INDEX
Explanations
the pronoun "I" and its variations in different contexts
New Auto-Interp
Negative Logits
appe
-0.16
elpers
-0.14
alion
-0.14
oks
-0.14
ç±į
-0.14
obl
-0.14
ester
-0.13
ijken
-0.13
HIR
-0.13
anya
-0.13
POSITIVE LOGITS
Can
0.21
Don
0.19
Miss
0.19
Should
0.17
See
0.17
Worship
0.17
Will
0.17
Need
0.16
Cant
0.16
Met
0.16
Activations Density 0.105%