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

    Neuronpedia

    INDEX
    Explanations

    numeric sequences

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and references to numeric codes or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    perature
    -0.66
    seless
    -0.64
    anooga
    -0.63
    orest
    -0.62
     retina
    -0.62
    emort
    -0.61
    undo
    -0.61
    agna
    -0.58
    atever
    -0.58
    âĸ¬
    -0.57
    POSITIVE LOGITS
    e
    0.92
    ffe
    0.81
    âĢ³
    0.78
    201
    0.74
    a
    0.72
    249
    0.72
    245
    0.70
    Bs
    0.68
    si
    0.68
    393
    0.68
    Act Density 0.053%

    No Known Activations