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

    Neuronpedia

    INDEX
    Explanations

    instances of the apostrophe used in contractions or possessives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -1.70
    ’
    -1.58
    ”
    -1.48
    ’,
    -1.38
     ‘
    -1.34
    ’.
    -1.32
    .’
    -1.29
    .”
    -1.27
    ,”
    -1.27
    ”,
    -1.24
    POSITIVE LOGITS
    。"
    1.51
    ...'
    1.43
     -"
    1.35
    ："
    1.33
     '
    1.32
     ...'
    1.31
    -'
    1.28
     -'
    1.28
    '...
    1.25
    --"
    1.24
    Act Density 0.296%

    No Known Activations