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

    Neuronpedia

    INDEX
    Explanations

    alphanumeric characters and symbols in a specific pattern

    oai_token-act-pair · gpt-3.5-turbo

    numeric and format-related data, particularly in reference to time and identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essor
    -0.75
    urga
    -0.73
    angelo
    -0.72
    gerald
    -0.69
    riad
    -0.64
    ÙĴ
    -0.63
    ourt
    -0.62
    urdue
    -0.62
     Tuls
    -0.61
    erella
    -0.61
    POSITIVE LOGITS
    ĪĴ
    0.96
    GHz
    0.93
    thirds
    0.78
     GHz
    0.77
    otide
    0.76
    ibrary
    0.73
    rontal
    0.73
    ethnic
    0.71
    agonists
    0.68
    hander
    0.64
    Act Density 0.291%

    No Known Activations