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

    Neuronpedia

    INDEX
    Explanations

    JavaScript code snippets containing specific characters and symbols

    oai_token-act-pair · gpt-3.5-turbo

    punctuation symbols and code terminators in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Wars
    -0.86
    ovy
    -0.84
    rons
    -0.77
    agic
    -0.76
    ascus
    -0.75
    inators
    -0.75
    plet
    -0.74
    orts
    -0.73
    asions
    -0.73
     spons
    -0.73
    POSITIVE LOGITS
     /*
    1.09
     };
    1.08
     }
    1.08
     //
    1.01
    */
    0.97
    };
    0.91
     ++
    0.87
    -)
    0.87
    alias
    0.84
    ;;;;;;;;;;;;
    0.82
    Act Density 0.023%

    No Known Activations