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

    Neuronpedia

    INDEX
    Explanations

    inquiries or topics related to questions and their associated contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ].)
    -0.84
     myſelf
    -0.81
     Majefty
    -0.80
     faſt
    -0.77
     "¡
    -0.74
    Rhestr
    -0.74
     pleaſure
    -0.73
     ―――――
    -0.73
     endfor
    -0.73
    FWIW
    -0.71
    POSITIVE LOGITS
      
    0.67
    Firstly
    0.60
     Firstly
    0.58
     disini
    0.57
       
    0.57
    AutoScale
    0.56
     azioni
    0.56
     dolayı
    0.54
     In
    0.54
     It
    0.54
    Act Density 0.014%

    No Known Activations