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

    Neuronpedia

    INDEX
    Explanations

    words associated with characterization and descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.54
    +#+#
    -0.51
    mogat
    -0.50
     acum
    -0.49
     épais
    -0.48
     Kendrick
    -0.48
    vician
    -0.48
     feveral
    -0.48
     Sicher
    -0.47
     הרי
    -0.47
    POSITIVE LOGITS
     regarded
    0.87
     treated
    0.81
     treating
    0.77
     Treated
    0.71
     Treat
    0.70
    TREAT
    0.70
    Treat
    0.69
     categorized
    0.69
     classified
    0.67
    ategorised
    0.67
    Act Density 0.674%

    No Known Activations