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

    Neuronpedia

    INDEX
    Explanations

    references to demographic statistics or numerical data

    oai_token-act-pair · gpt-3.5-turbo

    statistical data and percentages related to political affiliation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vend
    -0.69
     dressing
    -0.69
    antes
    -0.69
     boiler
    -0.67
     pier
    -0.65
     sten
    -0.65
     airst
    -0.64
     dare
    -0.64
    mens
    -0.64
     oath
    -0.63
    POSITIVE LOGITS
    verages
    1.17
    Average
    1.13
     averages
    1.01
     Average
    0.97
     averaged
    0.96
    flation
    0.95
    Percent
    0.95
     Percentage
    0.95
     Compar
    0.95
    Trend
    0.88
    Act Density 0.611%

    No Known Activations