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

    Neuronpedia

    INDEX
    Explanations

    information related to identification and classification, like country of registration, race, and model numbers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to race, country, and registration information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roxy
    -0.99
    inka
    -0.86
    raq
    -0.77
    etsk
    -0.75
    opa
    -0.75
    inth
    -0.73
    osures
    -0.73
    eln
    -0.70
    ldon
    -0.68
    anqu
    -0.67
    POSITIVE LOGITS
     affiliation
    1.05
     specificity
    0.89
     affili
    0.86
     specific
    0.82
     nationality
    0.81
     preference
    0.80
    names
    0.80
     identifier
    0.79
     specifics
    0.79
     selector
    0.78
    Act Density 0.405%

    No Known Activations