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

    Neuronpedia

    INDEX
    Explanations

    numbers related to quantities or measurements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     grate
    -0.59
    lessly
    -0.59
     Abram
    -0.58
     slightest
    -0.57
     microsc
    -0.57
    leans
    -0.56
     experiment
    -0.56
     logic
    -0.55
     Too
    -0.54
     whiff
    -0.53
    POSITIVE LOGITS
    %.
    0.83
    bps
    0.80
    %;
    0.77
    ãĥĩãĤ£
    0.73
    %,
    0.70
    ND
    0.69
    fps
    0.68
    EStreamFrame
    0.65
    KK
    0.65
    cn
    0.64
    Act Density 0.172%

    No Known Activations