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

    Neuronpedia

    INDEX
    Explanations

    numeric values and measurements mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vaugh
    -0.66
     Niet
    -0.63
    ueless
    -0.63
    ãĥ¼ãĥĨ
    -0.59
    emale
    -0.58
    Ire
    -0.57
     vulner
    -0.57
     helicop
    -0.56
    luster
    -0.56
     Seym
    -0.56
    POSITIVE LOGITS
     largeDownload
    0.77
     ][
    0.68
     ]
    0.64
    zbollah
    0.59
     Âł
    0.58
     };
    0.58
     ];
    0.56
     );
    0.55
     âĢ¢
    0.55
    iannopoulos
    0.55
    Act Density 0.483%

    No Known Activations