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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, especially names of individuals or places

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erence
    -0.85
    rection
    -0.79
    eson
    -0.78
    ascript
    -0.76
    THER
    -0.76
    uther
    -0.74
    acebook
    -0.73
    reason
    -0.72
    reviewed
    -0.72
    ĨĴ
    -0.72
    POSITIVE LOGITS
     Pradesh
    0.95
     sect
    0.88
     Massacre
    0.85
    yah
    0.83
     Municip
    0.83
    hai
    0.82
    ya
    0.81
     Province
    0.81
    ji
    0.76
     Airlines
    0.76
    Act Density 0.253%

    No Known Activations