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

    Neuronpedia

    INDEX
    Explanations

    keywords associated with protests and opposition to authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eph
    -0.14
    RIX
    -0.14
    ỡ
    -0.14
    lernen
    -0.13
    å¿
    -0.13
    ucken
    -0.13
    entlich
    -0.12
    reeNode
    -0.12
    ابÛĮ
    -0.12
    ovÃŃ
    -0.12
    POSITIVE LOGITS
     decisions
    0.30
     actions
    0.30
     treatment
    0.30
     policies
    0.28
     decision
    0.27
     recent
    0.26
     moves
    0.24
     perceived
    0.24
     Treatment
    0.24
     practices
    0.24
    Act Density 0.214%

    No Known Activations