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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their relationships within code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pro
    -0.52
     tri
    -0.49
     par
    -0.49
    ']=='
    -0.49
    $=\
    -0.48
    writerow
    -0.48
     Winaray
    -0.47
     be
    -0.46
     pros
    -0.46
    Hochspringen
    -0.46
    POSITIVE LOGITS
    ArgsConstructor
    1.09
    الإنجليزية
    0.89
    moveToFirst
    0.88
    ruptedException
    0.82
    UnsafeEnabled
    0.82
     للاسماء
    0.79
     NSCoder
    0.79
     ainfi
    0.78
    PreExecute
    0.78
    Personendaten
    0.78
    Act Density 0.051%

    No Known Activations