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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases, specifically indicating a moment just before something happens

    oai_token-act-pair · gpt-3.5-turbo

    temporal references indicating sequences of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    geist
    -0.86
    ology
    -0.77
    izo
    -0.76
    eria
    -0.74
    ãĤ¦ãĤ¹
    -0.73
    ographies
    -0.73
    ologies
    -0.73
    straight
    -0.72
    uph
    -0.71
    ulous
    -0.71
    POSITIVE LOGITS
     midnight
    1.54
     noon
    1.35
     sunrise
    1.31
     sunset
    1.29
     halftime
    1.21
     dusk
    1.20
     midday
    1.20
     dawn
    1.05
     Christmas
    1.03
     kickoff
    0.98
    Act Density 0.070%

    No Known Activations