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

    Neuronpedia

    INDEX
    Explanations

    terms related to totality and inclusiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tiroirs
    -0.47
    izarse
    -0.46
    gebn
    -0.46
    engesch
    -0.44
    ensch
    -0.43
    Билгалдахарш
    -0.42
    ArgsConstructor
    -0.42
     bouncing
    -0.42
     leaning
    -0.41
    enschutzer
    -0.41
    POSITIVE LOGITS
     모든
    0.65
     tuturor
    0.62
    一切
    0.60
     wszystkich
    0.59
     every
    0.58
     deleteAll
    0.57
     various
    0.56
     wszystkie
    0.56
     wszel
    0.56
     mọi
    0.56
    Act Density 0.526%

    No Known Activations