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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to identity and identification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    athy
    -0.16
    ila
    -0.15
    credits
    -0.15
    irting
    -0.15
    ansom
    -0.14
    -ÑĤаки
    -0.14
    owing
    -0.14
    icher
    -0.14
    ÙģÛĮ
    -0.14
    èīº
    -0.14
    POSITIVE LOGITS
    ahoo
    0.16
    اباÙĨ
    0.15
    /disable
    0.15
    ivent
    0.14
    AGO
    0.14
    ADDE
    0.14
    (identity
    0.14
    zed
    0.14
    ãĥ³ãĥĦ
    0.14
    616
    0.14
    Act Density 0.024%

    No Known Activations