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

    Neuronpedia

    INDEX
    Explanations

    phrases related to regulations and legal processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sampling
    -0.16
    vang
    -0.16
     mastering
    -0.15
    escaping
    -0.15
    getting
    -0.14
    attering
    -0.14
     tasting
    -0.14
    sampling
    -0.14
    landing
    -0.14
     surviving
    -0.14
    POSITIVE LOGITS
     wa
    0.31
     mand
    0.29
     award
    0.28
     en
    0.27
     instit
    0.27
     approving
    0.27
     am
    0.26
     requiring
    0.23
     imposing
    0.23
     author
    0.23
    Act Density 0.218%

    No Known Activations