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

    Neuronpedia

    INDEX
    Explanations

    references to confidence and understanding in learning contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    migrationBuilder
    -0.61
     autorytatywna
    -0.60
    RenderAtEndOf
    -0.59
    matchCondition
    -0.58
    httphttps
    -0.56
     subspecies
    -0.51
     despatch
    -0.50
    twimg
    -0.49
    ↘
    -0.49
    ditor
    -0.48
    POSITIVE LOGITS
     learning
    0.76
     concepts
    0.71
     memorize
    0.69
     propOrder
    0.68
    learning
    0.68
     memor
    0.67
     Learning
    0.65
     LEARNING
    0.65
     learned
    0.65
    Learning
    0.64
    Act Density 0.178%

    No Known Activations