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

    Neuronpedia

    INDEX
    Explanations

    specific durations of time expressed in years or months

    oai_token-act-pair · gpt-3.5-turbo

    references to time durations and the passage of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olini
    -0.67
    anooga
    -0.63
    roth
    -0.59
     Lanka
    -0.56
    acus
    -0.56
    aimon
    -0.55
    roid
    -0.53
    hof
    -0.51
    ocracy
    -0.51
    eus
    -0.51
    POSITIVE LOGITS
     ago
    1.24
     Ago
    1.01
     overdue
    0.89
     anniversary
    0.81
     elapsed
    0.78
    ago
    0.73
    old
    0.69
    long
    0.69
     since
    0.65
     hiatus
    0.65
    Act Density 0.087%

    No Known Activations