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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political correctness and historical narratives regarding race

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     esquer
    -0.66
    ScopeManager
    -0.59
    eadilan
    -0.57
    #+#
    -0.57
    traceback
    -0.56
     tendre
    -0.56
    czaj
    -0.55
    ритори
    -0.53
     Amal
    -0.52
    roek
    -0.52
    POSITIVE LOGITS
     conservative
    1.18
     conservatives
    1.06
    Conservative
    1.01
     Conservative
    1.00
    conservative
    1.00
     GOP
    0.94
     Conservatives
    0.88
     Republican
    0.88
     conservatism
    0.86
     reactionary
    0.78
    Act Density 0.731%

    No Known Activations