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

    Neuronpedia

    INDEX
    Explanations

    comparisons between current and past situations

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "earlier" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lua
    -0.81
    FW
    -0.72
    PORT
    -0.71
    liga
    -0.70
    fax
    -0.69
    eping
    -0.69
    Dash
    -0.68
     Pwr
    -0.68
    GH
    -0.68
    ertodd
    -0.68
    POSITIVE LOGITS
     versions
    1.11
     generations
    1.02
     stages
    0.95
     iterations
    0.91
     chapters
    0.89
     incarnation
    0.89
     installments
    0.89
     editions
    0.88
     eras
    0.86
     civilizations
    0.83
    Act Density 0.053%

    No Known Activations