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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ledon
    -0.15
    endor
    -0.15
    ãĥ³ãĥij
    -0.15
    jang
    -0.15
    ersh
    -0.15
    afort
    -0.14
    chet
    -0.14
    iteral
    -0.14
    ytic
    -0.14
    ilha
    -0.14
    POSITIVE LOGITS
    osph
    0.17
    st
    0.15
     Solomon
    0.15
    ACH
    0.14
    ass
    0.14
     Nass
    0.14
     CSR
    0.14
    unc
    0.14
     advanced
    0.13
     Mk
    0.13
    Act Density 0.000%

    No Known Activations