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

    Neuronpedia

    INDEX
    Explanations

    symbols and characters that may represent or emphasize emotions or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    swire
    -0.17
    ignty
    -0.15
    wares
    -0.15
    éĬĢ
    -0.15
    ÏĢε
    -0.15
     Higgins
    -0.14
     Moran
    -0.14
    WA
    -0.14
    fic
    -0.14
    auc
    -0.14
    POSITIVE LOGITS
    ï¸
    0.20
    ï¸ı
    0.15
    koli
    0.14
    hausen
    0.14
    /slick
    0.14
     Vincent
    0.13
     vic
    0.13
    pyx
    0.13
    upal
    0.13
    à¸Ļาม
    0.13
    Act Density 0.018%

    No Known Activations