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

    Neuronpedia

    INDEX
    Explanations

    instances of closing punctuation marks in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.68
    rungsseite
    -0.67
     ainfi
    -0.66
     desmotivaciones
    -0.66
     ſtate
    -0.66
     pleaſure
    -0.66
    DotNetBar
    -0.61
     ſon
    -0.61
     feroit
    -0.60
     perſon
    -0.59
    POSITIVE LOGITS
    ").
    2.33
    ').
    2.22
    }).
    2.16
    )).
    2.16
    ”).
    2.08
    ]).
    2.08
    ()).
    2.06
    ')).
    2.06
    ")).
    2.05
     }).
    2.05
    Act Density 0.431%

    No Known Activations