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

    Neuronpedia

    INDEX
    Explanations

    phrases related to duration

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing "the rest of" something or contextually referencing continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uyomi
    -0.84
    ħĭ
    -0.76
     Cosponsors
    -0.74
    acus
    -0.71
    ucci
    -0.71
    anan
    -0.70
    ĸļ
    -0.70
     è£ıè¦ļéĨĴ
    -0.66
     pestic
    -0.66
     mathemat
    -0.65
    POSITIVE LOGITS
     course
    0.92
    course
    0.83
    ordinary
    0.73
     sorts
    0.68
     Laur
    0.64
    rounder
    0.61
    amate
    0.61
    retch
    0.61
    ources
    0.61
    ude
    0.59
    Act Density 0.109%

    No Known Activations