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

    Neuronpedia

    INDEX
    Explanations

    specific proper nouns or names associated with significant entities or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carroll
    -0.17
     Erie
    -0.16
     Wag
    -0.15
     Ðĵол
    -0.15
    ollah
    -0.15
    .hxx
    -0.15
     Peyton
    -0.14
     OID
    -0.14
     Staten
    -0.14
     Axios
    -0.14
    POSITIVE LOGITS
     Yamaha
    0.38
     Duc
    0.30
     MT
    0.27
     Kawasaki
    0.27
     bikes
    0.27
     Triumph
    0.27
    MT
    0.25
     bike
    0.25
     Moto
    0.24
     Motorcycle
    0.24
    Act Density 0.003%

    No Known Activations