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

    Neuronpedia

    INDEX
    Explanations

    sections or markers that denote changes in context or structure in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -1.04
     iſt
    -0.93
    Rhestr
    -0.92
     étoient
    -0.91
     faſt
    -0.87
     avoient
    -0.86
    -0.85
     Monfieur
    -0.84
     pleaſure
    -0.83
    ſelf
    -0.81
    POSITIVE LOGITS
     
    1.39
    sprozess
    0.77
      
    0.77
    \{\\
    0.75
    sproz
    0.75
     "
    0.68
     K
    0.67
     
    0.67
       
    0.65
     C
    0.62
    Act Density 0.040%

    No Known Activations