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

    Neuronpedia

    INDEX
    Explanations

    extremes in numerical values such as 'lowest' or 'highest'

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating extreme quantitative values, specifically highs and lows in various metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĪ
    -0.74
    enegger
    -0.70
     Nightmares
    -0.67
    pron
    -0.66
    umbn
    -0.65
    oras
    -0.65
    tiny
    -0.64
    cult
    -0.64
    rio
    -0.63
    Cho
    -0.62
    POSITIVE LOGITS
     ever
    1.21
    ever
    1.18
     EVER
    1.13
     since
    0.95
     recorded
    0.93
     imaginable
    0.85
    Ever
    0.83
     mark
    0.82
     Ever
    0.81
     tally
    0.80
    Act Density 0.126%

    No Known Activations