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

    Neuronpedia

    INDEX
    Explanations

    terms related to physical bodies, organizations, or groups

    oai_token-act-pair · gpt-3.5-turbo

    references to various entities or groups identified as "body"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hoover
    -0.74
    ãĥĻ
    -0.73
    yrinth
    -0.71
    kers
    -0.67
    é¾į
    -0.65
     Clover
    -0.65
     Nex
    -0.64
     Generations
    -0.64
     Dickens
    -0.63
    antha
    -0.60
    POSITIVE LOGITS
    guards
    1.25
    guard
    1.18
     politic
    1.11
    building
    1.01
    weight
    0.92
    builder
    0.88
    chair
    0.88
    builders
    0.86
    work
    0.85
    anguage
    0.84
    Act Density 0.036%

    No Known Activations