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

    Neuronpedia

    INDEX
    Explanations

    phrases related to strong, aggressive, or strict stances or positions

    oai_token-act-pair · gpt-3.5-turbo

    references to a strict or "hardline" stance on various issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nih
    -0.80
    nesota
    -0.79
     Buildings
    -0.79
    à¤
    -0.78
    assies
    -0.77
    ãĤ¼ãĤ¦ãĤ¹
    -0.77
    ̶
    -0.76
    ĸļ
    -0.76
    neapolis
    -0.74
    brance
    -0.73
    POSITIVE LOGITS
     Islamist
    0.83
     Islamists
    0.80
     conservatives
    0.78
     stance
    0.78
     tendencies
    0.78
     zeal
    0.77
     stances
    0.75
     measures
    0.74
     tactics
    0.73
    edly
    0.71
    Act Density 0.047%

    No Known Activations