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

    Neuronpedia

    INDEX
    Explanations

    short phrases or sentences written by different individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their roles in various situations or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    united
    -0.72
     coffers
    -0.67
     Dates
    -0.66
     trillions
    -0.65
    etting
    -0.64
     mortals
    -0.63
     disparate
    -0.63
    irs
    -0.63
     Tickets
    -0.62
    ĸļ
    -0.62
    POSITIVE LOGITS
     remarked
    0.98
     surn
    0.97
     commented
    0.95
     told
    0.87
     testified
    0.87
     wrote
    0.83
     who
    0.81
     nicknamed
    0.77
     named
    0.76
     complained
    0.76
    Act Density 0.258%

    No Known Activations