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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific times or events occurring in the year

    oai_token-act-pair · gpt-3.5-turbo

    references to specific times or seasons of the year

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.73
    ingen
    -0.67
    conn
    -0.67
     unconscious
    -0.64
    license
    -0.62
    uppet
    -0.61
    document
    -0.59
     unnamed
    -0.59
    urger
    -0.58
    under
    -0.58
    POSITIVE LOGITS
     beck
    0.86
     rolls
    0.82
     bye
    0.82
     holidays
    0.81
     arrives
    0.80
     dawn
    0.80
     usher
    0.78
     kickoff
    0.78
     festivities
    0.77
     commence
    0.76
    Act Density 0.330%

    No Known Activations