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

    Neuronpedia

    INDEX
    Explanations

    terms related to training and testing data in machine learning contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    train and test data split

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.71
    PerformLayout
    -0.66
    httphttps
    -0.66
    Tikang
    -0.63
     nakalista
    -0.63
    $_['
    -0.60
    tvguidetime
    -0.57
    endphp
    -0.57
    gura
    -0.52
    enumii
    -0.51
    POSITIVE LOGITS
     training
    0.62
     Training
    0.52
    VertexAttrib
    0.48
    Training
    0.47
     Trainer
    0.45
     T
    0.45
     TRAINING
    0.45
     background
    0.43
     Trainings
    0.43
     trainer
    0.42
    Act Density 0.008%

    No Known Activations