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

    Neuronpedia

    INDEX
    Explanations

    titles of TV shows

    oai_token-act-pair · gpt-3.5-turbo

    comma-separated lists or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sclerosis
    -0.59
     Rounds
    -0.56
    asing
    -0.55
    lier
    -0.55
    ometers
    -0.53
    iaries
    -0.52
    iners
    -0.52
     reperc
    -0.50
     withdrawal
    -0.49
    sych
    -0.49
    POSITIVE LOGITS
     respectively
    1.16
     etc
    0.97
     aka
    0.87
     which
    0.86
     wherein
    0.83
     whereas
    0.80
    govtrack
    0.76
     thereby
    0.75
    while
    0.74
     whence
    0.73
    Act Density 0.322%

    No Known Activations