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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks that indicate the end of sentences or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    string literals and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ))
    -0.66
    ]))
    -0.63
    ])))
    -0.63
    )))
    -0.62
    )).
    -0.62
    ).
    -0.60
    ])
    -0.57
    )),
    -0.57
    ),
    -0.56
    ])),
    -0.56
    POSITIVE LOGITS
    <unused41>
    1.15
    [@BOS@]
    1.15
    <unused68>
    1.15
    <unused79>
    1.15
    <unused14>
    1.14
    <unused8>
    1.14
    <unused16>
    1.14
    <unused17>
    1.14
    <pad>
    1.14
    <unused3>
    1.14
    Act Density 0.022%

    No Known Activations