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

    Neuronpedia

    INDEX
    Explanations

    terms related to auditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tow
    -0.14
    ount
    -0.14
    heten
    -0.14
     cross
    -0.14
    ivos
    -0.14
     corre
    -0.14
    ake
    -0.13
     wheel
    -0.13
    uden
    -0.13
    erial
    -0.13
    POSITIVE LOGITS
    linky
    0.17
    otros
    0.15
    ģ
    0.15
    ÑģÑĤан
    0.15
    anian
    0.14
    yers
    0.14
    e
    0.14
    posta
    0.14
    et
    0.14
     Severity
    0.14
    Act Density 0.004%

    No Known Activations