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

    Neuronpedia

    INDEX
    Explanations

    names of high-ranking officials or executives

    oai_token-act-pair · gpt-3.5-turbo

    the presence of punctuation, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lings
    -0.70
    ":"/
    -0.69
    eeds
    -0.68
    izons
    -0.68
    ento
    -0.67
    fw
    -0.66
     dots
    -0.65
    Gaza
    -0.65
    awatts
    -0.65
    ismo
    -0.63
    POSITIVE LOGITS
     Steve
    1.08
     Mike
    1.08
     Jeffrey
    1.06
     Michael
    1.04
     Philip
    1.03
     Andrew
    1.03
     Denis
    1.03
     David
    1.02
     Deborah
    1.02
     Darren
    1.01
    Act Density 0.160%

    No Known Activations