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

    Neuronpedia

    INDEX
    Explanations

    durations of time in various units

    oai_token-act-pair · gpt-3.5-turbo

    references to time durations or periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ronics
    -0.72
    ħĭ
    -0.71
    tnc
    -0.70
     Cosponsors
    -0.65
    eus
    -0.65
    seek
    -0.64
    Sax
    -0.63
    Amb
    -0.62
     Compatibility
    -0.61
    acons
    -0.61
    POSITIVE LOGITS
     consecut
    0.91
     culminating
    0.90
     culmin
    0.88
     totaling
    0.88
    depending
    0.87
     depending
    0.83
     exhausting
    0.80
    elsius
    0.78
     uninterrupted
    0.77
     submer
    0.74
    Act Density 0.318%

    No Known Activations