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

    Neuronpedia

    INDEX
    Explanations

    timestamps or time-related cues in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to time progression or transitions in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rone
    -0.65
    ouk
    -0.63
    chief
    -0.60
    amen
    -0.57
    esson
    -0.56
    erved
    -0.56
    ka
    -0.55
    olicited
    -0.55
    Hide
    -0.55
    aught
    -0.54
    POSITIVE LOGITS
     timeline
    0.82
     timelines
    0.78
     hindsight
    0.78
    ween
    0.75
    history
    0.74
     eras
    0.74
     millennium
    0.73
    gypt
    0.73
     eternity
    0.71
    âĢ¢âĢ¢
    0.71
    Act Density 0.045%

    No Known Activations