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

    Neuronpedia

    INDEX
    Explanations

    words related to statistics and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isbury
    -0.15
    uyá»ģn
    -0.14
    ãĥĨãĥ«
    -0.14
     extremes
    -0.14
    iales
    -0.14
    ewis
    -0.14
    feb
    -0.13
    utow
    -0.13
    bew
    -0.13
    ήÏĤ
    -0.13
    POSITIVE LOGITS
    èĭ¦
    0.16
    AIN
    0.15
    ropoda
    0.15
    ilan
    0.14
     invert
    0.14
    578
    0.14
     Ferry
    0.14
     Threshold
    0.14
     threshold
    0.14
    onga
    0.14
    Act Density 0.149%

    No Known Activations