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

    Neuronpedia

    INDEX
    Explanations

    references to various types of addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isch
    -0.18
    ستاÙĨ
    -0.16
    umber
    -0.15
    abcdefghijklmnop
    -0.15
    AGER
    -0.14
    ogan
    -0.14
    iris
    -0.14
    uden
    -0.14
    tings
    -0.14
    abcdefghijkl
    -0.14
    POSITIVE LOGITS
    (es
    0.31
    ses
    0.24
    ess
    0.21
    able
    0.20
    esine
    0.20
    sed
    0.19
    ë¡Ŀ
    0.19
    es
    0.18
    /es
    0.18
    esModule
    0.18
    Act Density 0.021%

    No Known Activations