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

    Neuronpedia

    INDEX
    Explanations

    numerical references and counts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.76
    CloseOperation
    -0.50
    Réalisation
    -0.47
    adap
    -0.45
    Whilst
    -0.45
    AuthGuard
    -0.45
     Whilst
    -0.44
    FailureListener
    -0.44
    writeFieldEnd
    -0.44
    wanzig
    -0.44
    POSITIVE LOGITS
    Fifty
    0.88
     Fifty
    0.85
    Sixty
    0.81
     Sixty
    0.81
     eighty
    0.79
     Eighty
    0.79
     sixty
    0.77
     Seventy
    0.77
     fifty
    0.73
     Ninety
    0.72
    Act Density 0.379%

    No Known Activations