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

    Neuronpedia

    INDEX
    Explanations

    patterns associated with quoted strings or dialogue in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    closing quotation marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $_(
    -0.84
    AddTagHelper
    -0.84
    ingual
    -0.82
     queſta
    -0.82
    lihood
    -0.82
    <unused17>
    -0.79
     InputDecoration
    -0.79
    <unused41>
    -0.79
    <unused28>
    -0.79
    [@BOS@]
    -0.79
    POSITIVE LOGITS
    ")
    0.84
    ')
    0.73
    )")
    0.66
    "]
    0.64
    ())
    0.63
    }))
    0.63
    }")
    0.62
    (".")
    0.61
    "]))
    0.60
    ))
    0.60
    Act Density 0.045%

    No Known Activations