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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to cancellation or stopping actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    laps
    -0.16
    etler
    -0.16
    äºİ
    -0.15
    ed
    -0.15
    ná
    -0.15
    ening
    -0.15
    unma
    -0.15
    wine
    -0.15
    æĸ¼
    -0.15
    auc
    -0.14
    POSITIVE LOGITS
    led
    0.28
    ation
    0.26
    AnimationFrame
    0.22
    icious
    0.20
    LED
    0.20
    tered
    0.18
    ations
    0.18
    er
    0.17
    /post
    0.17
    able
    0.17
    Act Density 0.014%

    No Known Activations