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

    Neuronpedia

    INDEX
    Explanations

    narrative elements and character development in a story

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (!__
    -0.58
     "$@"
    -0.52
    baix
    -0.50
    ->___
    -0.47
     drauf
    -0.47
    ußen
    -0.47
     auffi
    -0.46
     poffe
    -0.46
    chke
    -0.46
     Either
    -0.45
    POSITIVE LOGITS
     when
    0.94
     lorsque
    0.73
     cuando
    0.72
     quando
    0.72
     هنگ
    0.72
     lorsqu
    0.70
    when
    0.68
     quand
    0.65
     وقتی
    0.65
     apabila
    0.64
    Act Density 0.334%

    No Known Activations