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

    Neuronpedia

    INDEX
    Explanations

    occurrences of official titles and roles related to authority or government

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aken
    -0.15
    eds
    -0.15
     uncompressed
    -0.14
    arga
    -0.14
    ouch
    -0.13
    etto
    -0.13
    ervlet
    -0.13
    ubb
    -0.13
    arg
    -0.13
    Dummy
    -0.13
    POSITIVE LOGITS
     declined
    0.43
     declines
    0.35
     refused
    0.33
     decline
    0.32
     wouldn
    0.31
     declining
    0.29
    decl
    0.25
     neither
    0.25
     deferred
    0.24
     couldn
    0.24
    Act Density 0.048%

    No Known Activations