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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal opinions or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -1.91
    ’
    -1.81
     ‘
    -1.70
    ”
    -1.67
    ’,
    -1.57
    .’
    -1.53
    ’.
    -1.47
    “
    -1.47
    .”
    -1.46
    ,’
    -1.45
    POSITIVE LOGITS
    。"
    1.42
     Efq
    1.32
     -"
    1.32
    ^(@)
    1.30
     ...'
    1.29
    ...'
    1.24
    ："
    1.22
     Jefus
    1.22
     doubtnut
    1.20
    --"
    1.18
    Act Density 0.719%

    No Known Activations