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

    Neuronpedia

    INDEX
    Explanations

    occurrences of "text" and its variations in different contexts

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

    text with curly braces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    apnews
    -0.35
     developing
    -0.34
    Captor
    -0.32
    KindOfClass
    -0.32
    <h1>
    -0.31
    satis
    -0.31
     extraordinary
    -0.31
    Satis
    -0.30
     ddelweddau
    -0.30
     Alcalde
    -0.30
    POSITIVE LOGITS
    delaire
    0.56
    ⤹
    0.55
     Verſ
    0.54
    msgTypes
    0.52
     Commencez
    0.51
     ***!
    0.50
    TokenNameLBRACE
    0.50
    careous
    0.50
     queſta
    0.50
    createStatement
    0.50
    Act Density 0.023%

    No Known Activations