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

    Neuronpedia

    INDEX
    Explanations

    references to academic publications and studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isin
    -0.15
    erb
    -0.14
     Grain
    -0.14
    uky
    -0.14
     Presidents
    -0.14
     Pioneer
    -0.14
     eskort
    -0.13
     Silk
    -0.13
     Fruit
    -0.13
    ukt
    -0.13
    POSITIVE LOGITS
    edly
    0.15
    $MESS
    0.15
     Consum
    0.15
    '])?
    0.14
    acks
    0.14
     Tavern
    0.13
    ylvania
    0.13
    ìŀIJìĿ¸
    0.13
    sville
    0.13
    callable
    0.13
    Act Density 0.211%

    No Known Activations