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

    Neuronpedia

    INDEX
    Explanations

    conversational exchanges and emotional reflections related to social events

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

    often preceding certain nouns

    np_acts-logits-general · gemini-2.0-flash

    sports game analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.69
     Lyra
    -0.57
    🏻‍♀️
    -0.55
     Judith
    -0.51
     läßt
    -0.50
     Beatrix
    -0.50
     Whilst
    -0.49
     proposent
    -0.49
    webElement
    -0.49
     orientation
    -0.49
    POSITIVE LOGITS
     offseason
    1.04
     postseason
    1.01
     playoff
    0.94
     coaches
    0.91
     player
    0.84
     preseason
    0.83
     players
    0.83
     coaching
    0.83
     coach
    0.82
     teammates
    0.82
    Act Density 0.745%

    No Known Activations