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

    Neuronpedia

    INDEX
    Explanations

    the word "which" and its contexts in the text, indicating a focus on clauses or explanations introduced by this term

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

    consequence or result of which

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.65
     uLocal
    -0.59
    sidemargin
    -0.57
     صوتيه
    -0.56
     فريبيس
    -0.56
    adaptiveStyles
    -0.55
    uttosto
    -0.54
    /**
    -0.54
     useState
    -0.52
     الرياضيه
    -0.52
    POSITIVE LOGITS
     enables
    0.55
     hence
    0.54
     is
    0.53
     Hence
    0.50
     thereby
    0.50
     would
    0.49
     ensures
    0.48
     thus
    0.47
     helps
    0.47
    Hence
    0.46
    Act Density 0.041%

    No Known Activations