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

    Neuronpedia

    INDEX
    Explanations

    questions about or expressions of confusion

    oai_token-act-pair · gpt-3.5-turbo

    inquiries about current events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    serv
    -0.81
    yes
    -0.74
    grand
    -0.69
    eah
    -0.68
    ritical
    -0.68
     dove
    -0.64
    ushed
    -0.63
    onso
    -0.63
    agu
    -0.63
    sworth
    -0.62
    POSITIVE LOGITS
     unfolding
    0.83
     unfold
    0.76
    Downloadha
    0.75
    etime
    0.74
     behalf
    0.74
     unnoticed
    0.74
    erous
    0.72
    abouts
    0.72
     upstairs
    0.70
    shore
    0.70
    Act Density 0.037%

    No Known Activations