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

    Neuronpedia

    INDEX
    Explanations

    mentions of events or incidents that occurred in the past

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods specifically described as "past."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anguage
    -0.89
    NEY
    -0.70
    GAN
    -0.68
    Services
    -0.65
    anded
    -0.65
    wagon
    -0.65
    Gun
    -0.65
    horn
    -0.64
    SK
    -0.64
    Software
    -0.63
    POSITIVE LOGITS
    ebin
    1.42
     tense
    0.95
    iche
    0.95
     past
    0.81
     decade
    0.80
     generations
    0.77
     week
    0.77
    ime
    0.75
    ĸļ
    0.74
    orate
    0.71
    Act Density 0.027%

    No Known Activations