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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and periods indicating sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     juſ
    -0.86
    Билгалдахарш
    -0.79
     desmotivaciones
    -0.76
     myſelf
    -0.75
     ſou
    -0.75
     faſt
    -0.75
     viſ
    -0.75
     auffi
    -0.74
     itſelf
    -0.73
     ſever
    -0.72
    POSITIVE LOGITS
    .
    0.93
    }$.
    0.69
    $.
    0.63
     .
    0.62
    ].
    0.59
    }.
    0.57
    ).
    0.57
    |.
    0.56
    .'.
    0.56
    ?.
    0.54
    Act Density 1.524%

    No Known Activations