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

    Neuronpedia

    INDEX
    Explanations

    elements related to engaging and compelling narratives or activities that are difficult to stop once started

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adden
    -0.17
    ãĥ³ãĥĶ
    -0.15
    ITHER
    -0.15
    anny
    -0.15
    arkin
    -0.14
    gon
    -0.14
    stal
    -0.14
    ither
    -0.14
    egan
    -0.14
     hum
    -0.14
    POSITIVE LOGITS
     swe
    0.15
    unfinished
    0.14
     ($.
    0.14
    abile
    0.14
    eam
    0.14
    vell
    0.14
    اÙĩر
    0.13
    Compact
    0.13
     Rao
    0.13
    orns
    0.13
    Act Density 0.117%

    No Known Activations