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

    Neuronpedia

    INDEX
    Explanations

    mentions of the physical body

    oai_token-act-pair · gpt-3.5-turbo

    mentions of deceased individuals and their bodies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ©Ł
    -0.86
    yrinth
    -0.77
     Kafka
    -0.75
    é¾į
    -0.71
    é¾įå
    -0.70
     Monthly
    -0.67
    kai
    -0.66
    Americ
    -0.65
     Hoover
    -0.64
     Opportun
    -0.63
    POSITIVE LOGITS
    guards
    1.40
    guard
    1.12
    heading
    0.95
    builder
    0.92
    builders
    0.89
    bags
    0.85
    building
    0.83
    letal
    0.82
    powder
    0.79
    fat
    0.78
    Act Density 0.022%

    No Known Activations