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

    Neuronpedia

    INDEX
    Explanations

    instances of passive voice and actions taken by entities in regulatory contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     regulated
    -0.16
     prohibited
    -0.16
     banned
    -0.15
    eme
    -0.14
     protected
    -0.14
    igu
    -0.14
    ãĤµãĥ¼
    -0.14
     subsidized
    -0.14
     controlled
    -0.14
     barred
    -0.14
    POSITIVE LOGITS
     meant
    0.22
     designed
    0.20
     implemented
    0.20
     intended
    0.19
     enacted
    0.18
     signed
    0.17
    silent
    0.17
     applied
    0.17
    implemented
    0.16
     dra
    0.16
    Act Density 0.088%

    No Known Activations