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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and alternatives related to decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Paglinawan
    -1.07
    aarrggbb
    -1.07
    /**
    -0.97
    __':
    -0.94
    Autoritní
    -0.89
     itſelf
    -0.86
     myſelf
    -0.86
    -0.85
     EconPapers
    -0.85
     Roskov
    -0.84
    POSITIVE LOGITS
     
    0.63
    ↵
    0.62
      
    0.62
     has
    0.58
     is
    0.58
    QSize
    0.57
     of
    0.57
     was
    0.55
     (
    0.55
    ...
    0.55
    Act Density 0.508%

    No Known Activations