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

    Neuronpedia

    INDEX
    Explanations

    numbers indicating a specific count or quantity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the number '12' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifully
    -0.76
     tremend
    -0.76
    icist
    -0.74
    Ô
    -0.72
    ICS
    -0.71
    ause
    -0.71
    osphere
    -0.70
    anooga
    -0.69
     behavi
    -0.68
    bsite
    -0.68
    POSITIVE LOGITS
    noon
    0.98
    650
    0.97
    34
    0.96
    91
    0.94
     Apostles
    0.92
    71
    0.89
    87
    0.89
    03
    0.88
    80
    0.88
    02
    0.88
    Act Density 0.054%

    No Known Activations