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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating specific locations or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    416
    -0.17
    nic
    -0.17
    ali
    -0.16
    ioc
    -0.15
    io
    -0.15
    ious
    -0.15
     Eisen
    -0.14
    iser
    -0.14
    wich
    -0.14
    rage
    -0.14
    POSITIVE LOGITS
     eye
    0.23
     angles
    0.20
    ataka
    0.19
     Eye
    0.19
     waist
    0.17
     chest
    0.17
    wa
    0.16
    eye
    0.16
    -eye
    0.16
     full
    0.16
    Act Density 0.088%

    No Known Activations