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

    Neuronpedia

    INDEX
    Explanations

    numerical references and religious or authoritative statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    setter
    -0.16
    avras
    -0.15
    YN
    -0.15
    ioc
    -0.14
    uff
    -0.14
    nts
    -0.14
    arella
    -0.14
    kuk
    -0.14
    iolet
    -0.13
    gard
    -0.13
    POSITIVE LOGITS
    271
    0.14
    ingham
    0.14
     McMahon
    0.14
    ishi
    0.14
    ero
    0.14
    unning
    0.14
    oen
    0.13
     wing
    0.13
    ulis
    0.13
    ogn
    0.13
    Act Density 0.083%

    No Known Activations