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

    Neuronpedia

    INDEX
    Explanations

    terms related to training and education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Osbourne
    -0.87
     Antara
    -0.85
     Diocese
    -0.81
     Edd
    -0.79
     Sedgwick
    -0.77
     KeyCode
    -0.77
     negativity
    -0.74
     Neel
    -0.74
     Spectroscopy
    -0.73
     bénévol
    -0.73
    POSITIVE LOGITS
     training
    1.20
     trainings
    1.02
     Training
    1.01
     train
    0.97
    Training
    0.96
    training
    0.93
     trainers
    0.92
    TRAIN
    0.89
    trained
    0.88
     TRAINING
    0.88
    Act Density 0.049%

    No Known Activations