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

    Neuronpedia

    INDEX
    Explanations

    terms related to training and conditioning processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.72
    HomeAsUpEnabled
    -0.58
     تانيه
    -0.57
     الحره
    -0.55
     المعيارى
    -0.54
    λίου
    -0.54
    Personendaten
    -0.53
     Dars
    -0.52
     Normdatei
    -0.51
     MainAxisSize
    -0.51
    POSITIVE LOGITS
     training
    1.04
    training
    0.99
     retraining
    0.95
    Training
    0.95
     Training
    0.92
     Trainings
    0.90
     TRAINING
    0.88
    TRAINING
    0.81
     trainings
    0.81
    trained
    0.79
    Act Density 1.004%

    No Known Activations