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

    Neuronpedia

    INDEX
    Explanations

    references to rankings and accolades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abel
    -0.16
     Ken
    -0.14
    ä¾
    -0.14
    nemonic
    -0.14
    anos
    -0.14
     Norm
    -0.14
    Ken
    -0.13
     пода
    -0.13
    idon
    -0.13
    agi
    -0.13
    POSITIVE LOGITS
     Trou
    0.15
    hone
    0.14
     plurality
    0.14
    Trou
    0.14
     çIJ
    0.14
    iggers
    0.13
    æĽ
    0.13
    ãģıãģł
    0.13
    iddle
    0.13
    Ïģιο
    0.13
    Act Density 0.112%

    No Known Activations