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

    Neuronpedia

    INDEX
    Explanations

    contractions in informal speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -1.71
     ‘
    -1.61
    ’
    -1.60
    ”
    -1.51
    ’,
    -1.46
    .’
    -1.42
    .”
    -1.39
    ’.
    -1.39
    ”,
    -1.33
    ,’
    -1.32
    POSITIVE LOGITS
     -"
    1.36
    ^(@)
    1.35
     Jefus
    1.34
     Efq
    1.33
    。"
    1.28
     purpoſe
    1.24
     Majefty
    1.23
     ftate
    1.21
     poffible
    1.21
     pleaf
    1.20
    Act Density 1.025%

    No Known Activations