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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values and terms relevant to measurement and standards in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ged
    -0.16
    ified
    -0.15
    appable
    -0.14
    linger
    -0.14
    ging
    -0.14
    ifying
    -0.14
    ERVED
    -0.14
    sic
    -0.14
    cken
    -0.14
    .LayoutParams
    -0.14
    POSITIVE LOGITS
    ฯ
    0.20
    /manual
    0.15
    orer
    0.15
    orie
    0.14
    aden
    0.14
    éf
    0.14
    åħĴ
    0.14
    Hp
    0.14
    atter
    0.13
    elry
    0.13
    Act Density 0.848%

    No Known Activations