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

    Neuronpedia

    INDEX
    Explanations

    references to statistics and numbers in text

    oai_token-act-pair · gpt-3.5-turbo

    quantitative data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    say
    -0.85
    assuming
    -0.80
    orah
    -0.74
    farious
    -0.68
     Parables
    -0.67
     Saying
    -0.67
     realise
    -0.65
    pose
    -0.64
     insisting
    -0.64
     insist
    -0.63
    POSITIVE LOGITS
     was
    1.29
     lasted
    1.25
     became
    1.21
     has
    1.17
     grew
    1.16
     peaked
    1.15
     went
    1.15
     underwent
    1.14
     transitioned
    1.13
     remains
    1.12
    Act Density 0.649%

    No Known Activations