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

    Neuronpedia

    INDEX
    Explanations

    references to hypocrisy and its implications in societal discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    argas
    -0.15
    argin
    -0.15
    ActivityResult
    -0.14
    dü
    -0.14
    ì¶ľ
    -0.14
    _VERBOSE
    -0.13
    ÐĶÐļ
    -0.13
    wheel
    -0.13
    itm
    -0.13
     Ñĥмов
    -0.13
    POSITIVE LOGITS
    ãĥ³ãĥĦ
    0.15
     ÑĢа
    0.14
    ãĥ¬ãĤ¹
    0.13
    RE
    0.13
    误
    0.13
    902
    0.13
     dred
    0.13
     aspir
    0.13
    ÏĦοι
    0.13
     inherited
    0.13
    Act Density 0.607%

    No Known Activations