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

    Neuronpedia

    INDEX
    Explanations

    statistical references and terms related to model validation metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CanadaChoose
    -0.52
    الحياه
    -0.44
    ఔ
    -0.42
    Hochspringen
    -0.39
    amsmath
    -0.39
    LElement
    -0.38
    Personendaten
    -0.38
     linkovi
    -0.37
     cromado
    -0.37
    zungs
    -0.36
    POSITIVE LOGITS
     Indicators
    0.44
    UniformLocation
    0.42
    UnitTesting
    0.42
    ReusableCell
    0.42
     składa
    0.42
     Pair
    0.42
     Bowling
    0.41
    rspec
    0.41
     Train
    0.40
     ModelExpression
    0.40
    Act Density 0.383%

    No Known Activations