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

    Neuronpedia

    INDEX
    Explanations

    patterns of punctuation and bracket usage in structured text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     trin
    -0.83
     pst
    -0.82
    bkz
    -0.79
    ׂ
    -0.76
     GTR
    -0.75
     StringTokenizer
    -0.73
     inclin
    -0.71
     Landon
    -0.68
     Gwend
    -0.68
     AGR
    -0.67
    POSITIVE LOGITS
    }]
    0.85
    .]
    0.85
    _]
    0.83
     $]$
    0.79
    ]].
    0.78
    isArray
    0.78
    ]]
    0.78
     ]
    0.74
    .*")]
    0.73
    }],
    0.72
    Act Density 0.308%

    No Known Activations