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

    Neuronpedia

    INDEX
    Explanations

    references to various forms of training or educational activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     écl
    -0.78
     Osbourne
    -0.77
     Edd
    -0.76
     Diocese
    -0.75
     KeyCode
    -0.74
     carbone
    -0.72
     Neel
    -0.71
     parishi
    -0.70
     parishioners
    -0.70
    yargs
    -0.70
    POSITIVE LOGITS
     training
    1.89
     Training
    1.59
    training
    1.55
    Training
    1.54
     trainings
    1.50
     TRAINING
    1.41
    TRAINING
    1.39
     trainers
    1.30
     Trainings
    1.28
     trainer
    1.23
    Act Density 0.045%

    No Known Activations