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

    Neuronpedia

    INDEX
    Explanations

    assertions evaluating boolean conditions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Heinz
    -0.67
    PREFERRED
    -0.64
    jkl
    -0.64
     cin
    -0.64
     Khu
    -0.61
    ynos
    -0.61
     Kain
    -0.60
     DAS
    -0.59
     Kula
    -0.59
     Ank
    -0.58
    POSITIVE LOGITS
    assertTrue
    1.63
    assertFalse
    1.34
    \{\\
    0.78
    IsTrue
    0.74
     resourceCulture
    0.73
    主教
    0.70
    (!(
    0.70
    RegressionTest
    0.69
     boolean
    0.68
    assertNotNull
    0.67
    Act Density 0.034%

    No Known Activations