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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases or financial terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating time intervals measured in years or months

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Borders
    -0.78
    UTF
    -0.67
     ESC
    -0.66
     Nicarag
    -0.64
    HCR
    -0.62
    hemy
    -0.60
    SourceFile
    -0.60
    orem
    -0.60
    anca
    -0.59
     Compass
    -0.59
    POSITIVE LOGITS
    based
    1.12
    time
    1.07
    long
    1.05
    sized
    1.01
    to
    0.97
    years
    0.96
    level
    0.96
    wise
    0.94
    year
    0.92
    gap
    0.92
    Act Density 0.066%

    No Known Activations