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

    Neuronpedia

    INDEX
    Explanations

    references to government and public policy initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imir
    -0.16
    entanyl
    -0.15
    zcze
    -0.15
    pta
    -0.15
     macOS
    -0.14
    akit
    -0.14
    .hl
    -0.14
     ÎijÏĢ
    -0.14
    LOBAL
    -0.14
     derp
    -0.13
    POSITIVE LOGITS
     (
    0.22
     federal
    0.21
     [
    0.21
    0.20
     --
    0.19
     government
    0.19
     Fed
    0.19
     fed
    0.19
    ,
    0.18
     <
    0.18
    Act Density 0.003%

    No Known Activations