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

    Neuronpedia

    INDEX
    Explanations

    references to laws and their enforcement status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.18
     prohibited
    -0.17
     forbidden
    -0.15
     (
    -0.15
     barred
    -0.15
     Valle
    -0.15
     Lazy
    -0.15
     categor
    -0.15
    eken
    -0.15
     banned
    -0.14
    POSITIVE LOGITS
     enforce
    0.28
     applied
    0.27
     violated
    0.26
     binding
    0.26
     enforced
    0.24
     aplic
    0.23
    binding
    0.23
    Binding
    0.23
     Binding
    0.22
     Enforcement
    0.22
    Act Density 0.236%

    No Known Activations