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

    Neuronpedia

    INDEX
    Explanations

    elements related to evaluation and endorsement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nackte
    -0.18
    htag
    -0.17
    èĽĽ
    -0.16
    APA
    -0.15
    aryana
    -0.15
    htags
    -0.14
    anian
    -0.14
    жд
    -0.14
    ESA
    -0.14
    ä¼
    -0.14
    POSITIVE LOGITS
    ness
    0.25
    ity
    0.19
    NESS
    0.18
    lyph
    0.16
    ITY
    0.15
    ÃŃl
    0.15
    -looking
    0.15
    luk
    0.15
    allet
    0.15
    emente
    0.15
    Act Density 0.005%

    No Known Activations