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

    Neuronpedia

    INDEX
    Explanations

    words related to oppression and social injustice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     بالنسبة
    -0.52
     __('
    -0.52
    ))]
    -0.50
    })]
    -0.48
     jsPsych
    -0.48
    AxisAlignment
    -0.45
    colate
    -0.44
    merkungen
    -0.44
    ilton
    -0.44
    RegressionTest
    -0.43
    POSITIVE LOGITS
     hoping
    2.18
     thinking
    1.98
     believing
    1.87
     expecting
    1.72
     knowing
    1.66
     fearing
    1.58
     Hoping
    1.57
    thinking
    1.54
    Hoping
    1.51
     intending
    1.46
    Act Density 0.832%

    No Known Activations