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

    Neuronpedia

    INDEX
    Explanations

    block-ending symbols like curly braces and closing brackets in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.34
     pleaſure
    -1.34
     itſelf
    -1.34
     Theſe
    -1.33
     Monfieur
    -1.29
     Majefty
    -1.27
     himſelf
    -1.20
     Efq
    -1.19
     themſelves
    -1.18
     ſhe
    -1.15
    POSITIVE LOGITS
    }
    1.20
    }
    1.16
    };
    1.14
    .}
    1.12
    };
    1.06
     }
    1.02
    );}
    1.02
    ]}
    1.01
     };
    1.00
    ();}
    0.97
    Act Density 0.338%

    No Known Activations