INDEX
Explanations
variations of the verb "to see" in different contexts
New Auto-Interp
Negative Logits
eryl
-0.18
Cassidy
-0.16
Jo
-0.15
ented
-0.15
iper
-0.14
ards
-0.14
Axe
-0.14
erras
-0.14
oplevel
-0.14
e
-0.14
POSITIVE LOGITS
batim
0.18
uns
0.18
izon
0.17
eneg
0.17
icker
0.17
.di
0.17
itable
0.17
ifiable
0.16
ırak
0.16
icer
0.15
Activations Density 0.014%