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

    Neuronpedia

    INDEX
    Explanations

    code snippets or symbols used in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    twimg
    -0.42
    CopyWith
    -0.42
    ypeł
    -0.40
    -------------</
    -0.40
     Fels
    -0.39
    AnchorStyles
    -0.39
    Vidite
    -0.38
     Exacts
    -0.38
    InitVars
    -0.38
    samples
    -0.38
    POSITIVE LOGITS
            
    0.51
                
    0.49
          
    0.49
    aarrggbb
    0.48
    səhifə
    0.47
    TagMode
    0.46
              
    0.45
     Савезне
    0.44
     للمعارف
    0.43
        
    0.43
    Act Density 0.500%

    No Known Activations