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

    Neuronpedia

    INDEX
    Explanations

    key terms related to regulatory standards and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ‘
    -0.17
     (~
    -0.15
     (“
    -0.14
     “âĢ¦
    -0.14
    ylon
    -0.14
     “
    -0.14
     (£
    -0.14
     Hlav
    -0.13
     utilise
    -0.13
    ‘
    -0.13
    POSITIVE LOGITS
     subsection
    0.21
     respecting
    0.21
     respect
    0.21
     Her
    0.18
     prescribed
    0.17
     —↵
    0.17
     referred
    0.17
     Parts
    0.16
     or
    0.16
    Parts
    0.15
    Act Density 0.004%

    No Known Activations