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

    Neuronpedia

    INDEX
    Explanations

    closing parentheses or brackets in various contexts

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

    closing parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stöd
    -0.58
     spørgsmål
    -0.54
     spørsmål
    -0.53
     klachten
    -0.52
     äls
    -0.51
     fråga
    -0.51
     frågor
    -0.51
     bodyParser
    -0.50
     katze
    -0.49
     Störungen
    -0.48
    POSITIVE LOGITS
    ))))
    1.34
    ))
    1.34
    )))
    1.34
    )))))
    1.23
    ()))
    1.23
     ))
    1.23
    ,))
    1.19
    '))
    1.16
    )).
    1.15
    ))
    1.13
    Act Density 0.052%

    No Known Activations