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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships or comparisons, particularly with the word "well."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istor
    -0.16
    ục
    -0.16
    onic
    -0.15
     ç©
    -0.15
    alette
    -0.15
    htable
    -0.14
    ç©
    -0.14
     Mah
    -0.14
    .populate
    -0.14
    ename
    -0.14
    POSITIVE LOGITS
    avn
    0.16
    åĴ²
    0.15
    $MESS
    0.15
    Pod
    0.15
    åĭ¢
    0.14
    olor
    0.14
    arduino
    0.14
    nest
    0.14
    åħ¼
    0.14
    embourg
    0.14
    Act Density 0.018%

    No Known Activations