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

    Neuronpedia

    INDEX
    Explanations

    words that indicate approximation or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fermés
    -0.68
     knex
    -0.61
    TextWatcher
    -0.61
    vestimento
    -0.61
     Ulm
    -0.59
    晴れ
    -0.59
     dále
    -0.58
     lugs
    -0.58
    djangoproject
    -0.58
    ibm
    -0.58
    POSITIVE LOGITS
     nearly
    2.66
    nearly
    2.50
     Nearly
    2.43
    Nearly
    2.30
     almost
    1.94
     Almost
    1.82
    Almost
    1.77
    almost
    1.74
     virtually
    1.59
    Casi
    1.55
    Act Density 0.084%

    No Known Activations