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

    Neuronpedia

    INDEX
    Explanations

    patterns of whitespace or formatting characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bbene
    -0.72
     $_"
    -0.63
    */;
    -0.60
     BorderRadius
    -0.60
    )();
    -0.59
    ."</
    -0.58
     houſe
    -0.57
     Efq
    -0.56
     Ith
    -0.56
     }}"></
    -0.56
    POSITIVE LOGITS
     Roskov
    0.69
    StructEnd
    0.67
      
    0.65
    ViewImports
    0.63
       
    0.62
    ">//
    0.61
    elemField
    0.60
                 
    0.59
                   
    0.58
             
    0.58
    Act Density 0.751%

    No Known Activations