INDEX
Explanations
the word "pop" and its variations, indicating references to rising or increasing popularity or visibility
New Auto-Interp
Negative Logits
}{*}{}-0.93
)$\\
-0.84
)");
-0.83
%}
-0.80
\}\\
-0.80
"}")
-0.80
}\]
-0.79
"):
-0.78
__":
-0.78
hdashline
-0.78
POSITIVE LOGITS
pop
1.26
Pop
1.20
pop
1.17
Pop
1.17
pops
1.14
POP
1.13
popping
1.07
popped
1.02
Popo
1.00
POP
1.00
Activations Density 0.011%