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

    Neuronpedia

    INDEX
    Explanations

    instances of training and educational materials or programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    training

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gle
    -0.50
     seemingly
    -0.48
    cop
    -0.46
    pec
    -0.46
    pon
    -0.44
    posi
    -0.44
    atto
    -0.43
     somewhat
    -0.43
     Pell
    -0.42
    inde
    -0.42
    POSITIVE LOGITS
     TRAINING
    1.03
    TRAINING
    1.02
    Training
    0.99
     trainings
    0.97
     Training
    0.96
     training
    0.96
    training
    0.90
     treinamento
    0.81
     retraining
    0.79
    培训
    0.74
    Act Density 0.011%

    No Known Activations