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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" in various forms and associated phrases

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

    Following "is" or "are" indicating a current state

    np_acts-logits-general · gemini-2.0-flash

    state of being or status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.66
     Commencez
    -0.64
    וויק
    -0.57
    webElementXpaths
    -0.56
    kloped
    -0.55
     vivement
    -0.52
    (")");
    -0.52
    IContainer
    -0.51
    brainly
    -0.51
     asimismo
    -0.51
    POSITIVE LOGITS
     pretty
    0.77
     kinda
    0.77
     weird
    0.66
    tifical
    0.65
     just
    0.62
     actually
    0.60
     horrible
    0.60
     terrible
    0.59
     awful
    0.59
     ridiculous
    0.58
    Act Density 0.495%

    No Known Activations