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

    Neuronpedia

    INDEX
    Explanations

    negative portrayals of human behavior and judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Liberties
    -0.17
    znik
    -0.17
    ứa
    -0.16
    okus
    -0.15
    leen
    -0.15
    ederland
    -0.14
    åŀ
    -0.14
    InnerText
    -0.14
    unky
    -0.14
    ishlist
    -0.14
    POSITIVE LOGITS
     intelligence
    0.35
     judgment
    0.34
     wisdom
    0.33
     judgement
    0.31
     logic
    0.30
    æĻº
    0.29
     rational
    0.28
     commons
    0.28
     brains
    0.28
     brain
    0.27
    Act Density 0.300%

    No Known Activations