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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and political concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to rights and social justice issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     anecd
    -0.64
    earable
    -0.62
    Sample
    -0.60
    CV
    -0.59
     largeDownload
    -0.59
    OVER
    -0.57
    ODUCT
    -0.57
    batch
    -0.57
    prisingly
    -0.56
    actic
    -0.56
    POSITIVE LOGITS
     tyranny
    0.81
     immoral
    0.80
     âĢ¦"
    0.79
     dignity
    0.79
     Sharia
    0.78
     righteousness
    0.78
     corrupt
    0.77
    .'"
    0.74
     caliphate
    0.73
     disgrace
    0.73
    Act Density 2.440%

    No Known Activations