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

    Neuronpedia

    INDEX
    Explanations

    phrases related to evaluation and critique of media and performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding words implying excessiveness

    np_acts-logits-general · gemini-2.0-flash

    too much

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.81
     AssemblyCulture
    -0.75
     ExecuteAsync
    -0.71
     cherchés
    -0.70
    UrlResolution
    -0.65
    хьтан
    -0.65
    tableFuture
    -0.64
    parsedMessage
    -0.64
    Initializable
    -0.61
    +:+
    -0.61
    POSITIVE LOGITS
     too
    3.71
    too
    3.07
    Too
    3.05
     Too
    3.01
     TOO
    2.80
     terlalu
    2.39
    TOO
    2.37
     demasiado
    2.34
     troppo
    2.34
     слишком
    2.29
    Act Density 0.682%

    No Known Activations