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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing a sense of distance or extent

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating distance or separation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    İĭ
    -0.76
    spin
    -0.69
    ycle
    -0.68
    amine
    -0.67
    cffff
    -0.66
    kefeller
    -0.63
     Universe
    -0.62
    "},"
    -0.60
    vous
    -0.60
    avorite
    -0.58
    POSITIVE LOGITS
     ado
    0.71
    fetched
    0.70
    thing
    0.70
    zx
    0.62
     aside
    0.61
    gue
    0.61
    points
    0.60
    forward
    0.60
    ahime
    0.60
    aghd
    0.59
    Act Density 0.017%

    No Known Activations