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

    Neuronpedia

    INDEX
    Explanations

    phrases related to identity and societal roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quot
    -0.17
     ‘
    -0.15
     quot
    -0.14
    ...'
    -0.14
    ayıp
    -0.14
    aku
    -0.14
    ,’”
    -0.14
     Diamonds
    -0.13
    uxt
    -0.13
     Ori
    -0.13
    POSITIVE LOGITS
     "
    0.30
    ".↵
    0.23
     "↵
    0.21
    ."↵
    0.21
    ".
    0.21
     ".
    0.21
     ".↵
    0.20
    ï¼ļ"
    0.20
    "↵
    0.20
    ",
    0.19
    Act Density 0.232%

    No Known Activations