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

    Neuronpedia

    INDEX
    Explanations

    legislative terms related to bills and laws

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    浪
    -0.15
    duced
    -0.15
    анÑģ
    -0.14
    adm
    -0.14
    aid
    -0.14
    Ø°
    -0.14
    abet
    -0.14
     suppressed
    -0.14
    alar
    -0.14
     whirl
    -0.13
    POSITIVE LOGITS
     author
    0.34
    author
    0.24
     ordering
    0.23
     mand
    0.23
     requiring
    0.22
    requ
    0.22
     award
    0.22
     guarantee
    0.21
     compelling
    0.21
     oblig
    0.20
    Act Density 0.301%

    No Known Activations