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

    Neuronpedia

    INDEX
    Explanations

    assertions of belief or confidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sanford
    -0.61
     responde
    -0.61
    庸
    -0.59
    cotti
    -0.57
    ragamo
    -0.57
    chesse
    -0.55
    ]]]
    -0.54
    ppard
    -0.54
    CLAS
    -0.53
    LikeLike
    -0.52
    POSITIVE LOGITS
     swears
    0.80
     swear
    0.79
     mxArray
    0.72
     convinced
    0.71
     pewno
    0.71
     NSCoder
    0.71
     Guarantee
    0.69
    CodeAttribute
    0.67
    sure
    0.66
     sicuro
    0.65
    Act Density 0.203%

    No Known Activations