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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to a significant or notable entity or unit

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "piece" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elsius
    -0.82
    osponsors
    -0.66
     consultants
    -0.61
     semin
    -0.60
     proliferation
    -0.59
     Lawyers
    -0.59
     Predators
    -0.58
    aeda
    -0.58
     blush
    -0.58
     translator
    -0.57
    POSITIVE LOGITS
    meal
    1.56
     piece
    1.08
    ngth
    1.00
     pieces
    0.90
    worms
    0.88
     Pieces
    0.87
    glass
    0.84
    ridges
    0.83
    breaker
    0.82
    DonaldTrump
    0.82
    Act Density 0.011%

    No Known Activations