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

    Neuronpedia

    INDEX
    Explanations

    the frequency of numerical values represented in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.08
     myſelf
    -1.08
    InjectAttribute
    -1.07
    rungsseite
    -1.05
     ―――――
    -1.04
     poffible
    -1.04
     للاسماء
    -1.01
     pleaſure
    -1.00
     AssemblyVersion
    -0.97
     Monfieur
    -0.96
    POSITIVE LOGITS
    0.67
    [toxicity=0]
    0.54
    /

    0.54
     mo
    0.52
    󠁢
    0.52
     or
    0.52
      (
    0.50
     atau
    0.50
     \&
    0.50
     Tw
    0.49
    Act Density 0.533%
    No Known Activations