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

    Neuronpedia

    INDEX
    Explanations

    words associated with significant roles or impacts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akh
    -0.17
    å¾Ģ
    -0.17
     Stanton
    -0.16
    $MESS
    -0.16
     åľ
    -0.15
    loyd
    -0.15
    оди
    -0.15
    sdale
    -0.14
    onto
    -0.14
     revolving
    -0.14
    POSITIVE LOGITS
    llum
    0.16
    _finish
    0.16
    abcdefghijklmnop
    0.16
    965
    0.15
     Basket
    0.15
    abee
    0.15
    ebra
    0.15
    982
    0.14
    bag
    0.14
    heap
    0.14
    Act Density 0.014%

    No Known Activations