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

    Neuronpedia

    INDEX
    Explanations

    large numbers written as digits within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, particularly in relation to statistics or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     newsp
    -0.74
     behav
    -0.69
     vag
    -0.65
     ------
    -0.65
     Cros
    -0.64
     Revel
    -0.64
     enthusi
    -0.62
    ngth
    -0.62
     enthus
    -0.60
     opin
    -0.60
    POSITIVE LOGITS
    000
    1.40
    500
    1.25
    200
    1.21
    400
    1.20
    600
    1.17
    700
    1.16
    800
    1.15
    300
    1.15
    900
    1.08
    250
    1.07
    Act Density 0.065%

    No Known Activations