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

    Neuronpedia

    INDEX
    Explanations

    references to the letter "S" or its different forms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REW
    -0.17
    гл
    -0.15
    lander
    -0.15
    ĽĦ
    -0.14
    ruk
    -0.14
    647
    -0.14
    ntax
    -0.14
    ifu
    -0.14
     Haupt
    -0.14
    ãĥªãĥ¼ãĤº
    -0.14
    POSITIVE LOGITS
    outh
    0.34
    ardin
    0.29
    OUTH
    0.22
    ousse
    0.22
    ierre
    0.21
    traits
    0.21
    ao
    0.20
    ør
    0.20
    anta
    0.20
    ão
    0.19
    Act Density 0.027%

    No Known Activations