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

    Neuronpedia

    INDEX
    Explanations

    words related to governmental control or oppression

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to forms of repression and oppressive systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PATH
    -0.76
    TAIN
    -0.73
    tein
    -0.72
    Fair
    -0.71
    gran
    -0.69
    leaf
    -0.68
     litter
    -0.68
    lder
    -0.68
    pool
    -0.67
    laus
    -0.67
    POSITIVE LOGITS
     repression
    1.37
     oppression
    0.95
     repressive
    0.93
     suppression
    0.88
     regimes
    0.86
     dictatorship
    0.82
     crackdown
    0.80
     apparatus
    0.80
     brutality
    0.80
     dictators
    0.76
    Act Density 0.018%

    No Known Activations