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

    Neuronpedia

    INDEX
    Explanations

    references to dystopian themes in literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ump
    -0.19
    omain
    -0.18
    ial
    -0.18
    ict
    -0.17
    ummy
    -0.16
    IVED
    -0.16
    avis
    -0.16
    awn
    -0.15
    emand
    -0.15
    ÙĪÙĦÛĮ
    -0.14
    POSITIVE LOGITS
    .gdx
    0.19
    fully
    0.19
    ostel
    0.16
    οÏįν
    0.16
    allon
    0.15
    yo
    0.15
    anel
    0.15
    icl
    0.15
    ful
    0.15
    ocrats
    0.15
    Act Density 0.061%

    No Known Activations