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

    Neuronpedia

    INDEX
    Explanations

    technical information related to software releases or updates

    oai_token-act-pair · gpt-3.5-turbo

    references to dates and numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lud
    -1.04
    lder
    -0.82
     Vald
    -0.81
     ghost
    -0.74
    kas
    -0.73
    ody
    -0.73
     Merchant
    -0.70
     cran
    -0.70
    ud
    -0.68
     Qiao
    -0.68
    POSITIVE LOGITS
    9
    1.67
     9
    1.56
    930
    1.10
    nine
    1.08
     nine
    1.08
    909
    1.08
     Nine
    1.08
    925
    1.07
    911
    1.06
    Nine
    1.06
    Act Density 0.170%

    No Known Activations