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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the outcome or effectiveness of an action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ubbo
    -0.17
    gger
    -0.15
    istingu
    -0.15
    ird
    -0.15
    unkt
    -0.15
    olan
    -0.15
    ikers
    -0.14
    mq
    -0.14
    LOUR
    -0.14
    ency
    -0.14
    POSITIVE LOGITS
    375
    0.15
    gabe
    0.15
    ä¿Ĺ
    0.14
    addtogroup
    0.14
    åħ±åĴĮ
    0.14
    occupied
    0.14
    ¯ÃĤ
    0.14
    ีร
    0.14
    oga
    0.14
    دÙĪ
    0.14
    Act Density 0.040%

    No Known Activations