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

    Neuronpedia

    INDEX
    Explanations

    conversational elements and narrative interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Sentences ending with periods

    np_acts-logits-general · gemini-2.0-flash

    narrative sequence markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnsafeEnabled
    -0.74
    PerformLayout
    -0.69
     EconPapers
    -0.63
    DrawerToggle
    -0.63
    RenderAtEndOf
    -0.62
    </caption>
    -0.61
    LabelTagHelper
    -0.61
    Попис
    -0.59
    ंदीखरीदारी
    -0.57
    конец
    -0.57
    POSITIVE LOGITS
     hindsight
    1.29
     retrospect
    1.24
     afterward
    1.24
     Afterward
    1.21
    Afterwards
    1.17
     afterwards
    1.17
     later
    1.16
     Afterwards
    1.10
    Later
    1.08
     Later
    1.05
    Act Density 0.247%

    No Known Activations