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

    Neuronpedia

    INDEX
    Explanations

    terms related to precision and accuracy in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.77
     Centrale
    -0.71
    ImageBackground
    -0.71
    kaido
    -0.70
     Belf
    -0.70
     Burs
    -0.70
    wegg
    -0.68
     Burroughs
    -0.68
     megal
    -0.67
    Belf
    -0.67
    POSITIVE LOGITS
     grace
    1.21
    Grace
    1.20
     Grace
    1.19
    grace
    1.06
     GRACE
    1.06
     graceful
    1.06
    GRACE
    1.02
     elegance
    1.00
     gracefully
    0.94
    Precision
    0.92
    Act Density 0.076%

    No Known Activations