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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "forgotten" and related concepts of belief and expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    目
    -0.47
    BagLayout
    -0.46
     inci
    -0.46
     pops
    -0.46
     eng
    -0.45
     deh
    -0.45
     terr
    -0.45
     prose
    -0.44
     Expl
    -0.44
     clou
    -0.43
    POSITIVE LOGITS
     believes
    1.30
     considers
    1.28
     forgets
    1.23
     forgotten
    1.18
     neglected
    1.13
     overlooked
    1.11
     považ
    1.09
     считает
    1.09
     thinks
    1.06
     consideró
    1.06
    Act Density 0.297%

    No Known Activations