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

    Neuronpedia

    INDEX
    Explanations

    various types of punctuation marks in code or text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Maru
    -0.77
    plet
    -0.76
     nắm
    -0.75
    vieve
    -0.74
     Ged
    -0.74
     Kna
    -0.71
     Flyer
    -0.71
    veer
    -0.71
     vân
    -0.71
     entanto
    -0.71
    POSITIVE LOGITS
    })));
    1.01
    ")
    0.94
    ",""
    0.93
    __*/
    0.91
    "}")
    0.91
    }")
    0.90
    ]]);
    0.88
    ]][
    0.85
    ']").
    0.85
    )")
    0.84
    Act Density 0.172%

    No Known Activations