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

    Neuronpedia

    INDEX
    Explanations

    references to dogs and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Arcadia
    -0.93
     Rial
    -0.92
     Transparency
    -0.86
     Miri
    -0.84
     Temples
    -0.83
     Camb
    -0.82
     Plin
    -0.81
     Sedgwick
    -0.79
     Eſ
    -0.77
     EAN
    -0.77
    POSITIVE LOGITS
     dogs
    1.50
     Dog
    1.49
     Dogs
    1.43
     dog
    1.41
     DOG
    1.37
    Dog
    1.34
    Dogs
    1.32
    dogs
    1.20
     DOGS
    1.20
    dog
    1.18
    Act Density 0.099%

    No Known Activations