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

    Neuronpedia

    INDEX
    Explanations

    terms related to ethical and moral judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DEM
    -0.57
     recoil
    -0.55
     moratorium
    -0.54
     unemployed
    -0.52
    rily
    -0.51
     curls
    -0.50
    Const
    -0.50
     withd
    -0.50
     )]
    -0.49
     skelet
    -0.49
    POSITIVE LOGITS
    uary
    0.78
    ordering
    0.74
    ivating
    0.72
    onduct
    0.70
    odon
    0.70
    inction
    0.68
    Studio
    0.68
    aminer
    0.67
    urai
    0.66
    odo
    0.66
    Act Density 0.136%

    No Known Activations