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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to performance metrics and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nacionales
    -0.61
     esquecer
    -0.47
     idea
    -0.47
     Idee
    -0.46
     vuestros
    -0.45
     Absicht
    -0.44
     fusil
    -0.43
    ۗ
    -0.43
     ideia
    -0.43
     necessários
    -0.43
    POSITIVE LOGITS
     performance
    1.84
     Performance
    1.72
    performance
    1.71
    Performance
    1.64
     performances
    1.56
     PERFORMANCE
    1.56
    PERFORMANCE
    1.47
     Performances
    1.41
    Performances
    1.33
     perform
    1.23
    Act Density 0.167%

    No Known Activations