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

    Neuronpedia

    INDEX
    Explanations

    terms related to best practices, courses, flight, taxpayers, doomsday, players, bartering services, violence and aggression, scoring, riders, traveling, committing to record, fasting, evaluating, data processing, and debt contracting

    oai_token-act-pair · gpt-3.5-turbo

    terms related to numerical data and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     looph
    -0.54
     OF
    -0.49
     ghetto
    -0.47
     AND
    -0.46
     Comet
    -0.46
     and
    -0.45
     gorilla
    -0.45
     hating
    -0.44
     Encyclopedia
    -0.44
     Miracle
    -0.43
    POSITIVE LOGITS
     respectively
    0.93
     versa
    0.74
    *.
    0.67
     depending
    0.66
    .?
    0.65
    %.
    0.65
     accordingly
    0.64
    .<
    0.64
    +.
    0.63
     selves
    0.63
    Act Density 0.978%

    No Known Activations