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

    Neuronpedia

    INDEX
    Explanations

    exclamatory statements or expressions of emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    !」
    -0.60
    Autoritní
    -0.55
    ?」
    -0.49
    原始内容存档于
    -0.49
     travailleurs
    -0.45
     lizenzfreies
    -0.44
    ?!”
    -0.44
    gameserver
    -0.43
     wciąż
    -0.43
    chées
    -0.43
    POSITIVE LOGITS
     !!
    1.52
     !
    1.46
     !!!
    1.36
     !)
    1.34
     !!!!
    1.23
     ?
    1.20
     !!!!!
    1.14
     !!!!!!
    1.12
     !"
    1.12
     ?)
    1.09
    Act Density 0.214%

    No Known Activations