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

    Neuronpedia

    INDEX
    Explanations

    time-related information such as days, months, and years

    oai_token-act-pair · gpt-3.5-turbo

    references to time, specifically events and occurrences in relation to weeks, months, and years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ¶
    -0.56
    owsky
    -0.55
    este
    -0.55
    ources
    -0.53
    imon
    -0.52
    ordes
    -0.52
    robe
    -0.51
    Contents
    -0.50
    yles
    -0.50
     nowadays
    -0.49
    POSITIVE LOGITS
    's
    1.41
    ÃŃs
    0.91
    âĢ²
    0.85
    ´
    0.80
    \'
    0.76
    Ê
    0.70
     prayers
    0.67
    �
    0.66
    `
    0.65
    ividual
    0.63
    Act Density 0.151%

    No Known Activations