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

    Neuronpedia

    INDEX
    Explanations

    names of locations and people

    oai_token-act-pair · gpt-3.5-turbo

    references to American pop culture and notable individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ation
    -0.95
    ators
    -0.94
    ations
    -0.90
    ator
    -0.88
    ating
    -0.85
    ated
    -0.80
     Milan
    -0.77
    ATION
    -0.72
    ovember
    -0.71
    KER
    -0.71
    POSITIVE LOGITS
    heastern
    0.98
    ocial
    0.78
    icult
    0.73
     sap
    0.72
    ocratic
    0.71
     Downs
    0.68
    mort
    0.68
    rig
    0.67
    ellect
    0.65
     mosqu
    0.64
    Act Density 0.042%

    No Known Activations