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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causation or origins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ume
    -0.16
    lez
    -0.15
    度
    -0.15
    Ư
    -0.15
    ault
    -0.15
    IZ
    -0.14
    iz
    -0.14
    Happy
    -0.14
    ettle
    -0.14
    oplevel
    -0.13
    POSITIVE LOGITS
     Previous
    0.15
    ÙĬتÙĬ
    0.14
    ourn
    0.14
    .shtml
    0.14
    ephy
    0.14
    iÅ¡tÄĽ
    0.13
    adele
    0.13
    ento
    0.13
     à¤ĸड
    0.13
    RAINT
    0.13
    Act Density 0.112%

    No Known Activations