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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of people and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sah
    -0.15
    awner
    -0.14
    zte
    -0.13
    lož
    -0.13
    dni
    -0.13
    atak
    -0.12
    зи
    -0.12
    ëĶ©
    -0.12
    occan
    -0.12
    IBLE
    -0.12
    POSITIVE LOGITS
    ian
    0.17
    our
    0.17
    shire
    0.17
    ism
    0.16
    ory
    0.15
    ì¦ĺ
    0.15
    amente
    0.15
    ous
    0.15
    istan
    0.15
    ians
    0.14
    Act Density 0.138%

    No Known Activations