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

    Neuronpedia

    INDEX
    Explanations

    statements indicating awareness or knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yntaxException
    -0.63
     queſta
    -0.60
    GEBURTSDATUM
    -0.58
    SBATCH
    -0.57
    InputBorder
    -0.57
    Espèce
    -0.56
    Derbyniad
    -0.56
     AttributeSet
    -0.54
    IBOutlet
    -0.54
    RegistryLite
    -0.54
    POSITIVE LOGITS
     know
    2.64
    know
    2.50
    Know
    2.47
     Know
    2.38
     KNOW
    2.19
    KNOW
    2.13
     knows
    2.11
    knows
    1.94
     knew
    1.74
    知道
    1.61
    Act Density 0.174%

    No Known Activations