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

    Neuronpedia

    INDEX
    Explanations

    references to specific geographic locations

    oai_token-act-pair · gpt-3.5-turbo

    references to the Aspen Institute or related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    role
    -0.67
    antha
    -0.62
    variable
    -0.57
    thy
    -0.57
    responsible
    -0.57
    aer
    -0.54
    rieve
    -0.54
    thora
    -0.54
    oute
    -0.54
    outed
    -0.54
    POSITIVE LOGITS
    ESE
    0.90
     Pradesh
    0.82
    ansas
    0.80
    IRC
    0.77
     Petroleum
    0.74
     skyline
    0.72
    ese
    0.70
     Airlines
    0.69
     Airways
    0.68
     Lumpur
    0.67
    Act Density 0.286%

    No Known Activations