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

    Neuronpedia

    INDEX
    Explanations

    references to animals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BufferException
    -0.53
     يتيمه
    -0.49
     Administrativna
    -0.48
     edelstahl
    -0.47
     récomp
    -0.47
     régulière
    -0.47
     laſſen
    -0.46
    parsedMessage
    -0.46
     müſſen
    -0.46
     gustaMe
    -0.45
    POSITIVE LOGITS
     Animal
    1.30
    Animal
    1.22
     animal
    1.22
    animal
    1.12
     ANIMAL
    0.99
    ANIMAL
    0.96
    動物
    0.60
    动物
    0.59
    LabelTagHelper
    0.49
     defaultstate
    0.47
    Act Density 0.053%

    No Known Activations