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

    Neuronpedia

    INDEX
    Explanations

    time-related events or historical comparisons

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "since" paired with numerical references indicating time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BILITIES
    -0.90
    bart
    -0.81
    ODY
    -0.72
    amina
    -0.72
    yll
    -0.70
    inders
    -0.67
    pta
    -0.66
    rations
    -0.66
    bly
    -0.65
    Reference
    -0.65
    POSITIVE LOGITS
     inception
    0.84
    rely
    0.81
     1945
    0.77
     1949
    0.76
     1999
    0.75
     1928
    0.75
     1895
    0.75
     1929
    0.74
     2009
    0.74
     1979
    0.73
    Act Density 0.032%

    No Known Activations