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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and reflections on written discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    protoimpl
    -0.71
    Rüyada
    -0.68
    SharedCtor
    -0.67
     Himself
    -0.63
    脚注の使い方
    -0.63
     незавершена
    -0.62
    ...),
    -0.61
     Itself
    -0.58
     الرياضيه
    -0.58
     himself
    -0.56
    POSITIVE LOGITS
     furthermore
    1.01
     also
    0.98
     but
    0.97
     additionally
    0.97
     meanwhile
    0.92
     moreover
    0.91
     however
    0.89
     oh
    0.88
     luckily
    0.87
     if
    0.87
    Act Density 0.164%

    No Known Activations