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

    Neuronpedia

    INDEX
    Explanations

    instances of technical or formatting elements within text, particularly in the context of documents or programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -1.02
     myſelf
    -0.88
     faſt
    -0.88
     ―――――
    -0.84
    ſelves
    -0.82
     Theſe
    -0.82
     uſed
    -0.80
     Jefus
    -0.80
     itſelf
    -0.79
     Chriſt
    -0.79
    POSITIVE LOGITS
    CJK
    2.13
    oneofs
    0.73
     honor
    0.70
    honor
    0.68
     señ
    0.64
    lně
    0.59
     jLabel
    0.58
     sì
    0.57
    Eggs
    0.57
     onor
    0.56
    Act Density 0.062%

    No Known Activations