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

    Neuronpedia

    INDEX
    Explanations

    references to training programs and modules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Osbourne
    -0.88
     Antara
    -0.86
     Diocese
    -0.80
     KeyCode
    -0.77
     Neel
    -0.75
     Heard
    -0.74
     Edd
    -0.73
     Spectroscopy
    -0.73
     negativity
    -0.72
     Magnetism
    -0.72
    POSITIVE LOGITS
     training
    1.23
     trainings
    1.06
     Training
    1.05
    Training
    1.00
    training
    0.97
     trainers
    0.97
    TRAINING
    0.92
     Trainings
    0.90
     TRAINING
    0.89
     trainer
    0.88
    Act Density 0.039%

    No Known Activations