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

    Neuronpedia

    INDEX
    Explanations

    capitalized acronyms with three letters

    oai_token-act-pair · gpt-3.5-turbo

    references to the abbreviation "FE" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assian
    -0.78
    ographer
    -0.76
    minded
    -0.75
    azines
    -0.71
    agically
    -0.71
    ination
    -0.70
    appropriately
    -0.69
    folk
    -0.69
     Siren
    -0.68
    nian
    -0.68
    POSITIVE LOGITS
    VE
    1.09
    ATURES
    1.06
    ATURE
    1.03
    FE
    1.02
    ET
    0.95
    QU
    0.93
    BR
    0.92
    ZZ
    0.89
    VER
    0.88
    ASON
    0.88
    Act Density 0.011%

    No Known Activations