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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to various forms of measurement, analysis, or processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Савезне
    -1.05
     EconPapers
    -1.03
     iſt
    -1.00
     चीज़ों
    -1.00
    OGND
    -0.98
    WithIOException
    -0.96
     Theſe
    -0.95
     通販
    -0.93
    -0.92
     ―――――
    -0.91
    POSITIVE LOGITS
    .
    0.69
     in
    0.64
      
    0.64
    ,
    0.63
     so
    0.59
     is
    0.56
     (
    0.55
     on
    0.53
    ↵↵
    0.53
     and
    0.53
    Act Density 1.193%

    No Known Activations