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

    Neuronpedia

    INDEX
    Explanations

    references to history and historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.83
     najbol
    -0.72
     RIPRODUZIONE
    -0.71
     rigue
    -0.70
     Vaticano
    -0.69
     Wolfram
    -0.69
     Lombar
    -0.68
     diría
    -0.68
     warszaw
    -0.67
    addPreferredGap
    -0.67
    POSITIVE LOGITS
     history
    2.23
    history
    1.89
     History
    1.83
     histories
    1.81
     HISTORY
    1.68
    History
    1.67
     useHistory
    1.61
    HISTORY
    1.60
     Histories
    1.42
     historia
    1.38
    Act Density 0.049%

    No Known Activations