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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases and patterns, particularly in the context of personal opinions and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ^(@)
    -1.04
     "...
    -0.97
     -"
    -0.93
     doubtnut
    -0.93
    #+#
    -0.92
     ...'
    -0.91
     $\$
    -0.88
     '"
    -0.88
    ...'
    -0.87
    ..."
    -0.84
    POSITIVE LOGITS
     “
    1.66
    ”
    1.57
    ’
    1.51
     ‘
    1.50
    “
    1.47
    ’,
    1.46
    ’.
    1.43
    .’
    1.41
    ,’
    1.38
    ,”
    1.34
    Act Density 1.152%

    No Known Activations