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

    Neuronpedia

    INDEX
    Explanations

    the repeated phrase "the."

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

    the followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ainfi
    -0.65
     queſta
    -0.63
    BagConstraints
    -0.60
    XmlAccessType
    -0.59
     beſte
    -0.58
    richTextPanel
    -0.57
    AutoScaleMode
    -0.57
    بوابة
    -0.56
    <unused3>
    -0.56
    <unused23>
    -0.56
    POSITIVE LOGITS
     is
    0.49
    is
    0.40
     surla
    0.40
     arrest
    0.37
     ref
    0.37
     has
    0.36
    re
    0.35
     re
    0.35
     reduction
    0.35
     inclusion
    0.35
    Act Density 0.031%

    No Known Activations