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

    Neuronpedia

    INDEX
    Explanations

    specific punctuation marks that signify conversational breaks or transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     \@
    -0.63
    ävän
    -0.62
    Hdr
    -0.62
     Tome
    -0.61
    łby
    -0.60
    columnHeader
    -0.60
    sieur
    -0.59
     Gare
    -0.58
    ophyll
    -0.58
     crescent
    -0.58
    POSITIVE LOGITS
    ])
    0.96
    ))
    0.93
    ]),
    0.86
    ?).
    0.86
    )),
    0.86
    ?),
    0.83
    ),
    0.83
    )).
    0.82
    .)
    0.80
    ?)
    0.80
    Act Density 0.494%

    No Known Activations