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

    Neuronpedia

    INDEX
    Explanations

    references to political oppression and repression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĪØ«
    -0.16
    ENCIL
    -0.15
    thern
    -0.15
    ypad
    -0.15
     znam
    -0.15
    .NULL
    -0.14
     loophole
    -0.14
     irres
    -0.14
    ego
    -0.14
    ypo
    -0.13
    POSITIVE LOGITS
     repression
    0.23
     censorship
    0.23
     Gest
    0.22
     clamp
    0.21
     Kafka
    0.20
     arrests
    0.20
     censor
    0.20
     authorities
    0.18
     police
    0.18
     Clamp
    0.18
    Act Density 0.377%

    No Known Activations