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

    Neuronpedia

    INDEX
    Explanations

    percentage numbers and demographic information

    oai_token-act-pair · gpt-3.5-turbo

    references to demographic data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ellie
    -0.71
     Canaver
    -0.70
    pload
    -0.68
     Destination
    -0.66
     Tracker
    -0.65
     Predator
    -0.64
    ãĥ¯
    -0.64
     Cerberus
    -0.63
     takedown
    -0.63
    wark
    -0.63
    POSITIVE LOGITS
     socio
    1.05
     socioeconomic
    1.04
     elderly
    0.95
     socially
    0.95
     unmarried
    0.92
     disadvantaged
    0.91
     (>
    0.91
     economically
    0.90
    medium
    0.88
     affluent
    0.87
    Act Density 0.563%

    No Known Activations