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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate comparisons and relationships between entities or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.64
    PerPage
    -0.53
    cshtml
    -0.53
    orsese
    -0.51
     webdriver
    -0.51
    NORE
    -0.50
    ionage
    -0.48
     thiệu
    -0.48
    త్ర
    -0.47
    haltens
    -0.46
    POSITIVE LOGITS
    RegressionTest
    0.76
    ConstraintMaker
    0.62
    stretchr
    0.60
     विश्वसनीयता
    0.58
    κτηρισ
    0.57
    ftagPool
    0.55
    ImageContext
    0.51
     kasarigan
    0.51
     Pitman
    0.51
    cassert
    0.50
    Act Density 2.026%

    No Known Activations