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

    Neuronpedia

    INDEX
    Explanations

    terms related to cleansing and removing impurities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oken
    -0.16
    Ú©ÙĪ
    -0.16
    rien
    -0.16
    gren
    -0.15
    olis
    -0.15
    emit
    -0.14
    chos
    -0.14
     ún
    -0.14
    .times
    -0.14
    EDA
    -0.13
    POSITIVE LOGITS
    oir
    0.16
    urai
    0.16
     EXEMPLARY
    0.15
    554
    0.15
    æĪĴ
    0.15
    uzzi
    0.14
    Ľi
    0.14
    awah
    0.14
    usercontent
    0.14
    ani
    0.14
    Act Density 0.079%

    No Known Activations