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

    Neuronpedia

    INDEX
    Explanations

    references to stereotypes and discussions about their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uu
    -0.16
    usty
    -0.16
    aning
    -0.15
    endo
    -0.14
    asive
    -0.14
    riel
    -0.14
    uju
    -0.14
    ìĪł
    -0.14
    .sky
    -0.14
    Å¡lo
    -0.14
    POSITIVE LOGITS
    ishly
    0.14
    .Views
    0.14
     Caps
    0.14
    éĢļãĤĬ
    0.13
    apse
    0.13
    ize
    0.13
    .Dial
    0.13
    beeld
    0.13
     Fay
    0.13
    zs
    0.13
    Act Density 0.055%

    No Known Activations