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

    Neuronpedia

    INDEX
    Explanations

    references to dogs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rial
    -0.69
    prepareStatement
    -0.69
    Lz
    -0.68
    ']):
    -0.65
     Nij
    -0.65
    ═
    -0.65
    Bronnen
    -0.64
     Tomo
    -0.62
    FORMA
    -0.62
    (),
    -0.61
    POSITIVE LOGITS
     dog
    2.58
     dogs
    2.47
     Dog
    2.42
    Dog
    2.33
    dog
    2.30
     DOG
    2.18
     Dogs
    2.16
    Dogs
    1.98
     DOGS
    1.94
    DOG
    1.89
    Act Density 0.035%

    No Known Activations