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

    Neuronpedia

    INDEX
    Explanations

    words related to the size or magnitude of something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the magnitude or extent of issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.70
    olkien
    -0.69
    ategor
    -0.66
     Advertisement
    -0.61
    issy
    -0.60
    Eva
    -0.58
    ocally
    -0.58
     Ago
    -0.56
    INO
    -0.56
    isse
    -0.55
    POSITIVE LOGITS
     of
    1.06
     thereof
    1.03
    iest
    1.02
    of
    0.80
    liest
    0.80
    iness
    0.80
    fulness
    0.79
    lessness
    0.79
     inherent
    0.77
     OF
    0.76
    Act Density 0.320%

    No Known Activations