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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions or terms, especially related to specific weeks or weekdays

    oai_token-act-pair · gpt-3.5-turbo

    references to recent publications or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pron
    -0.67
     PAT
    -0.67
     sacrific
    -0.63
     sew
    -0.62
    icent
    -0.60
     parap
    -0.59
     ect
    -0.59
    coat
    -0.56
     ancest
    -0.56
     quo
    -0.56
    POSITIVE LOGITS
     titled
    0.83
     outlining
    0.78
     headlined
    0.76
    doi
    0.76
    NPR
    0.73
    enthal
    0.73
    published
    0.72
     detailing
    0.72
     afternoon
    0.71
    arie
    0.69
    Act Density 0.168%

    No Known Activations