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

    Neuronpedia

    INDEX
    Explanations

    numbers and mathematical expressions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rave
    -0.60
     racks
    -0.53
    âĢij
    -0.51
    ãĢİ
    -0.51
    ":[{"
    -0.48
     proced
    -0.48
     trouble
    -0.47
     (£
    -0.46
     insider
    -0.46
     ($
    -0.46
    POSITIVE LOGITS
     )
    3.39
     ),
    2.78
     ).
    2.77
     .)
    2.70
     ))
    2.63
     ):
    2.60
     )]
    2.50
     );
    2.48
     )))
    2.31
     ));
    2.16
    Act Density 0.013%

    No Known Activations