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

    Neuronpedia

    INDEX
    Explanations

    punctuations and their significance in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     FetchType
    -0.82
    ugeot
    -0.78
    odotus
    -0.74
    ANCIAL
    -0.74
    arangay
    -0.74
    конец
    -0.72
    LEncoder
    -0.72
     løpet
    -0.69
     
    -0.68
    ="<?=$
    -0.68
    POSITIVE LOGITS
    .
    1.15
    ))).
    1.12
    ])).
    1.08
    }$.
    1.06
    $.
    1.06
    })).
    1.06
    }.
    1.02
    ).
    1.02
    )}.
    1.01
    ))$.
    1.00
    Act Density 2.558%

    No Known Activations