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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating authorship or sources of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nam
    -0.16
    Ñīи
    -0.15
    Nam
    -0.15
     Weinstein
    -0.14
    _________________↵↵
    -0.14
    INET
    -0.14
    ëļ
    -0.13
    й
    -0.13
    azen
    -0.13
    óc
    -0.13
    POSITIVE LOGITS
    spender
    0.15
    errer
    0.14
    ays
    0.14
    ีà¸ŀ
    0.14
    ccd
    0.14
    еÑı
    0.14
    ecided
    0.14
    isclosed
    0.14
    pong
    0.13
    quam
    0.13
    Act Density 0.032%

    No Known Activations