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

    Neuronpedia

    INDEX
    Explanations

    When the neuron fires, it looks for the word "indeed" in the text

    oai_token-act-pair · gpt-3.5-turbo

    the word "indeed" and its variations to emphasize certainty or confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rals
    -0.63
    Streamer
    -0.61
    76561
    -0.59
    Mesh
    -0.59
    center
    -0.58
    assic
    -0.57
    Winged
    -0.57
    Ĺ
    -0.56
    QB
    -0.56
     weap
    -0.56
    POSITIVE LOGITS
    ional
    0.88
    uala
    0.79
     qualifies
    0.72
    EngineDebug
    0.68
     belong
    0.66
    arist
    0.65
    netflix
    0.64
    eem
    0.64
     formatted
    0.64
    forth
    0.63
    Act Density 0.017%

    No Known Activations