INDEX
Explanations
occurrences of the word "blank" and its variations, indicating a focus on emptiness or absence
New Auto-Interp
Negative Logits
ekil
-0.18
ropic
-0.17
rious
-0.16
strict
-0.16
leigh
-0.16
gings
-0.15
antas
-0.15
wend
-0.15
zan
-0.15
rians
-0.15
POSITIVE LOGITS
eted
0.39
eting
0.37
slate
0.30
ety
0.27
Slate
0.25
canv
0.22
enburg
0.21
ens
0.20
Blank
0.20
canvas
0.20
Activations Density 0.007%