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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating moral or ethical teachings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    deen
    -0.15
    TintColor
    -0.15
    eft
    -0.15
    rowsable
    -0.14
    йн
    -0.14
    Norm
    -0.14
    amy
    -0.14
     Norm
    -0.14
    AIT
    -0.14
     assignable
    -0.13
    POSITIVE LOGITS
     Wisdom
    0.15
    539
    0.15
     Pro
    0.15
     Richt
    0.15
    交
    0.15
     Bias
    0.14
     Prov
    0.14
     CPR
    0.14
     wisdom
    0.14
    affles
    0.14
    Act Density 0.096%

    No Known Activations