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

    Neuronpedia

    INDEX
    Explanations

    specific dates and numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bread
    -0.16
     CE
    -0.15
     tie
    -0.14
    phins
    -0.14
     eye
    -0.14
     Piet
    -0.14
    ela
    -0.14
    olar
    -0.14
     zeros
    -0.14
    roll
    -0.14
    POSITIVE LOGITS
    seau
    0.17
    otec
    0.16
    érique
    0.15
    orta
    0.15
    furt
    0.15
    getto
    0.14
    èĬ
    0.14
    uniq
    0.14
    QWidget
    0.14
     Torch
    0.13
    Act Density 0.127%

    No Known Activations