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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical or statistical notation in expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    RegistryLite
    -0.87
    parsedMessage
    -0.86
     Roskov
    -0.83
    LookAnd
    -0.82
    transQ
    -0.82
     Италијани
    -0.80
    SuppressMessage
    -0.77
    adaptiveStyles
    -0.72
    })));
    -0.69
    IUrlHelper
    -0.69
    POSITIVE LOGITS
     costas
    0.54
    visející
    0.53
     destinées
    0.49
     esboço
    0.48
    onekana
    0.48
     blanches
    0.47
    forbes
    0.47
     universale
    0.46
    conceito
    0.46
     permanentes
    0.46
    Act Density 0.024%

    No Known Activations