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

    Neuronpedia

    INDEX
    Explanations

    elements related to societal control and dystopian themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hayes
    -0.19
    atron
    -0.18
    831
    -0.17
    311
    -0.16
    cation
    -0.15
     Bans
    -0.15
    811
    -0.15
    uvre
    -0.14
    591
    -0.14
    931
    -0.14
    POSITIVE LOGITS
    ilater
    0.19
     saf
    0.18
     Fet
    0.17
    alph
    0.17
    iences
    0.17
    иÑĤелÑĮÑģÑĤва
    0.16
     ordin
    0.16
    imb
    0.16
    rights
    0.16
    pees
    0.16
    Act Density 0.536%

    No Known Activations