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

    Neuronpedia

    INDEX
    Explanations

    references to performance metrics and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PathVariable
    -0.82
    adaptiveStyles
    -0.80
     Drapeau
    -0.78
     comigo
    -0.73
    yntaxException
    -0.72
     amanhã
    -0.72
     Gilman
    -0.71
     Rät
    -0.70
     Bigelow
    -0.70
     abierto
    -0.70
    POSITIVE LOGITS
     performance
    2.68
     Performance
    2.42
    Performance
    2.40
    performance
    2.31
     performances
    2.26
     PERFORMANCE
    2.24
    PERFORMANCE
    2.16
     Performances
    1.87
    Performances
    1.73
    perform
    1.68
    Act Density 0.096%

    No Known Activations