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

    Neuronpedia

    INDEX
    Explanations

    references to numerical concepts and representations in programming and mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     esternos
    -0.67
    первых
    -0.65
    Kjelder
    -0.61
     lenker
    -0.59
    anyeol
    -0.56
    Controllo
    -0.56
     NDEBUG
    -0.56
    醐
    -0.56
    riwal
    -0.55
    AnchorStyles
    -0.55
    POSITIVE LOGITS
    دانشنامهٔ
    0.78
    Decimal
    0.75
     decimal
    0.75
     numbers
    0.73
     digits
    0.72
     Decimal
    0.71
     chiffres
    0.67
     calculators
    0.66
     Numbers
    0.66
    decimal
    0.64
    Act Density 0.788%

    No Known Activations