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

    Neuronpedia

    INDEX
    Explanations

    mentions of time duration, particularly in months

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Vorte
    -0.58
    )−
    -0.56
    ArgsConstructor
    -0.54
    脚注の使い方
    -0.53
    abus
    -0.53
    ).</
    -0.53
    setupUi
    -0.52
    BagLayout
    -0.52
     entgegen
    -0.52
     Celle
    -0.52
    POSITIVE LOGITS
     persons
    0.99
     Persons
    0.97
     months
    0.94
    months
    0.86
    persons
    0.83
    Persons
    0.82
     CreateTagHelper
    0.80
     Months
    0.78
     PERSONS
    0.77
     MONTHS
    0.70
    Act Density 0.054%

    No Known Activations