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

    Neuronpedia

    INDEX
    Explanations

    specific types of coding-related keywords and phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to coding, class definitions, and data types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ):
    -0.68
     entreprene
    -0.67
     paras
    -0.66
     ).
    -0.66
    ò
    -0.65
    ñ
    -0.64
    naissance
    -0.63
     pione
    -0.63
    ©¶æ
    -0.63
    ?).
    -0.62
    POSITIVE LOGITS
    >
    1.18
    '
    1.07
    ]
    1.06
    }
    1.05
    "
    1.00
    []
    0.92
    ]'
    0.90
    |
    0.89
    }}
    0.85
    {
    0.83
    Act Density 0.072%

    No Known Activations