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

    Neuronpedia

    INDEX
    Explanations

    materials or substances that things are made of

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating material composition or the origin of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     challeng
    -0.92
    accompan
    -0.83
    anwhile
    -0.75
    gradation
    -0.71
    edi
    -0.69
    isSpecialOrderable
    -0.68
    comings
    -0.67
    facing
    -0.67
    diagn
    -0.67
    icious
    -0.66
    POSITIVE LOGITS
    Wan
    0.88
     sag
    0.62
     silicon
    0.62
     allowances
    0.61
     dent
    0.61
     mistake
    0.60
     pure
    0.59
    SAY
    0.58
    ertodd
    0.58
    ··
    0.57
    Act Density 0.090%

    No Known Activations