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

    Neuronpedia

    INDEX
    Explanations

    the word "Coll" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    references to "Colliers" or other related terms associated with that name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¥µ
    -0.81
    oshenko
    -0.78
    visor
    -0.76
    thing
    -0.74
    PDATE
    -0.73
    isSpecialOrderable
    -0.71
    FORE
    -0.71
    ItemImage
    -0.70
    WARE
    -0.69
    fulness
    -0.68
    POSITIVE LOGITS
    ateral
    1.12
    apsed
    1.02
    apse
    0.99
    ision
    0.97
    isions
    0.96
    ossus
    0.92
    oqu
    0.90
    iery
    0.89
    onel
    0.88
    ouri
    0.86
    Act Density 0.009%

    No Known Activations