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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases, specifically durations like weeks, months, and years

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    inite
    -0.79
    emale
    -0.76
    acus
    -0.74
    acted
    -0.74
    Reviewer
    -0.67
    liction
    -0.65
    amate
    -0.63
    eton
    -0.62
    atively
    -0.62
    gebra
    -0.61
    POSITIVE LOGITS
     ago
    1.67
     Ago
    1.37
     ahead
    1.02
     later
    0.97
     shy
    0.92
     apart
    0.87
     Later
    0.85
     elapsed
    0.83
     earlier
    0.80
     overdue
    0.79
    Act Density 0.124%

    No Known Activations