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

    Neuronpedia

    INDEX
    Explanations

    references to training and education activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Osbourne
    -0.85
     écl
    -0.81
     Edd
    -0.80
     KeyCode
    -0.80
     Diocese
    -0.79
     bénévol
    -0.76
     Automobiles
    -0.75
     Antara
    -0.72
     Heard
    -0.71
     Necklace
    -0.71
    POSITIVE LOGITS
     training
    1.50
     Training
    1.27
    Training
    1.23
    training
    1.23
     trainings
    1.20
     TRAINING
    1.12
    TRAINING
    1.12
     trainers
    1.09
     trained
    1.06
    trained
    1.06
    Act Density 0.046%

    No Known Activations