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

    Neuronpedia

    INDEX
    Explanations

    phrases that include variations of the word "all."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yonel
    -0.19
    ylvania
    -0.18
    ulen
    -0.17
    elle
    -0.15
    ilk
    -0.15
    oppable
    -0.14
    laden
    -0.14
    ulture
    -0.14
    ious
    -0.14
    ohl
    -0.14
    POSITIVE LOGITS
    ollipop
    0.18
    ameda
    0.18
    ness
    0.17
    iances
    0.16
    iges
    0.16
    andro
    0.16
    ender
    0.16
    igham
    0.15
    bie
    0.15
    igators
    0.15
    Act Density 0.046%

    No Known Activations