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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to individuals and locations in a news article

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    selves
    -0.75
    ically
    -0.71
    CLASSIFIED
    -0.70
    heast
    -0.68
    heastern
    -0.67
    ications
    -0.64
    iques
    -0.60
    folk
    -0.60
    rd
    -0.60
    */(
    -0.60
    POSITIVE LOGITS
    pole
    0.91
    orescence
    0.88
    oresc
    0.87
    uffy
    0.86
    acies
    0.86
    owship
    0.86
    nuts
    0.84
    acy
    0.80
    orescent
    0.77
    erella
    0.77
    Act Density 0.055%

    No Known Activations