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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -1.75
    ’
    -1.70
     ‘
    -1.67
    ”
    -1.54
    ’,
    -1.50
    .’
    -1.45
    ’.
    -1.40
    .”
    -1.37
    ,’
    -1.36
    “
    -1.34
    POSITIVE LOGITS
    ^(@)
    1.40
     Efq
    1.39
     -"
    1.39
    。"
    1.37
     Jefus
    1.34
     ...'
    1.26
     Majefty
    1.24
     poffible
    1.24
     itſelf
    1.23
     pleaf
    1.23
    Act Density 1.233%

    No Known Activations