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

    Neuronpedia

    INDEX
    Explanations

    references to data distributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cinogen
    -0.78
    +#+
    -0.77
    Facile
    -0.74
     vostri
    -0.73
     Boeh
    -0.72
     Jep
    -0.70
    لح
    -0.69
    rainy
    -0.69
    checs
    -0.69
     oocytes
    -0.68
    POSITIVE LOGITS
     distribution
    2.28
     Distribution
    2.03
     distribu
    1.97
     distributions
    1.95
    Distribution
    1.91
    distribution
    1.90
     distributing
    1.89
     distribute
    1.89
     DISTRIBUTION
    1.79
     distributed
    1.78
    Act Density 0.092%

    No Known Activations