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

    Neuronpedia

    INDEX
    Explanations

    references to physical bodies and body-related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    δά
    -0.18
    aises
    -0.17
    inger
    -0.16
    spd
    -0.16
    erna
    -0.15
    amac
    -0.15
    اÙĩÛĮ
    -0.14
    ignum
    -0.14
    èle
    -0.14
    GRAY
    -0.14
    POSITIVE LOGITS
    building
    0.21
    guard
    0.21
    guards
    0.21
     odor
    0.20
     Pier
    0.19
    builders
    0.19
     Butter
    0.19
     image
    0.18
    builder
    0.17
     pier
    0.17
    Act Density 0.013%

    No Known Activations