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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific people endorsing or associated with certain candidates or professions

    oai_token-act-pair · gpt-3.5-turbo

    the verb "is" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Prior
    -0.71
    Prior
    -0.67
     Reef
    -0.65
     Lauder
    -0.64
     miscarriage
    -0.58
    IOR
    -0.58
     casualty
    -0.57
    onyms
    -0.57
     Leilan
    -0.55
     Hebdo
    -0.55
    POSITIVE LOGITS
    been
    0.90
    forth
    0.89
    lightly
    0.82
    ready
    0.79
     gonna
    0.78
    leeve
    0.78
    igi
    0.77
     been
    0.76
    aper
    0.74
    wered
    0.72
    Act Density 0.121%

    No Known Activations