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

    Neuronpedia

    INDEX
    Explanations

    phrases involving forms of the verb "have" indicating possession or experience

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

    Follows "has" or "have" (perfect tense)

    np_acts-logits-general · gemini-2.0-flash

    has been

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kiin
    -0.33
    else
    -0.27
     anders
    -0.27
    地说
    -0.27
     výkon
    -0.26
     nästa
    -0.25
     langue
    -0.24
     iVar
    -0.24
     rendement
    -0.24
     geliyor
    -0.24
    POSITIVE LOGITS
     been
    1.29
     had
    0.92
    been
    0.89
     gotten
    0.81
    sizeCache
    0.80
     got
    0.80
     ब्रेकडाउन
    0.79
     Been
    0.78
     BEEN
    0.78
    had
    0.76
    Act Density 0.508%

    No Known Activations