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

    Neuronpedia

    INDEX
    Explanations

    strings and expressions related to text formatting or quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \""
    -1.07
    }}"
    -0.96
     $("<
    -0.85
     "}
    -0.85
     Menge
    -0.84
     "*",
    -0.82
    “”
    -0.82
    {}".
    -0.81
    (",")
    -0.80
    }".
    -0.80
    POSITIVE LOGITS
     '
    1.92
     ‘
    1.72
     ('
    1.45
    ='
    1.42
    ('
    1.37
    =>'
    1.35
    !='
    1.34
     (‘
    1.30
     ='
    1.27
    ==='
    1.24
    Act Density 0.168%

    No Known Activations