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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate actions or transitions in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orts
    -0.16
     yelled
    -0.14
    urr
    -0.14
     excer
    -0.14
    _listen
    -0.13
    ãģ¨æĢĿ
    -0.13
     ÙĨÙħ
    -0.13
    verbatim
    -0.13
     portrayed
    -0.13
    obra
    -0.13
    POSITIVE LOGITS
     describe
    0.41
     explain
    0.38
     describing
    0.37
     describes
    0.36
     mention
    0.35
     talk
    0.34
     descri
    0.34
     explaining
    0.33
    describe
    0.32
     discuss
    0.31
    Act Density 0.055%

    No Known Activations