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

    Neuronpedia

    INDEX
    Explanations

    references to political scandals and corruption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )}</
    -0.64
     hâte
    -0.64
    ]]:
    -0.61
     CreateTagHelper
    -0.61
    ."</
    -0.61
    horabuena
    -0.60
    ')):
    -0.59
    ).</
    -0.58
     ModelExpression
    -0.58
    +'</
    -0.58
    POSITIVE LOGITS
     scandal
    0.86
     controversy
    0.78
     scandals
    0.75
     incident
    0.70
     incidents
    0.69
     controversies
    0.68
    RegressionTest
    0.64
     allegations
    0.64
    事件
    0.63
     infamous
    0.63
    Act Density 0.466%

    No Known Activations