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

    Neuronpedia

    INDEX
    Explanations

    mentions of animals and their related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lupin
    -0.83
     كومونز
    -0.78
     Rhapsody
    -0.78
     hypoch
    -0.76
     convaincre
    -0.75
    vernight
    -0.73
    Blame
    -0.73
     imponer
    -0.72
     poderosa
    -0.71
     ujednoznacz
    -0.70
    POSITIVE LOGITS
     animal
    1.39
     animals
    1.35
     Animal
    1.28
    Animal
    1.22
     Animals
    1.19
    animal
    1.19
    animals
    1.15
    Animals
    1.15
     ANIMAL
    1.14
    ANIMAL
    1.12
    Act Density 0.078%

    No Known Activations