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

    Neuronpedia

    INDEX
    Explanations

    numbers at the beginning of phrases

    oai_token-act-pair · gpt-3.5-turbo

    structured numerical identifiers or listings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.84
    ileaks
    -0.80
    Ô
    -0.78
     behavi
    -0.78
    ifully
    -0.77
    chwitz
    -0.77
    anooga
    -0.77
    ierrez
    -0.76
    merce
    -0.76
    icist
    -0.75
    POSITIVE LOGITS
    91
    1.01
    34
    0.99
    92
    0.96
    87
    0.96
    650
    0.96
     Apostles
    0.94
    94
    0.93
    71
    0.93
    noon
    0.92
    02
    0.91
    Act Density 0.046%

    No Known Activations