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

    Neuronpedia

    INDEX
    Explanations

    expressions related to time

    oai_token-act-pair · gpt-3.5-turbo

    references to specific time periods or repeated mentions of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorite
    -0.71
     cipher
    -0.70
     plunge
    -0.67
    KING
    -0.67
    ortium
    -0.66
    malink
    -0.66
    mology
    -0.64
     WORLD
    -0.63
     mathemat
    -0.63
    MODE
    -0.61
    POSITIVE LOGITS
    frames
    0.85
    glass
    0.72
    opes
    0.67
    oshenko
    0.67
    staff
    0.66
    cross
    0.64
    iday
    0.64
    frame
    0.62
     distortions
    0.62
    oa
    0.61
    Act Density 0.019%

    No Known Activations