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

    Neuronpedia

    INDEX
    Explanations

    references to file operations and data structures in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -1.44
     Jefus
    -1.41
     Anſ
    -1.34
     iſt
    -1.34
     ſeveral
    -1.34
     ―――――
    -1.33
    ſelf
    -1.33
     $_"
    -1.31
     Efq
    -1.31
     itſelf
    -1.30
    POSITIVE LOGITS
      
    0.84
     
    0.72
       
    0.65
     ,
    0.62
     I
    0.60
     (
    0.59
     "
    0.58
     for
    0.58
     of
    0.56
        
    0.55
    Act Density 0.540%

    No Known Activations