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

    Neuronpedia

    INDEX
    Explanations

    numerical and alphanumeric sequences

    oai_token-act-pair · gpt-3.5-turbo

    numerical patterns or identifiers, such as values resembling codes or URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    perature
    -0.76
    âĸ¬
    -0.70
    igue
    -0.70
    seless
    -0.67
    agna
    -0.66
     CLSID
    -0.63
    FontSize
    -0.62
     administ
    -0.59
     Leban
    -0.59
    iple
    -0.58
    POSITIVE LOGITS
    ffe
    0.84
    e
    0.81
    wm
    0.77
    201
    0.74
    rez
    0.74
    eff
    0.74
    df
    0.74
    eem
    0.71
    dd
    0.71
    249
    0.70
    Act Density 0.057%

    No Known Activations