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

    Neuronpedia

    INDEX
    Explanations

    time-related terms, specifically referring to days or hours

    oai_token-act-pair · gpt-3.5-turbo

    references to time intervals or timing in events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    duct
    -0.76
    duction
    -0.76
    =-=-=-=-=-=-=-=-
    -0.70
    cephal
    -0.69
    Reviewer
    -0.66
    DL
    -0.65
    inite
    -0.65
    acus
    -0.65
    ubis
    -0.64
    browser
    -0.64
    POSITIVE LOGITS
     ahead
    0.87
     ago
    0.81
     shy
    0.80
     Ago
    0.80
     apiece
    0.73
     busiest
    0.69
     eve
    0.69
     premature
    0.68
     EDT
    0.68
    pring
    0.67
    Act Density 0.068%

    No Known Activations