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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific groups of people

    oai_token-act-pair · gpt-3.5-turbo

    references to various groups of individuals or personnel, particularly in official or organizational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wise
    -0.76
    OUS
    -0.73
    monster
    -0.72
    OF
    -0.71
    PUT
    -0.68
    odo
    -0.62
    of
    -0.62
    Reloaded
    -0.61
    CHECK
    -0.61
    VALUE
    -0.60
    POSITIVE LOGITS
    hips
    1.39
    hip
    1.05
     who
    0.97
     stationed
    0.96
    paces
    0.90
     alike
    0.82
    '
    0.80
    hops
    0.79
     whom
    0.77
    who
    0.75
    Act Density 0.359%

    No Known Activations