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

    Neuronpedia

    INDEX
    Explanations

    references to original names or titles and their variants in listings or catalogs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vailability
    -0.15
    opc
    -0.15
    ote
    -0.15
    umi
    -0.14
    otes
    -0.14
    OTE
    -0.13
    наÑĤ
    -0.13
    élé
    -0.13
    ikat
    -0.13
    regar
    -0.13
    POSITIVE LOGITS
    zÄĻ
    0.16
    FRING
    0.16
    ander
    0.16
    vie
    0.15
    anders
    0.14
    agu
    0.14
    (Func
    0.14
    rade
    0.14
    ocha
    0.14
    ذا
    0.13
    Act Density 0.016%

    No Known Activations