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

    Neuronpedia

    INDEX
    Explanations

    punctuation or sentence-ending structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aniem
    -0.17
    urance
    -0.17
    igkeit
    -0.15
     («
    -0.15
    ’s
    -0.15
     (“
    -0.15
    :
    -0.14
    =-=-=-=-
    -0.14
    ,
    -0.14
    ↵
    -0.14
    POSITIVE LOGITS
    cord
    0.15
    fter
    0.14
    uci
    0.13
    Laughs
    0.13
    ýv
    0.13
    tbl
    0.13
     quoting
    0.13
    infeld
    0.12
    ichten
    0.12
    ',(
    0.12
    Act Density 0.031%

    No Known Activations