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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and code snippets

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and symbols typically found in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ħĭ
    -0.90
    rael
    -0.86
    din
    -0.84
    Wars
    -0.78
    senal
    -0.77
    deen
    -0.76
    hof
    -0.75
    ovy
    -0.74
    bledon
    -0.74
    ascus
    -0.72
    POSITIVE LOGITS
     }
    1.16
     };
    1.15
     /*
    1.11
     //
    1.09
    };
    0.98
     });
    0.94
     ++
    0.87
    }"
    0.87
    */
    0.87
    //
    0.84
    Act Density 0.022%

    No Known Activations