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

    Neuronpedia

    INDEX
    Explanations

    variations of the verb "to be," indicating states of existence or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Being
    -0.18
    Being
    -0.18
    being
    -0.17
     being
    -0.17
     být
    -0.17
    many
    -0.16
     бÑĭÑĤÑĮ
    -0.16
     бÑĥÑĤи
    -0.15
    ly
    -0.15
     被
    -0.15
    POSITIVE LOGITS
    friend
    0.23
     able
    0.22
    COME
    0.20
    fall
    0.18
    eline
    0.18
    arded
    0.17
    fits
    0.17
    stride
    0.17
    get
    0.17
    /is
    0.17
    Act Density 0.501%

    No Known Activations