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

    Neuronpedia

    INDEX
    Explanations

    instances of the verbs "do" and "did" in various forms and contexts

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

    did as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fantasi
    -0.32
    mathcal
    -0.30
     McKin
    -0.30
    #![
    -0.29
    ätzlich
    -0.29
    lecteur
    -0.29
     voted
    -0.29
     didn
    -0.29
    石
    -0.29
     torch
    -0.28
    POSITIVE LOGITS
    AndEndTag
    0.88
    RectangleBorder
    0.70
     AssemblyCulture
    0.68
    featureID
    0.67
    دانشنامهٔ
    0.64
    DockStyle
    0.64
    complexContent
    0.60
    delwed
    0.56
    GOTREF
    0.56
    astify
    0.56
    Act Density 0.026%

    No Known Activations