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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.78
     maș
    -0.73
     houſe
    -0.68
     Jefus
    -0.58
     affari
    -0.57
     Level
    -0.56
    ztály
    -0.54
     enfans
    -0.54
     CanadaChoose
    -0.53
    getLevel
    -0.53
    POSITIVE LOGITS
    بوابة
    0.68
    তথ্যসূত্র
    0.51
    .。
    0.49
     coincide
    0.48
    。
    0.48
     ardından
    0.47
     pretende
    0.47
     οποία
    0.45
    %，
    0.45
    <tfoot>
    0.45
    Act Density 0.008%

    No Known Activations