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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their associations with numerical values or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Goy
    -0.71
    ixante
    -0.71
     Gwyn
    -0.69
    eſt
    -0.69
     ympä
    -0.67
     Dol
    -0.67
    tling
    -0.66
    émon
    -0.65
    IFICATE
    -0.65
    Ə
    -0.65
    POSITIVE LOGITS
    ])
    1.55
    })
    1.51
    ))
    1.50
    }))
    1.48
    )
    1.45
    ）
    1.41
    )}
    1.39
    ")
    1.38
    ]))
    1.38
    "))
    1.38
    Act Density 0.569%

    No Known Activations