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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific non-alphanumeric tokens or formatting elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    e
    -0.85
    ed
    -0.82
     Schroeder
    -0.81
     ORE
    -0.81
     Tind
    -0.80
    помним
    -0.78
    attro
    -0.75
    getvalue
    -0.75
     Bess
    -0.73
     Mendes
    -0.73
    POSITIVE LOGITS
    ()))
    1.60
    ']))
    1.59
    ]))
    1.50
    ())
    1.41
    ))
    1.39
    '))
    1.39
    ])
    1.38
    ++)
    1.38
    )))
    1.38
    __':
    1.37
    Act Density 0.033%

    No Known Activations