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

    Neuronpedia

    INDEX
    Explanations

    references to specific items, such as articles, memos, or events

    oai_token-act-pair · gpt-3.5-turbo

    references to articles and organized discussions related to societal issues and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mayo
    -0.58
     Dane
    -0.58
    DAQ
    -0.57
    Category
    -0.56
     Oval
    -0.56
     Pru
    -0.55
    ãĥĥãĥī
    -0.55
    Ire
    -0.54
    bledon
    -0.54
    RELATED
    -0.53
    POSITIVE LOGITS
    ↵Âł
    0.90
     ·
    0.84
     ][
    0.83
     Âł
    0.81
     ..........
    0.77
    ³³³
    0.73
     ]
    0.72
     ....
    0.70
     ³³
    0.70
    îĢ
    0.68
    Act Density 0.920%

    No Known Activations