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

    Neuronpedia

    INDEX
    Explanations

    references to fictional characters or elements from various stories or franchises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upal
    -0.16
     Sponge
    -0.15
     Gün
    -0.15
    UF
    -0.14
     paddle
    -0.14
     Shut
    -0.14
    721
    -0.14
     Programming
    -0.14
     sponge
    -0.14
     padd
    -0.14
    POSITIVE LOGITS
     Witch
    0.23
    witch
    0.17
     witch
    0.17
     Baths
    0.16
     Vys
    0.15
    odash
    0.15
     Ger
    0.15
    麻
    0.15
    .sz
    0.15
     Warsaw
    0.15
    Act Density 0.004%

    No Known Activations