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

    Neuronpedia

    INDEX
    Explanations

    dates in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    dates and timestamps within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cons
    -0.71
     honoured
    -0.70
     darling
    -0.67
     dece
    -0.66
     permit
    -0.65
     undermin
    -0.65
     facilit
    -0.64
     Chal
    -0.63
     champions
    -0.63
     apprentices
    -0.63
    POSITIVE LOGITS
    20439
    1.00
    Twe
    0.92
    Loading
    0.92
    RAW
    0.90
    Rum
    0.88
    Inst
    0.88
    Twitter
    0.87
    TW
    0.87
    Official
    0.86
    Advertisements
    0.85
    Act Density 0.093%

    No Known Activations