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

    Neuronpedia

    INDEX
    Explanations

    phrases related to categorization or classification

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate classifications or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pat
    -0.69
    nut
    -0.69
     Merchants
    -0.69
     Citiz
    -0.67
     Sidd
    -0.67
    chal
    -0.66
     Strateg
    -0.62
     Bosh
    -0.61
     Hemp
    -0.61
    atto
    -0.61
    POSITIVE LOGITS
    interstitial
    0.77
    generation
    0.71
    ulhu
    0.63
    ãĢĤ
    0.62
     characterize
    0.62
     everywhere
    0.61
    agate
    0.60
    chool
    0.60
     owing
    0.59
     converge
    0.58
    Act Density 0.072%

    No Known Activations