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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their contextual use in written content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -1.01
    '):
    -0.97
    "):
    -0.93
     Forumite
    -0.93
    NUMX
    -0.93
     ―――――
    -0.91
    VIRONMENT
    -0.89
    \]
    -0.88
    VERTISEMENT
    -0.87
    '},
    -0.87
    POSITIVE LOGITS
     Thats
    1.12
    Thats
    1.09
     thats
    1.06
    Dont
    0.96
    this
    0.96
    thats
    0.95
     alot
    0.91
     Also
    0.90
    Lets
    0.89
    Also
    0.89
    Act Density 0.415%

    No Known Activations