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

    Neuronpedia

    INDEX
    Explanations

    verbs related to rules, laws, and regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to legal rules and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Zeit
    -0.74
    ighting
    -0.74
    Plot
    -0.67
     Warm
    -0.65
     dreaming
    -0.65
     reminis
    -0.64
     Interstellar
    -0.64
     Velocity
    -0.63
     Glas
    -0.63
     Indust
    -0.62
    POSITIVE LOGITS
     apply
    1.48
     prohibit
    1.44
     expire
    1.28
     prohibiting
    1.26
     prohibits
    1.22
     forbid
    1.21
     restrict
    1.17
    apply
    1.17
     outlaw
    1.16
    enforcement
    1.16
    Act Density 0.255%

    No Known Activations