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

    Neuronpedia

    INDEX
    Explanations

    words and phrases used to convey contrast or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    list
    -0.15
    arch
    -0.15
    uen
    -0.15
     QDir
    -0.14
    dd
    -0.14
    _ptr
    -0.14
    DED
    -0.14
    urm
    -0.14
    orno
    -0.14
    pon
    -0.14
    POSITIVE LOGITS
    CHandle
    0.16
    zÃŃ
    0.15
    egie
    0.15
    erli
    0.15
    /Dk
    0.15
    $LANG
    0.14
    Constraints
    0.14
    heimer
    0.14
    Coach
    0.14
    iyat
    0.14
    Act Density 0.001%

    No Known Activations