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

    Neuronpedia

    INDEX
    Explanations

    phrases related to training or education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Expressway
    -0.80
     Vaticano
    -0.79
     WARRANT
    -0.73
     RAILWAY
    -0.72
    kadot
    -0.70
     Diocese
    -0.70
     Neel
    -0.70
     Molecules
    -0.67
     aé
    -0.66
     Shaft
    -0.65
    POSITIVE LOGITS
     training
    2.66
     Training
    2.35
    Training
    2.25
    training
    2.25
     TRAINING
    2.01
    TRAINING
    1.90
     trainings
    1.73
     Trainings
    1.56
     treinamento
    1.44
     pelatihan
    1.28
    Act Density 0.040%

    No Known Activations