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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation marks, particularly apostrophes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.81
    Abitanti
    -0.80
     صوتيه
    -0.79
     ―――――
    -0.78
     Pera
    -0.70
     alis
    -0.70
    NewUrlParser
    -0.68
    ంది
    -0.67
     Silo
    -0.67
    voje
    -0.66
    POSITIVE LOGITS
    s
    1.42
    ’
    1.30
    )’
    0.89
    €™
    0.88
    '
    0.88
    }'
    0.77
    ‘
    0.76
    .’
    0.74
    !’
    0.74
    ’.
    0.73
    Act Density 0.354%

    No Known Activations