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

    Neuronpedia

    INDEX
    Explanations

    references to the creation and establishment of programs, initiatives, or governmental structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    recent
    -0.15
     lately
    -0.15
     recent
    -0.15
    olders
    -0.14
    rin
    -0.14
    æľĢè¿ij
    -0.13
    Ïħν
    -0.13
    ศร
    -0.13
     outgoing
    -0.13
     recently
    -0.13
    POSITIVE LOGITS
     mechanism
    0.25
     permanent
    0.22
     dedicated
    0.21
     separate
    0.19
     mechanisms
    0.18
     entity
    0.17
     pilot
    0.17
     framework
    0.17
     Mechan
    0.16
     proto
    0.16
    Act Density 0.300%

    No Known Activations