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

    Neuronpedia

    INDEX
    Explanations

    references to a specific time frame - "this past"

    oai_token-act-pair · gpt-3.5-turbo

    references to time, specifically events that happened in the past

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cius
    -0.77
    idem
    -0.72
     Spirits
    -0.72
    icons
    -0.71
    Naz
    -0.66
    spect
    -0.65
    inen
    -0.64
    ateurs
    -0.64
    urtles
    -0.63
     spirits
    -0.63
    POSITIVE LOGITS
    cture
    0.92
     weekend
    0.82
     avenue
    0.78
    worldly
    0.73
     WEEK
    0.72
     season
    0.72
     offseason
    0.71
     possession
    0.70
     century
    0.70
    fecture
    0.68
    Act Density 0.087%

    No Known Activations