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

    Neuronpedia

    INDEX
    Explanations

    present tense forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sbin
    -0.17
    licht
    -0.16
    ÑĤоÑĢа
    -0.15
    ãĤ¤ãĥī
    -0.15
    AJOR
    -0.14
     ofs
    -0.14
    Ïīδ
    -0.13
     oku
    -0.13
     Barth
    -0.13
    pile
    -0.13
    POSITIVE LOGITS
    unner
    0.14
    unsch
    0.14
    its
    0.14
    ideon
    0.14
    ibal
    0.14
    uko
    0.13
     Vaults
    0.13
    rique
    0.13
    tion
    0.13
    imap
    0.13
    Act Density 0.165%

    No Known Activations