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

    Neuronpedia

    INDEX
    Explanations

    the word "originally"

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

    past states or origins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enumi
    -0.60
    SharedCtor
    -0.57
    出版年
    -0.55
     שוליים
    -0.52
    ynomial
    -0.52
    arakhand
    -0.51
    PMailer
    -0.50
     الاطلاع
    -0.49
     scoper
    -0.49
    
    -0.48
    POSITIVE LOGITS
     initially
    0.75
     originally
    0.72
     primarily
    0.68
     Initially
    0.67
    marily
    0.64
    urally
    0.63
    tically
    0.63
    Initially
    0.63
    Originally
    0.61
     Originally
    0.60
    Act Density 0.010%

    No Known Activations