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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iyi
    -0.17
    er
    -0.17
    anou
    -0.17
    ed
    -0.16
    ا
    -0.16
    A
    -0.14
    h
    -0.14
    zburg
    -0.14
    B
    -0.13
    redients
    -0.13
    POSITIVE LOGITS
    uby
    0.17
    ndef
    0.16
    ereo
    0.14
    ɵ
    0.14
    jos
    0.14
    xEA
    0.13
    olan
    0.13
    /***/
    0.13
    rous
    0.13
    comed
    0.13
    Act Density 0.174%

    No Known Activations