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

    Neuronpedia

    INDEX
    Explanations

    code constructs and data types commonly used in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     iſt
    -1.30
     ſind
    -1.11
     auffi
    -1.08
     Majefty
    -1.08
     ་་
    -1.07
     Efq
    -1.06
     ―――――
    -1.05
     $_(
    -1.05
     ſche
    -1.02
     Anſ
    -0.99
    POSITIVE LOGITS
     my
    0.86
     k
    0.72
      
    0.70
     f
    0.68
     test
    0.67
     x
    0.66
     p
    0.66
     d
    0.64
     ,
    0.63
     c
    0.62
    Act Density 0.165%

    No Known Activations