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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence endings

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

    beginning-of-sequence (BOS) markers and document start tags.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
     
    -0.79
     FetchType
    -0.78
    odotus
    -0.77
    ugeot
    -0.76
    конец
    -0.72
    extAlignment
    -0.71
    ANCIAL
    -0.71
     Fut
    -0.71
     cellpadding
    -0.70
     vixion
    -0.69
    POSITIVE LOGITS
    .
    1.37
    ))).
    1.25
    }$.
    1.21
    ).
    1.17
    ])).
    1.15
    }.
    1.15
    ))$.
    1.14
    ].
    1.14
    $.
    1.13
    })).
    1.12
    Act Density 2.494%

    No Known Activations