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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aned
    -0.17
    eview
    -0.16
    ÂŃi
    -0.15
    /animations
    -0.15
    udur
    -0.15
    rani
    -0.14
    Ñijл
    -0.14
    uentes
    -0.13
    endir
    -0.13
    ute
    -0.13
    POSITIVE LOGITS
    elik
    0.15
    flix
    0.15
    chosen
    0.14
    .BLL
    0.14
    izr
    0.14
     Ricky
    0.14
     knight
    0.13
    ãĥķãĥĪ
    0.13
     rip
    0.13
     chosen
    0.13
    Act Density 0.023%

    No Known Activations