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

    Neuronpedia

    INDEX
    Explanations

    sentences containing questions, statements, or specific punctuation that indicate uncertainty or inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.70
    <eos>
    -0.64
    ⓧ
    -0.55
     des
    -0.55
    ',
    -0.53
     
    -0.52
    乃至
    -0.51
    '],'
    -0.51
     or
    -0.51
    \",\"
    -0.50
    POSITIVE LOGITS
     ​​
    1.26
     שוליים
    1.01
    PerformLayout
    0.88
    audiovisuel
    0.88
    出版年
    0.85
    DeleteBehavior
    0.77
     auffi
    0.76
     gebeten
    0.76
    PhysRevLett
    0.74
    Przypisy
    0.72
    Act Density 0.428%

    No Known Activations