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

    Neuronpedia

    INDEX
    Explanations

    specific technical terms and phrases associated with confirmation and agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propOrder
    -0.61
     дописавши
    -0.60
     Baillargeon
    -0.59
    ⓧ
    -0.58
    Spoljašnje
    -0.58
     himo
    -0.56
    +#+
    -0.56
     OFDb
    -0.55
     Paglinawan
    -0.55
     NSCoder
    -0.53
    POSITIVE LOGITS
    polate
    0.55
     Hist
    0.55
     averaging
    0.51
    as
    0.51
    ę
    0.49
    ja
    0.48
    ita
    0.48
    ೆ
    0.47
     Taub
    0.47
    etta
    0.46
    Act Density 0.248%

    No Known Activations