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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs and forms of the verb "to be" indicating change or status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     its
    -1.28
     itself
    -0.98
     Its
    -0.98
    Its
    -0.97
    its
    -0.94
    它的
    -0.87
    它
    -0.84
    itself
    -0.77
     Itself
    -0.73
    webElementXpaths
    -0.72
    POSITIVE LOGITS
     themselves
    1.57
    themselves
    1.43
    それぞれ
    1.14
    どれも
    1.08
     serem
    1.06
     themſelves
    1.05
     모두
    1.03
     collectively
    1.02
    一个个
    1.01
     were
    1.00
    Act Density 0.926%

    No Known Activations