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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical norms and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ſelves
    -0.59
    原始内容存档于
    -0.57
    archiviato
    -0.56
     pleaſure
    -0.56
     ſch
    -0.55
     juſ
    -0.54
     purpoſe
    -0.53
    ofür
    -0.52
     فريبيس
    -0.52
     cuantas
    -0.51
    POSITIVE LOGITS
    nick
    0.66
    norm
    0.64
     norm
    0.56
     differ
    0.56
     repaired
    0.54
    normal
    0.52
     differed
    0.50
     Differ
    0.50
     норма
    0.49
     normal
    0.48
    Act Density 0.301%

    No Known Activations