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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating negation or lack of occurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onViewCreated
    -0.91
     تضيفلها
    -0.88
    GraphicsUnit
    -0.85
    GEBURTSDATUM
    -0.80
    رشف
    -0.77
    Enders
    -0.74
    pexpr
    -0.74
    RegressionTest
    -0.70
    InputBorder
    -0.70
    脚注の使い方
    -0.69
    POSITIVE LOGITS
     stuff
    0.67
     veldig
    0.64
     ...
    0.56
     T
    0.56
     '
    0.55
     
    0.54
     virgen
    0.53
     "
    0.53
    ↵
    0.53
     I
    0.52
    Act Density 0.147%

    No Known Activations