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

    Neuronpedia

    INDEX
    Explanations

    references to animals and their behaviors or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.83
     Rhapsody
    -0.76
    withstanding
    -0.76
     Teb
    -0.76
     suprême
    -0.75
    AddTagHelper
    -0.72
     dourada
    -0.72
     كومونز
    -0.71
     metropolitana
    -0.70
     mediodía
    -0.70
    POSITIVE LOGITS
     animal
    2.00
     animals
    1.91
     Animal
    1.79
    animal
    1.78
    Animal
    1.76
    animals
    1.65
     ANIMAL
    1.65
     Animals
    1.64
    Animals
    1.59
    ANIMAL
    1.58
    Act Density 0.069%

    No Known Activations