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

    Neuronpedia

    INDEX
    Explanations

    phrases that express opinion or evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     anún
    -0.80
     mauva
    -0.80
     ་་
    -0.79
     photolibrary
    -0.78
     démocr
    -0.75
     pérd
    -0.75
     poichè
    -0.73
     própri
    -0.71
     técn
    -0.70
     perciò
    -0.68
    POSITIVE LOGITS
     "
    1.22
     “
    1.16
     
    1.03
     '
    0.97
     ‘
    0.93
     «
    0.93
     non
    0.90
     new
    0.88
     $
    0.87
     big
    0.85
    Act Density 2.898%

    No Known Activations