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

    Neuronpedia

    INDEX
    Explanations

    names of people, titles, or roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ï¼ļ↵↵
    -0.17
     (“
    -0.16
    ëĿ¼ëĬĶ
    -0.15
    té
    -0.14
     whim
    -0.14
    leurs
    -0.14
    ìĿ´ëĿ¼ëĬĶ
    -0.14
    :↵↵↵
    -0.14
    LETE
    -0.14
    ;
    -0.13
    POSITIVE LOGITS
     adding
    0.24
     Adds
    0.23
    added
    0.21
     Adding
    0.21
    adding
    0.21
    adds
    0.20
     added
    0.20
     adds
    0.20
    -added
    0.20
    Adds
    0.19
    Act Density 0.126%

    No Known Activations