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

    Neuronpedia

    INDEX
    Explanations

    the use of the word "Had" in various contexts

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

    past tense or conditional past

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mybatisplus
    -0.74
    PyExc
    -0.65
    parsedMessage
    -0.61
    ніципалі
    -0.60
    adaptiveStyles
    -0.59
    DotNetBar
    -0.58
     skjø
    -0.57
     فريبيس
    -0.57
    Spoljašnje
    -0.57
    featureID
    -0.56
    POSITIVE LOGITS
     Had
    1.13
    Had
    1.05
     Has
    0.75
    Has
    0.68
     Been
    0.55
     Got
    0.54
     HAD
    0.53
    Been
    0.51
    Were
    0.50
     Was
    0.50
    Act Density 0.017%

    No Known Activations