC-0.026
Token<|endoftext|>
Token ID50256
Feature activation+3.02e+00

Pos logit contributions
 levers+0.004
 brushes+0.003
uits+0.003
 swirl+0.003
 ABC+0.003
Neg logit contributions
isher-0.003
eros-0.003
over-0.003
 Amen-0.003
mer-0.003
TokenTim
Token ID14967
Feature activation-2.92e+00

Pos logit contributions
isher+0.067
eros+0.063
 Amen+0.060
over+0.060
mer+0.057
Neg logit contributions
 levers-0.059
 brushes-0.054
 marks-0.051
 ABC-0.051
 swirl-0.051
Token and
Token ID290
Feature activation+8.91e-01

Pos logit contributions
 levers+0.054
 brushes+0.045
uits+0.045
 swirl+0.044
 ABC+0.043
Neg logit contributions
isher-0.069
eros-0.067
over-0.064
 Amen-0.062
mer-0.061
Token Mia
Token ID32189
Feature activation-3.59e+00

Pos logit contributions
isher+0.022
eros+0.021
over+0.020
 Amen+0.019
mer+0.019
Neg logit contributions
 levers-0.016
 brushes-0.014
uits-0.013
 swirl-0.013
Ma-0.013
Token liked
Token ID8288
Feature activation+1.40e+00

Pos logit contributions
 levers+0.059
uits+0.047
Ma+0.046
 switches+0.045
 ABC+0.044
Neg logit contributions
isher-0.090
eros-0.086
over-0.086
mer-0.085
bye-0.084
Token to
Token ID284
Feature activation+6.06e-01

Pos logit contributions
isher+0.033
eros+0.032
over+0.031
 Amen+0.030
mer+0.029
Neg logit contributions
 levers-0.025
 brushes-0.022
uits-0.021
 swirl-0.021
Ma-0.021
Token play
Token ID711
Feature activation-8.31e-02

Pos logit contributions
isher+0.009
 Amen+0.009
eros+0.009
over+0.008
date+0.008
Neg logit contributions
 levers-0.016
Ma-0.014
uits-0.013
 brushes-0.013
 switches-0.013
Token with
Token ID351
Feature activation+5.47e-01

Pos logit contributions
 swirl+0.001
 marks+0.001
 hoops+0.001
 brushes+0.001
 levers+0.001
Neg logit contributions
 Amen-0.002
isher-0.002
eros-0.002
bye-0.002
well-0.002
Token the
Token ID262
Feature activation-8.78e-01

Pos logit contributions
isher+0.010
eros+0.010
ised+0.009
over+0.009
olph+0.009
Neg logit contributions
 levers-0.012
uits-0.011
Ma-0.011
 widen-0.010
 ABC-0.010
Token Sam
Token ID3409
Feature activation-3.43e+00

Pos logit contributions
 levers+0.036
 brushes+0.032
uits+0.030
 swirl+0.030
 marks+0.029
Neg logit contributions
isher-0.050
eros-0.049
 Amen-0.048
over-0.047
mer-0.045
Token hurt
Token ID5938
Feature activation-8.05e-01

Pos logit contributions
 levers+0.067
 brushes+0.059
uits+0.058
Ma+0.057
 swirl+0.057
Neg logit contributions
isher-0.074
eros-0.072
over-0.070
 Amen-0.068
mer-0.066
Token himself
Token ID2241
Feature activation-2.02e+00

Pos logit contributions
 levers+0.017
 brushes+0.016
uits+0.015
 ABC+0.015
 swirl+0.015
Neg logit contributions
isher-0.016
eros-0.015
over-0.015
ter-0.014
mer-0.014
Token and
Token ID290
Feature activation-4.42e-01

Pos logit contributions
 levers+0.036
 brushes+0.031
 marks+0.030
 swirl+0.030
 ABC+0.030
Neg logit contributions
isher-0.049
eros-0.048
 Amen-0.046
over-0.045
mer-0.043
Token made
Token ID925
Feature activation-2.65e+00

Pos logit contributions
 levers+0.009
 brushes+0.008
 swirl+0.007
 marks+0.007
uits+0.007
Neg logit contributions
isher-0.010
eros-0.010
over-0.010
 Amen-0.009
mer-0.009
Token Tom
Token ID4186
Feature activation-3.80e+00

Pos logit contributions
 levers+0.060
 brushes+0.055
uits+0.054
 ABC+0.053
Ma+0.052
Neg logit contributions
isher-0.048
eros-0.045
over-0.044
 Amen-0.041
 reunited-0.040
Token cry
Token ID3960
Feature activation-7.35e-01

Pos logit contributions
 levers+0.067
 brushes+0.058
uits+0.057
Ma+0.055
 swirl+0.055
Neg logit contributions
isher-0.089
over-0.086
eros-0.086
 Amen-0.083
 reunited-0.080
Token.
Token ID13
Feature activation-1.48e+00

Pos logit contributions
 levers+0.014
 brushes+0.012
 swirl+0.012
 marks+0.011
 ABC+0.011
Neg logit contributions
isher-0.017
eros-0.017
over-0.016
 Amen-0.016
mer-0.015
Token They
Token ID1119
Feature activation-1.15e+00

Pos logit contributions
 levers+0.037
 swirl+0.034
uits+0.034
 ABC+0.034
 brushes+0.033
Neg logit contributions
eros-0.022
over-0.022
 Amen-0.021
isher-0.021
 Now-0.020
Token were
Token ID547
Feature activation-3.49e-01

Pos logit contributions
 levers+0.025
 brushes+0.022
uits+0.022
 ABC+0.022
 swirl+0.021
Neg logit contributions
isher-0.023
eros-0.022
 Amen-0.021
over-0.020
mer-0.019
Token very
Token ID845
Feature activation-2.15e-01

Pos logit contributions
 levers+0.005
 brushes+0.004
 swirl+0.004
 marks+0.004
 switches+0.004
Neg logit contributions
isher-0.010
eros-0.009
over-0.009
mer-0.009
bye-0.009
Token had
Token ID550
Feature activation+1.04e+00

Pos logit contributions
isher+0.057
eros+0.055
over+0.053
 Amen+0.052
mer+0.049
Neg logit contributions
 levers-0.049
 brushes-0.043
 swirl-0.041
uits-0.041
 ABC-0.040
Token ever
Token ID1683
Feature activation+1.22e+00

Pos logit contributions
isher+0.019
eros+0.018
over+0.017
 Amen+0.017
mer+0.016
Neg logit contributions
 levers-0.025
 brushes-0.022
uits-0.021
 swirl-0.021
 ABC-0.021
Token been
Token ID587
Feature activation+1.41e+00

Pos logit contributions
isher+0.024
eros+0.023
over+0.022
 Amen+0.022
mer+0.021
Neg logit contributions
 levers-0.027
 brushes-0.024
uits-0.023
 swirl-0.023
 ABC-0.023
Token.
Token ID13
Feature activation+6.57e-01

Pos logit contributions
isher+0.031
eros+0.030
 Amen+0.029
over+0.028
mer+0.026
Neg logit contributions
 levers-0.027
 brushes-0.024
 swirl-0.024
uits-0.024
 marks-0.023
Token<|endoftext|>
Token ID50256
Feature activation+2.48e+00

Pos logit contributions
isher+0.018
eros+0.017
over+0.016
mer+0.016
ishing+0.015
Neg logit contributions
 levers-0.009
Ma-0.009
 brushes-0.008
 swirl-0.008
uits-0.008
TokenJ
Token ID41
Feature activation-3.56e+00

Pos logit contributions
isher+0.058
eros+0.054
over+0.052
 Amen+0.052
mer+0.049
Neg logit contributions
 levers-0.046
 brushes-0.041
uits-0.040
 ABC-0.039
 swirl-0.039
Tokenill
Token ID359
Feature activation-3.34e+00

Pos logit contributions
 levers+0.075
 switches+0.061
 swirl+0.060
 screens+0.059
 widen+0.056
Neg logit contributions
isher-0.080
over-0.079
eros-0.074
ase-0.073
ugg-0.073
Token was
Token ID373
Feature activation+7.07e-02

Pos logit contributions
 levers+0.066
 brushes+0.056
uits+0.055
 swirl+0.054
 ABC+0.054
Neg logit contributions
isher-0.073
eros-0.071
over-0.069
 Amen-0.067
mer-0.066
Token a
Token ID257
Feature activation+9.27e-01

Pos logit contributions
isher+0.002
eros+0.002
mer+0.002
 Amen+0.002
boat+0.001
Neg logit contributions
 levers-0.001
 brushes-0.001
 swirl-0.001
uits-0.001
 blush-0.001
Token three
Token ID1115
Feature activation+7.39e-01

Pos logit contributions
isher+0.022
eros+0.021
over+0.020
 Amen+0.019
boat+0.019
Neg logit contributions
 levers-0.016
 brushes-0.015
 swirl-0.014
 ABC-0.014
Ma-0.014
Token year
Token ID614
Feature activation+3.08e+00

Pos logit contributions
isher+0.011
eros+0.010
 Amen+0.009
over+0.009
ter+0.009
Neg logit contributions
 levers-0.019
 brushes-0.018
 swirl-0.018
 ABC-0.018
 marks-0.017
Token listen
Token ID6004
Feature activation-1.15e+00

Pos logit contributions
 levers+0.026
 brushes+0.023
uits+0.021
 swirl+0.021
 ABC+0.021
Neg logit contributions
isher-0.037
over-0.035
eros-0.035
 Amen-0.035
mer-0.033
Token.
Token ID13
Feature activation-2.42e-01

Pos logit contributions
 levers+0.026
 brushes+0.023
 swirl+0.022
Ma+0.022
uits+0.022
Neg logit contributions
isher-0.021
over-0.021
eros-0.021
 Amen-0.020
mer-0.019
Token She
Token ID1375
Feature activation-1.13e-01

Pos logit contributions
 levers+0.005
uits+0.005
 swirl+0.004
 brushes+0.004
Ma+0.004
Neg logit contributions
isher-0.005
over-0.005
eros-0.005
 Amen-0.004
 Now-0.004
Token p
Token ID279
Feature activation-6.29e-01

Pos logit contributions
 levers+0.002
uits+0.002
Ma+0.002
 ABC+0.002
 swirl+0.002
Neg logit contributions
isher-0.002
eros-0.002
ar-0.002
penter-0.002
ager-0.002
Tokeninches
Token ID45457
Feature activation-1.04e+00

Pos logit contributions
 levers+0.011
 swirl+0.009
 brushes+0.009
uits+0.009
 ABC+0.009
Neg logit contributions
isher-0.016
eros-0.015
over-0.014
 Amen-0.014
mer-0.014
Token Ben
Token ID3932
Feature activation-5.16e+00

Pos logit contributions
 levers+0.024
uits+0.023
 ABC+0.021
 brushes+0.021
 swirl+0.020
Neg logit contributions
isher-0.018
over-0.017
eros-0.017
ised-0.016
ter-0.016
Token's
Token ID338
Feature activation-1.80e+00

Pos logit contributions
 levers+0.101
 brushes+0.090
uits+0.090
Ma+0.085
 ABC+0.085
Neg logit contributions
isher-0.110
eros-0.106
over-0.106
 Amen-0.099
mer-0.098
Token hand
Token ID1021
Feature activation-2.28e+00

Pos logit contributions
 levers+0.036
uits+0.034
 brushes+0.033
Ma+0.033
 switches+0.032
Neg logit contributions
isher-0.036
eros-0.036
 Amen-0.032
over-0.031
mer-0.031
Token hard
Token ID1327
Feature activation-1.83e+00

Pos logit contributions
 levers+0.044
 brushes+0.039
uits+0.038
Ma+0.037
 ABC+0.037
Neg logit contributions
isher-0.050
eros-0.049
over-0.048
 Amen-0.046
mer-0.045
Token.
Token ID13
Feature activation-1.26e+00

Pos logit contributions
 levers+0.032
 brushes+0.028
 marks+0.027
uits+0.027
 ABC+0.026
Neg logit contributions
isher-0.045
eros-0.044
 Amen-0.043
over-0.042
mer-0.040
Token Ben
Token ID3932
Feature activation-4.03e+00

Pos logit contributions
 levers+0.027
 brushes+0.023
uits+0.023
 swirl+0.022
 ABC+0.022
Neg logit contributions
isher-0.025
over-0.025
eros-0.025
 Amen-0.023
 Now-0.023