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

    Neuronpedia

    INDEX
    Explanations

    names of countries and regions

    oai_token-act-pair · gpt-3.5-turbo

    references to geographic locations and historical regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    msg
    -0.82
    inventoryQuantity
    -0.79
    Snap
    -0.76
     outspoken
    -0.73
     confidentiality
    -0.72
    Vote
    -0.72
    Companies
    -0.71
     accuracy
    -0.71
    NSA
    -0.70
    Rating
    -0.70
    POSITIVE LOGITS
     conquered
    0.99
     Minor
    0.95
     Indies
    0.88
     circa
    0.86
     Basin
    0.83
     Antiqu
    0.83
    alia
    0.81
     illum
    0.80
     Canal
    0.79
    ankind
    0.77
    Act Density 0.188%

    No Known Activations