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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific ethnic or religious groups

    oai_token-act-pair · gpt-3.5-turbo

    references to specific marginalized groups and their social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.76
    ĸļ
    -0.75
     Archdemon
    -0.75
    Rog
    -0.73
     ellipt
    -0.73
    arium
    -0.72
    eus
    -0.69
    ortex
    -0.67
    abolic
    -0.63
     Turing
    -0.61
    POSITIVE LOGITS
     nationalist
    1.02
    istani
    1.02
     nationalists
    1.01
     communities
    0.99
     Nadu
    0.99
     minorities
    0.98
    pora
    0.95
     separatist
    0.93
     Muslims
    0.92
     separatists
    0.89
    Act Density 0.190%

    No Known Activations