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

    Neuronpedia

    INDEX
    Explanations

    references to popular science fiction franchises and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -0.81
     otomatig
    -0.80
     itſelf
    -0.79
     myſelf
    -0.79
     AssemblyTitle
    -0.78
    ."));
    -0.76
     Monfieur
    -0.76
     kaynağından
    -0.75
     Anſ
    -0.74
     softmax
    -0.73
    POSITIVE LOGITS
    Leia
    0.54
     Jedi
    0.48
    kru
    0.48
    Yoda
    0.48
     II
    0.45
     __
    0.45
     
    0.44
    prises
    0.44
     "
    0.43
     Han
    0.43
    Act Density 0.429%

    No Known Activations