INDEX
Explanations
expressions of excitement or appreciation, particularly about food or shared experiences
New Auto-Interp
Negative Logits
aldi
-0.15
ayıp
-0.14
âĹij
-0.14
]("-0.13
Ñıж
-0.13
ìĭ¤
-0.13
)↵↵↵↵↵↵↵↵
-0.13
?↵↵↵↵↵↵
-0.13
adıģ
-0.12
ENCHMARK
-0.12
POSITIVE LOGITS
pinned
0.36
pin
0.33
Pin
0.31
pins
0.29
PIN
0.28
bookmark
0.27
PIN
0.26
_pin
0.26
Pin
0.25
-pin
0.25
Activations Density 0.015%