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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate identity or authorship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä¹ĭä¸Ģ
    -0.14
     addCriterion
    -0.13
    ạ
    -0.13
    onsense
    -0.12
    -eslint
    -0.12
    á»ĵi
    -0.12
    eparator
    -0.12
     chatte
    -0.12
    _STD
    -0.12
    СÐŀ
    -0.11
    POSITIVE LOGITS
     who
    1.23
    who
    1.08
     Who
    1.04
     whom
    0.97
    Who
    0.96
    è°ģ
    0.87
     quien
    0.82
     qui
    0.73
     WHO
    0.71
    WHO
    0.69
    Act Density 0.514%

    No Known Activations