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

    Neuronpedia

    INDEX
    Explanations

    formatted output strings in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.80
     dedans
    -0.67
     sympy
    -0.64
     setuptools
    -0.63
    -0.63
    adaptiveStyles
    -0.61
     AppColors
    -0.61
    __()
    -0.60
    🏽
    -0.60
    "…
    -0.59
    POSITIVE LOGITS
    ("%
    1.97
     "%
    1.48
    ('%
    1.47
     ("%
    1.46
    ,"%
    1.33
     '%
    1.19
    ="%
    1.08
    ='%
    1.06
    "%
    0.96
    '%
    0.93
    Act Density 0.099%

    No Known Activations