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

    Neuronpedia

    INDEX
    Explanations

    references to body-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "body"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kafka
    -0.87
     Dickens
    -0.72
     Hoover
    -0.72
     Ans
    -0.70
     Jarrett
    -0.68
     Booth
    -0.68
    ãĥĻ
    -0.67
     Tart
    -0.66
     Trey
    -0.65
     Doodle
    -0.65
    POSITIVE LOGITS
    guards
    1.27
    builders
    1.12
    guard
    1.09
    building
    1.04
    builder
    1.00
    weight
    0.99
    parts
    0.94
    anguage
    0.94
    wash
    0.92
    fat
    0.88
    Act Density 0.025%

    No Known Activations