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

    Neuronpedia

    INDEX
    Explanations

    categories of entities or classifications

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Siri
    -0.47
    ѝ
    -0.47
    unknownFields
    -0.46
    ն
    -0.45
     meurt
    -0.44
    ness
    -0.44
     jälkeen
    -0.44
    AndPassword
    -0.44
    englisch
    -0.44
     aérea
    -0.43
    POSITIVE LOGITS
    ThroughAttribute
    0.87
    __':
    0.76
    Diweddarwch
    0.71
    RegressionTest
    0.68
    __':
    0.66
    featureID
    0.66
    WriteBarrier
    0.65
    SequentialGroup
    0.65
    fillType
    0.65
    formik
    0.65
    Act Density 0.050%

    No Known Activations