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

    Neuronpedia

    INDEX
    Explanations

    formatted numerical values and their rounding specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     faveur
    -0.57
     setId
    -0.55
    TypedDataSet
    -0.53
    anguard
    -0.51
    ]")]
    -0.49
    CPtr
    -0.49
    tute
    -0.48
     صوتيه
    -0.48
     ?>/
    -0.48
    bootstrapcdn
    -0.48
    POSITIVE LOGITS
     accuracy
    1.08
     precision
    1.03
     Accuracy
    0.88
    precision
    0.87
     rounding
    0.86
     Precis
    0.85
     Precision
    0.84
     decimals
    0.84
    Precis
    0.83
    accuracy
    0.83
    Act Density 0.291%

    No Known Activations