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

    Neuronpedia

    INDEX
    Explanations

    references to authority and its divine delegation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unsch
    -0.15
    ((↵
    -0.14
    errat
    -0.13
    ayette
    -0.13
    unya
    -0.13
    utin
    -0.13
    verbatim
    -0.13
    ÏĢιÏĥ
    -0.13
     Rural
    -0.13
    ixin
    -0.13
    POSITIVE LOGITS
     rightly
    0.21
     morally
    0.20
     ordering
    0.19
     moral
    0.19
     goods
    0.19
     ordered
    0.18
     coerc
    0.17
    auer
    0.17
     Ordering
    0.16
     duties
    0.16
    Act Density 0.007%

    No Known Activations