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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "are" in various contexts

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

    are followed by states or characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mainloop
    -0.48
    adaptiveStyles
    -0.47
    TestingModule
    -0.47
    脚注の使い方
    -0.46
    исленность
    -0.46
    parsedMessage
    -0.45
     اهل
    -0.43
    帖最后由
    -0.43
    abstractmethod
    -0.43
    wachsenen
    -0.43
    POSITIVE LOGITS
    ίναι
    0.73
     are
    0.73
    Mereka
    0.63
    他们是
    0.63
     theyre
    0.61
    它们
    0.60
     blitt
    0.59
     שלהם
    0.59
     niitä
    0.59
    它們
    0.59
    Act Density 0.032%

    No Known Activations