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

    Neuronpedia

    INDEX
    Explanations

    references to calculations and numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azu
    -0.16
    chal
    -0.14
    agn
    -0.14
    nost
    -0.14
    ghi
    -0.14
    chl
    -0.13
    chner
    -0.13
    tol
    -0.13
     Herc
    -0.13
    chi
    -0.13
    POSITIVE LOGITS
    éĢ
    0.15
    uts
    0.15
    klä
    0.14
    inkel
    0.14
    ibir
    0.14
    idlo
    0.14
    ÙĪØ«
    0.14
     меÑĤалли
    0.13
    ÑĤÑĥÑĢ
    0.13
    ajÃŃ
    0.13
    Act Density 0.003%

    No Known Activations