INDEX
Explanations
instances of the word "blink" and its variations
New Auto-Interp
Negative Logits
TEGER
-0.17
rio
-0.15
aurus
-0.15
OURS
-0.15
addock
-0.14
ÅĻej
-0.14
aday
-0.14
aggi
-0.14
ogram
-0.14
ilon
-0.14
POSITIVE LOGITS
ingly
0.27
twice
0.24
ered
0.22
irk
0.21
Twice
0.19
blink
0.18
Blink
0.18
enheim
0.18
eye
0.17
-fast
0.17
Activations Density 0.005%