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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and special characters in formatted text or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kiw
    -0.70
     Shin
    -0.70
     confessions
    -0.69
     Palestin
    -0.69
     Mush
    -0.66
     Tart
    -0.66
     Ryder
    -0.64
     Hobby
    -0.63
     sucker
    -0.62
     monog
    -0.62
    POSITIVE LOGITS
    },
    1.06
     =>
    0.99
    }.
    0.97
    ]}
    0.96
    }
    0.92
    than
    0.91
    },"
    0.90
    =>
    0.88
    ],[
    0.86
    };
    0.84
    Act Density 0.660%

    No Known Activations