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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns referring to one's self or direct address

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ekl
    -0.17
    apiro
    -0.17
    utzer
    -0.17
    øy
    -0.15
    artz
    -0.15
    ama
    -0.14
    annon
    -0.14
    ugh
    -0.14
     sá»ķ
    -0.14
     âĨĴ↵↵
    -0.13
    POSITIVE LOGITS
     tennis
    0.27
     strategy
    0.24
     Tennis
    0.23
     opponent
    0.22
     doubles
    0.22
    strategy
    0.21
     Strategy
    0.21
    Strategy
    0.21
     match
    0.21
     matches
    0.21
    Act Density 0.000%

    No Known Activations