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

    Neuronpedia

    INDEX
    Explanations

    instances of stopping or pausing actions within a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ikh
    -0.17
    kh
    -0.17
     crown
    -0.15
    chl
    -0.15
    errat
    -0.15
    zzo
    -0.14
     Crown
    -0.14
    _TRACE
    -0.14
    encing
    -0.14
     moder
    -0.14
    POSITIVE LOGITS
    -stop
    0.16
    971
    0.15
    ftar
    0.15
    690
    0.15
     à¤ªà¥ľ
    0.15
    çek
    0.15
    à¹Ģà¸Ĺ
    0.15
    933
    0.14
    STOP
    0.14
    idar
    0.14
    Act Density 0.157%

    No Known Activations