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

    Neuronpedia

    INDEX
    Explanations

    various forms of the verb "to be" and its contractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -1.39
     ‘
    -1.31
    .’
    -1.27
    ”
    -1.27
    ’
    -1.26
    ?’
    -1.23
    ’.
    -1.21
    ’,
    -1.19
    ,’
    -1.17
    .”
    -1.16
    POSITIVE LOGITS
     -"
    0.99
    。"
    0.97
    '
    0.95
     "¿
    0.93
     Majefty
    0.92
    berdayakan
    0.90
     ...'
    0.89
    ^(@)
    0.87
     "...
    0.86
     doubtnut
    0.86
    Act Density 1.073%

    No Known Activations