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

    Neuronpedia

    INDEX
    Explanations

    tokens representing formatting elements or delimiters in structured documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ArgsConstructor
    -0.96
     EconPapers
    -0.94
     pinulongan
    -0.92
    ^(@)
    -0.91
     Мексичка
    -0.91
    تقاوى
    -0.90
    AxisAlignment
    -0.88
    SizeMode
    -0.83
    databind
    -0.81
    BRARY
    -0.80
    POSITIVE LOGITS
    .
    0.91
    ↵↵
    0.77
    .”
    0.70
    ”.
    0.69
    }}}}
    0.66
    <eos>
    0.66
    ]).
    0.65
    。
    0.64
    )).
    0.63
    ).
    0.62
    Act Density 0.991%

    No Known Activations