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

    Neuronpedia

    INDEX
    Explanations

    references to the collective subject "we" in various contexts

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

    "we" followed by verbs explaining content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    QMetaType
    -0.65
    ſelf
    -0.63
    ſelves
    -0.62
     ſtand
    -0.58
     ſta
    -0.57
    DotNetBar
    -0.54
    AutoresizingMask
    -0.54
     okuyayım
    -0.54
     ſel
    -0.53
    styleable
    -0.53
    POSITIVE LOGITS
     We
    0.56
    We
    0.48
     we
    0.47
     create
    0.42
    我们将
    0.40
     insight
    0.40
    วันที่
    0.39
    要
    0.39
     tale
    0.39
     describe
    0.39
    Act Density 0.059%

    No Known Activations