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

    Neuronpedia

    INDEX
    Explanations

    specific events or occurrences related to dates and locations

    oai_token-act-pair · gpt-3.5-turbo

    words indicating decisions or actions taken during significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     1961
    -0.92
     someday
    -0.91
     1997
    -0.91
     1990
    -0.91
     1951
    -0.90
     1996
    -0.90
     1947
    -0.89
     1991
    -0.87
     1956
    -0.87
     1978
    -0.87
    POSITIVE LOGITS
    cade
    0.74
    Reviewer
    0.74
    NAS
    0.73
     MSNBC
    0.73
     unveiling
    0.72
    BRE
    0.71
     Pastebin
    0.70
    EMS
    0.69
     announcing
    0.67
    UFC
    0.66
    Act Density 0.839%

    No Known Activations