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

    Neuronpedia

    INDEX
    Explanations

    mentions of attributes in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ùĩ
    -0.19
    ness
    -0.18
    mie
    -0.17
    é®
    -0.15
    alytics
    -0.15
    edException
    -0.15
    stellen
    -0.15
    ÅĻet
    -0.15
    žen
    -0.15
    sik
    -0.14
    POSITIVE LOGITS
    ally
    0.26
    orous
    0.19
    ALLY
    0.19
    ually
    0.19
    istically
    0.18
    fully
    0.17
    (Attribute
    0.17
    urally
    0.17
    uters
    0.17
    åĢ¼
    0.17
    Act Density 0.074%

    No Known Activations