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

    Neuronpedia

    INDEX
    Explanations

    concepts related to decision-making and taking action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Its
    -1.21
     Its
    -1.19
     its
    -0.97
    its
    -0.84
     оно
    -0.67
     Оно
    -0.66
     ITS
    -0.66
    它的
    -0.60
    ITS
    -0.60
     jeho
    -0.57
    POSITIVE LOGITS
     them
    1.43
    uxxxx
    0.93
    them
    0.82
    TagMode
    0.79
     ARXIV
    0.72
     ainfi
    0.72
     وتسجيلات
    0.67
     المعيارى
    0.67
     malheure
    0.66
     THEM
    0.66
    Act Density 0.232%

    No Known Activations