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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and structural elements in a document

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

    Comes after a comma, parenthesis, or number

    np_acts-logits-general · gemini-2.0-flash

    accompanying file

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteBarrier
    -0.76
    LookAnd
    -0.76
    ьаж
    -0.70
    oredCriteria
    -0.66
    awtextra
    -0.62
     ujednoznacz
    -0.62
    sizeCache
    -0.61
     Réponses
    -0.61
    WriteLiteral
    -0.61
     rhestr
    -0.60
    POSITIVE LOGITS
     child
    1.08
    child
    1.08
     Child
    0.76
    Child
    0.76
     CHILD
    0.75
     children
    0.74
    children
    0.72
    CHILD
    0.70
     enfant
    0.57
     childs
    0.57
    Act Density 0.022%

    No Known Activations