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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names appearing in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eldorf
    -0.17
    jad
    -0.16
    apore
    -0.16
    ongyang
    -0.15
    ynes
    -0.15
    Ç
    -0.15
    ียว
    -0.14
    елиÑĩ
    -0.14
    stoff
    -0.14
    undy
    -0.14
    POSITIVE LOGITS
    igy
    0.15
     CONTRIBUTORS
    0.15
    452
    0.14
     Obr
    0.14
     .|
    0.13
    ropolitan
    0.13
     John
    0.13
     Patri
    0.13
    igos
    0.13
    iless
    0.13
    Act Density 0.083%

    No Known Activations