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

    Neuronpedia

    INDEX
    Explanations

    quantitative expressions of loss or demographic statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iri
    -0.15
    äge
    -0.14
    _preference
    -0.14
    osy
    -0.14
    ocr
    -0.13
    icot
    -0.13
    Ľ°
    -0.13
    eyim
    -0.13
    ÏĦοÏĤ
    -0.13
    senal
    -0.13
    POSITIVE LOGITS
    ailable
    0.15
    hen
    0.15
     ways
    0.15
     Ways
    0.15
    aze
    0.15
    riter
    0.15
    regon
    0.14
    xeb
    0.14
     compl
    0.14
     Subscriber
    0.14
    Act Density 0.055%

    No Known Activations