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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks that signify the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ContentAsync
    -0.59
    <bos>
    -0.58
     يتيمه
    -0.56
    WithEmail
    -0.55
     pastic
    -0.54
    ?\\
    -0.53
    Collegamenti
    -0.53
    ▬▬▬▬▬▬▬▬
    -0.52
     frit
    -0.51
    鈥
    -0.51
    POSITIVE LOGITS
    ########.
    0.77
     poichè
    0.73
     Lordships
    0.70
     néglig
    0.69
     économies
    0.68
     spokoj
    0.68
    ButterKnife
    0.67
    ٫
    0.66
    ddots
    0.66
     réfugiés
    0.65
    Act Density 0.680%

    No Known Activations