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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and certain structural markers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.94
     myſelf
    -0.78
    enumii
    -0.70
    VersionUID
    -0.69
    ReusableCell
    -0.67
    ioutil
    -0.66
    WriteBarrier
    -0.66
    ...");
    -0.64
     tartalomajánló
    -0.64
     Eſ
    -0.63
    POSITIVE LOGITS
    確かに
    1.08
    なるほど
    0.98
    这话
    0.92
    たしか
    0.89
    Sounds
    0.89
    是啊
    0.86
     Sounds
    0.84
    这句话
    0.83
     Certainly
    0.74
     clearly
    0.74
    Act Density 0.280%

    No Known Activations