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

    Neuronpedia

    INDEX
    Explanations

    references to time periods, especially related to centuries

    oai_token-act-pair · gpt-3.5-turbo

    references to various centuries in historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.92
    toc
    -0.85
    DAQ
    -0.83
    oaded
    -0.82
     sqor
    -0.80
    aciously
    -0.80
    ebin
    -0.79
    orously
    -0.77
    acious
    -0.77
    ettings
    -0.76
    POSITIVE LOGITS
     Century
    1.18
     Fox
    0.83
     Mile
    0.76
     Vision
    0.75
    aire
    0.74
     Cent
    0.74
     Edison
    0.73
     Cig
    0.73
     Feet
    0.72
     Brotherhood
    0.72
    Act Density 0.017%

    No Known Activations