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

    Neuronpedia

    INDEX
    Explanations

    references to significant or notable items in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.14
    lander
    -0.14
    ستاÙĨ
    -0.14
     tem
    -0.14
    li
    -0.13
    eya
    -0.13
     fallen
    -0.13
    UAGE
    -0.13
    ogue
    -0.13
    _likelihood
    -0.13
    POSITIVE LOGITS
     pes
    0.23
     thing
    0.20
     little
    0.20
     Pes
    0.19
    pes
    0.18
     blasted
    0.18
     damn
    0.18
    Pes
    0.17
     damned
    0.17
     darn
    0.17
    Act Density 0.179%

    No Known Activations