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

    Neuronpedia

    INDEX
    Explanations

    technical terms and specific measurements related to optimization and performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .onView
    -0.20
    é³´
    -0.16
    едини
    -0.15
    edition
    -0.14
    ç±
    -0.14
     покол
    -0.14
    kate
    -0.14
    anson
    -0.14
     equality
    -0.14
    è£Ĥ
    -0.13
    POSITIVE LOGITS
    uer
    0.17
    steen
    0.15
    179
    0.14
    _stderr
    0.14
    lace
    0.13
    aret
    0.13
    oen
    0.13
    atham
    0.13
     Belt
    0.13
     —
    0.13
    Act Density 0.001%

    No Known Activations