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

    Neuronpedia

    INDEX
    Explanations

    questions or queries that begin with "Q" and contain numerical identifiers or parameters

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.99
    #+#
    -0.85
    issauga
    -0.72
     NSCoder
    -0.70
    kháu
    -0.67
    InitVars
    -0.66
     saites
    -0.65
    WriteAttribute
    -0.60
    httphttps
    -0.60
     kasarigan
    -0.59
    POSITIVE LOGITS
    ↵
    0.82
    ↵↵
    0.65
    </h2>
    0.57
    <>());
    0.56
                          
    0.56
                           
    0.55
                   
    0.54
    0.54
                 
    0.52
                  
    0.52
    Act Density 0.187%
    No Known Activations