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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating frequency or typicality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WriteLiteral
    -0.50
    AutoresizingMask
    -0.41
    ён
    -0.39
    دانلود
    -0.39
     breat
    -0.39
     phosph
    -0.39
     Crot
    -0.38
     Gou
    -0.38
    balleur
    -0.38
    FileOutputStream
    -0.37
    POSITIVE LOGITS
     usually
    1.45
    Usually
    1.42
     Usually
    1.39
    usually
    1.30
    Usual
    1.23
     typically
    1.20
     Usual
    1.17
     zwykle
    1.16
    Typically
    1.15
     normally
    1.13
    Act Density 0.228%

    No Known Activations