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

    Neuronpedia

    INDEX
    Explanations

    references to numbers and their significance in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.69
    Four
    -0.67
    FOUR
    -0.64
     Four
    -0.63
    thâu
    -0.62
    four
    -0.58
    verifyException
    -0.58
    ItemBackground
    -0.58
    localctx
    -0.54
     disambiguazione
    -0.54
    POSITIVE LOGITS
     forty
    0.77
     Forty
    0.65
    forty
    0.54
    Forty
    0.52
     cuarenta
    0.49
    4
    0.47
     quarante
    0.46
     FORT
    0.44
    pan
    0.43
    四十
    0.43
    Act Density 0.991%

    No Known Activations