Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     alguien
    -0.07
     بكل
    -0.07
    พรรณ
    -0.07
    Levels
    -0.07
    Stat
    -0.07
     Stat
    -0.06
    Last
    -0.06
    affer
    -0.06
     grew
    -0.06
    Hands
    -0.06
    POSITIVE LOGITS
    鄚
    0.08
     örg
    0.08
    תחר
    0.07
    قس
    0.07
    داعش
    0.07
     targ
    0.07
    몹
    0.07
    狷
    0.07
    expr
    0.07
    *,
    0.06
    Act Density 0.001%

    No Known Activations