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

    Neuronpedia

    INDEX
    Explanations

    numbers that relate to mathematical factors

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    resizingMask
    -0.53
    uttgart
    -0.50
     all
    -0.50
    all
    -0.48
    antMatchers
    -0.46
    Log
    -0.46
     safe
    -0.46
    itis
    -0.45
    RegressionTest
    -0.45
    راتيج
    -0.45
    POSITIVE LOGITS
    
    0.70
     ostavi
    0.65
     gepubliceerd
    0.65
    WindowConstants
    0.63
    IUrlHelper
    0.61
    newswire
    0.60
    Tikang
    0.59
    ⓘ
    0.59
    IsContent
    0.58
     useContext
    0.57
    Act Density 0.011%

    No Known Activations