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

    Neuronpedia

    INDEX
    Explanations

    organizations or entities related to various industries or sectors

    oai_token-act-pair · gpt-3.5-turbo

    references to various groups of people involved in different societal roles or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ASED
    -0.63
    owship
    -0.62
    iasis
    -0.61
    osi
    -0.61
    ariat
    -0.60
     Thing
    -0.59
     Railroad
    -0.58
    UCK
    -0.57
    urse
    -0.57
    bernatorial
    -0.57
    POSITIVE LOGITS
    hip
    0.91
    folk
    0.85
    avers
    0.83
    ynthesis
    0.82
    ensitive
    0.76
    ettings
    0.75
    '
    0.74
    ynt
    0.73
    afety
    0.72
    uggest
    0.72
    Act Density 0.389%

    No Known Activations