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

    Neuronpedia

    INDEX
    Explanations

    references to time in the past

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods, specifically past events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cius
    -0.74
    DERR
    -0.71
    Naz
    -0.66
    VALUE
    -0.65
    effic
    -0.65
    pex
    -0.64
     Pwr
    -0.63
     inhibitors
    -0.63
    bytes
    -0.63
    gencies
    -0.61
    POSITIVE LOGITS
     weekend
    1.08
    ebin
    0.94
    cture
    0.87
    fecture
    0.83
     week
    0.83
     afternoon
    0.76
     season
    0.73
     WEEK
    0.72
     Weekend
    0.72
    nder
    0.72
    Act Density 0.065%

    No Known Activations