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

    Neuronpedia

    INDEX
    Explanations

    specific nouns that represent entities or concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allery
    -0.14
    对æĸ¹
    -0.14
    enu
    -0.14
    ëŀĺ
    -0.14
    owards
    -0.13
    zelf
    -0.13
    /inet
    -0.13
    oria
    -0.13
    alty
    -0.13
    ernity
    -0.13
    POSITIVE LOGITS
    aire
    0.14
     æı
    0.14
    Rib
    0.13
     âĢ¦↵↵
    0.13
     martial
    0.13
    åĿĬ
    0.13
    åij¢
    0.13
    .ejb
    0.12
    ILT
    0.12
    YRO
    0.12
    Act Density 0.441%

    No Known Activations