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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a significant event or occurrence happening since a specific point in time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating durations of time since notable events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BILITIES
    -0.88
    bart
    -0.73
    ahn
    -0.70
    anie
    -0.69
    pta
    -0.69
     GOODMAN
    -0.67
    iculty
    -0.67
    ODY
    -0.66
    Fight
    -0.66
    rations
    -0.66
    POSITIVE LOGITS
     inception
    0.91
     1979
    0.89
     2009
    0.89
     1945
    0.88
     1975
    0.86
     1999
    0.86
     October
    0.85
     1928
    0.85
     1998
    0.84
     2006
    0.84
    Act Density 0.034%

    No Known Activations