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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting indicators related to data structures or code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.64
     itſelf
    -1.55
     Мексичка
    -1.55
    <bos>
    -1.53
    Personensuche
    -1.50
     themſelves
    -1.45
     ſeveral
    -1.45
     Jefus
    -1.43
     Efq
    -1.42
     ſtate
    -1.42
    POSITIVE LOGITS
      
    0.83
    /
    0.71
     and
    0.70
    ↵↵
    0.67
     
    0.66
    -
    0.62
    <eos>
    0.62
     /
    0.60
    ,
    0.59
     to
    0.59
    Act Density 0.069%

    No Known Activations