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

    Neuronpedia

    INDEX
    Explanations

    references to dogs in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ră
    -0.42
    pulseira
    -0.42
     beleza
    -0.42
     Reif
    -0.40
    ⓧ
    -0.40
    ViewImports
    -0.39
    เศ
    -0.37
     Crespo
    -0.37
    inguém
    -0.36
     opinião
    -0.36
    POSITIVE LOGITS
     dogs
    1.71
    dogs
    1.41
     Dogs
    1.39
     pets
    1.38
    Dogs
    1.34
     rats
    1.25
     DOGS
    1.23
     horses
    1.22
     pigs
    1.19
     Pets
    1.18
    Act Density 0.179%

    No Known Activations