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

    Neuronpedia

    INDEX
    Explanations

    the word "all" and phrases emphasizing totality or completeness

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

    "All" followed by a preposition/article

    np_acts-logits-general · gemini-2.0-flash

    spread across or throughout

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hindsight
    -0.51
    atguigu
    -0.51
     javier
    -0.49
    +:+
    -0.49
    ChildScrollView
    -0.49
    DataBinding
    -0.48
    fowl
    -0.48
     Diſ
    -0.48
     iſt
    -0.48
    ⊱
    -0.48
    POSITIVE LOGITS
     across
    0.77
     throughout
    0.74
    throughout
    0.72
     all
    0.71
     الرياضيه
    0.69
     <>",
    0.60
    ]=>
    0.59
     through
    0.57
     hours
    0.57
     along
    0.57
    Act Density 0.087%

    No Known Activations