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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically closing parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    დ
    -0.56
     bottom
    -0.56
     Grim
    -0.56
     Tur
    -0.54
    𝙜
    -0.54
     Chit
    -0.53
     сті
    -0.53
     Matth
    -0.53
    복
    -0.53
     Pin
    -0.52
    POSITIVE LOGITS
    ),
    1.94
    ()),
    1.85
    .),
    1.81
    '),
    1.81
    +),
    1.78
    ”),
    1.77
    }),
    1.77
    %),
    1.76
    )),
    1.75
    "),
    1.74
    Act Density 0.163%

    No Known Activations