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

    Neuronpedia

    INDEX
    Explanations

    words related to the human body

    oai_token-act-pair · gpt-3.5-turbo

    references to the human body and its attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hoover
    -0.78
     Clover
    -0.73
     Booth
    -0.71
     Ans
    -0.69
    ãĥĻ
    -0.68
     Doodle
    -0.68
    yrinth
    -0.64
     Fundamental
    -0.62
     Kafka
    -0.62
     Motorsport
    -0.59
    POSITIVE LOGITS
    guards
    1.30
    builders
    1.26
    building
    1.23
    builder
    1.22
    guard
    1.15
    weight
    1.14
     politic
    1.08
    fat
    1.05
    parts
    1.00
     odor
    0.94
    Act Density 0.037%

    No Known Activations