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

    Neuronpedia

    INDEX
    Explanations

    numerical values followed by words

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and their occurrences within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     helicop
    -0.64
     Niet
    -0.63
     Azerb
    -0.62
    iterranean
    -0.60
     Seym
    -0.60
    edIn
    -0.60
    Category
    -0.59
     Borders
    -0.58
    (*
    -0.58
     disadvant
    -0.57
    POSITIVE LOGITS
     ][
    0.77
     ]
    0.65
     )]
    0.60
     Falcon
    0.60
     )
    0.59
    azes
    0.59
     ].
    0.59
     ));
    0.58
     );
    0.57
     )))
    0.57
    Act Density 0.059%

    No Known Activations