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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases and events

    oai_token-act-pair · gpt-3.5-turbo

    temporal references and significant dates in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nowadays
    -0.75
    >,
    -0.70
     tonight
    -0.69
     lately
    -0.69
     tomorrow
    -0.68
    ahime
    -0.67
    verty
    -0.67
    imar
    -0.67
     beforehand
    -0.66
    Present
    -0.66
    POSITIVE LOGITS
     researcher
    0.69
     consortium
    0.65
     researchers
    0.64
    raged
    0.63
     blogger
    0.60
     Newsweek
    0.60
     masked
    0.59
     surfaced
    0.58
     Mehran
    0.58
     representatives
    0.57
    Act Density 0.589%

    No Known Activations