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

    Neuronpedia

    INDEX
    Explanations

    dashes or hyphens used in lists or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     PLE
    -0.75
     {}",
    -0.75
     Ã
    -0.72
    ₄
    -0.72
     Benoit
    -0.69
     $<$
    -0.68
     ´
    -0.68
    {}",
    -0.67
    NOPQRST
    -0.67
     Merv
    -0.66
    POSITIVE LOGITS
    —
    1.77
    ”—
    1.65
    )—
    1.57
    !—
    1.54
    —“
    1.52
    ?—
    1.52
    ——
    1.52
    —(
    1.50
     —
    1.47
    ,—
    1.46
    Act Density 0.244%

    No Known Activations