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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "the" in various contexts

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

    owner, event, newspaper, funds, discussion, arrest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     дописавши
    -0.73
     propOrder
    -0.73
     itſelf
    -0.68
    exitRule
    -0.68
    sizeCache
    -0.66
    Rptr
    -0.66
    KommentareTeilen
    -0.66
    ſammen
    -0.64
    httphttps
    -0.63
    -0.63
    POSITIVE LOGITS
     now
    0.34
     mar
    0.31
     also
    0.29
    ↵
    0.28
     Ben
    0.26
      
    0.26
     isNameExpr
    0.26
     correct
    0.25
     means
    0.25
     imper
    0.25
    Act Density 0.006%

    No Known Activations