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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific formatting markers or structural elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.98
    fromnode
    -0.90
    StoryboardSegue
    -0.85
     الرياضيه
    -0.84
     Roskov
    -0.80
    featureID
    -0.80
    ThroughAttribute
    -0.80
    ngdoc
    -0.80
     دیکھیے
    -0.80
     Италијани
    -0.79
    POSITIVE LOGITS
     utafitiHapana
    0.46
    帖最后由
    0.44
    <bos>
    0.43
    america
    0.36
     veuillez
    0.35
    ’
    0.35
     i
    0.34
     desplazamiento
    0.33
     עלי
    0.33
    全文
    0.32
    Act Density 0.478%

    No Known Activations