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

    Neuronpedia

    INDEX
    Explanations

    terms related to performance and evaluation metrics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ligh
    -0.51
     heightened
    -0.50
     nim
    -0.47
    GLOBALS
    -0.46
     fleeting
    -0.45
     gruesome
    -0.43
    allen
    -0.42
     flipping
    -0.42
    ent
    -0.42
     pallet
    -0.42
    POSITIVE LOGITS
     performance
    1.32
     Performance
    1.26
     PERFORMANCE
    1.23
    Performance
    1.20
    performance
    1.12
    PERFORMANCE
    1.10
     performances
    1.09
     Performances
    1.09
     performer
    1.04
    Performances
    1.04
    Act Density 0.337%

    No Known Activations