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

    Neuronpedia

    INDEX
    Explanations

    references to dogs and their activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rial
    -0.91
     Transparency
    -0.83
     Camb
    -0.82
     hypoch
    -0.78
     Arcadia
    -0.76
     Temples
    -0.75
     pinn
    -0.75
     Eſ
    -0.75
     Dami
    -0.73
     Holloway
    -0.73
    POSITIVE LOGITS
     dogs
    1.69
     Dog
    1.62
     dog
    1.60
     Dogs
    1.55
     DOG
    1.55
    Dog
    1.47
    Dogs
    1.41
     DOGS
    1.35
    dog
    1.33
    DOG
    1.29
    Act Density 0.102%

    No Known Activations