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

    Neuronpedia

    INDEX
    Explanations

    dates specified in the format 'mid-[month]' with varying degrees of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to time periods, specifically referencing "mid" followed by various time markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AVG
    -0.78
     DRAG
    -0.73
    éĹĺ
    -0.69
     badges
    -0.68
     Cosponsors
    -0.68
     Starr
    -0.68
     Canaver
    -0.65
     Neville
    -0.65
     Painter
    -0.64
     SOS
    -0.64
    POSITIVE LOGITS
    range
    1.14
    century
    1.11
    term
    1.11
    season
    1.11
    sent
    1.11
    sized
    1.07
    level
    1.07
    distance
    1.06
    grade
    1.04
    trial
    1.00
    Act Density 0.029%

    No Known Activations