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

    Neuronpedia

    INDEX
    Explanations

    the verb "be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    many
    -0.15
     бÑĭÑĤÑĮ
    -0.15
     být
    -0.15
    Being
    -0.15
    uya
    -0.14
    оген
    -0.14
    being
    -0.14
     Being
    -0.14
    ly
    -0.13
    EGIN
    -0.13
    POSITIVE LOGITS
    friend
    0.25
     able
    0.19
    COME
    0.18
    fits
    0.17
    arded
    0.17
    /is
    0.17
    eline
    0.16
    fall
    0.15
    OfType
    0.15
    è¿«
    0.15
    Act Density 0.353%

    No Known Activations