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

    Neuronpedia

    INDEX
    Explanations

    timings or specific time frames

    oai_token-act-pair · gpt-3.5-turbo

    mentions of time periods marked by "mid" followed by a specific time frame

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DRAG
    -0.76
     Freed
    -0.76
     badges
    -0.75
     Torch
    -0.71
     Achievements
    -0.70
     Calculator
    -0.66
     merits
    -0.64
     IDs
    -0.64
     Neville
    -0.63
     Petty
    -0.63
    POSITIVE LOGITS
    range
    1.28
    century
    1.22
    season
    1.22
    sent
    1.21
    sized
    1.17
    session
    1.17
    period
    1.16
    tier
    1.16
    distance
    1.15
    level
    1.14
    Act Density 0.026%

    No Known Activations