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

    Neuronpedia

    INDEX
    Explanations

    numbers that correspond to specific information or data points

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     ',
    -0.67
     ,"
    -0.67
     comprom
    -0.66
     ",
    -0.63
    milo
    -0.62
     cooperative
    -0.62
    naissance
    -0.60
     superst
    -0.60
     positively
    -0.58
     cho
    -0.57
    POSITIVE LOGITS
    ][
    1.82
    ]
    1.71
    ]"
    1.39
    ].
    1.35
    ])
    1.33
    ]).
    1.32
    ],[
    1.31
    ]'
    1.27
    ]:
    1.21
    ]),
    1.21
    Act Density 0.035%

    No Known Activations