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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing a quality or condition

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that describe varying degrees of intensity or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aleb
    -0.69
    Bel
    -0.58
    Mat
    -0.58
    Hat
    -0.56
    usalem
    -0.56
    moon
    -0.56
    Faith
    -0.56
    abs
    -0.55
    ©¶æ
    -0.54
    cknowled
    -0.54
    POSITIVE LOGITS
     indeed
    0.83
     compared
    0.75
     insofar
    0.73
     nowadays
    0.73
     sounding
    0.73
     ashore
    0.72
    idious
    0.65
    isable
    0.65
    ––
    0.64
     (>
    0.63
    Act Density 0.346%

    No Known Activations