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

    Neuronpedia

    INDEX
    Explanations

    the number "63" mentioned in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, specifically those associated with measurements or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesday
    -0.80
    achus
    -0.80
    pire
    -0.80
     disadvant
    -0.77
    iya
    -0.69
    ushed
    -0.68
    cock
    -0.67
    ened
    -0.66
    olitan
    -0.66
    parency
    -0.66
    POSITIVE LOGITS
    dfx
    0.99
    328
    0.93
    803
    0.86
    obal
    0.83
    ographically
    0.76
    otomy
    0.76
     mph
    0.74
    _.
    0.73
    326
    0.70
     Minutes
    0.70
    Act Density 0.056%

    No Known Activations