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

    Neuronpedia

    INDEX
    Explanations

    dates specified in the format "Month Dayth, Year" within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    references to specific time periods and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStream
    -0.77
    Such
    -0.72
    ealous
    -0.71
    Yet
    -0.68
    agin
    -0.68
    SourceFile
    -0.66
    iffe
    -0.65
    That
    -0.62
    viation
    -0.62
    arah
    -0.62
    POSITIVE LOGITS
     we
    1.11
     there
    0.86
     please
    0.85
     THERE
    0.78
     you
    0.77
     attendees
    0.73
     participants
    0.70
    there
    0.70
    we
    0.70
     contestants
    0.69
    Act Density 0.305%

    No Known Activations