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

    Neuronpedia

    INDEX
    Explanations

    references to training and educational initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nakalista
    -0.54
     propOrder
    -0.47
     AppComponent
    -0.45
    RRect
    -0.41
     veroor
    -0.39
     gevallen
    -0.38
    <bos>
    -0.38
     AspNetCore
    -0.36
     meg
    -0.35
    ModelAttribute
    -0.35
    POSITIVE LOGITS
     training
    4.06
     Training
    3.72
    Training
    3.69
    training
    3.58
     TRAINING
    3.48
    TRAINING
    3.22
     trainings
    2.95
     Trainings
    2.75
     treinamento
    2.63
    训练
    2.52
    Act Density 0.069%

    No Known Activations