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

    Neuronpedia

    INDEX
    Explanations

    instances of formatting symbols and punctuation typically used in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ^(@)
    -1.56
     تضيفلها
    -1.47
    yntaxException
    -1.44
     myſelf
    -1.44
    NUMX
    -1.43
     Савезне
    -1.42
     Мексичка
    -1.40
     itſelf
    -1.39
     Efq
    -1.35
    ſelf
    -1.33
    POSITIVE LOGITS
    <eos>
    1.20
    ↵↵
    1.17
    ↵
    1.01
    .
    0.84
    "
    0.83
     
    0.83
    :
    0.82
    (
    0.77
    1
    0.75
    5
    0.74
    Act Density 0.815%

    No Known Activations