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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esi
    -0.15
     adultes
    -0.15
    kest
    -0.14
    818
    -0.14
    ntax
    -0.14
    mente
    -0.14
    Almost
    -0.14
    almost
    -0.14
     rather
    -0.14
    ware
    -0.14
    POSITIVE LOGITS
     anymore
    0.31
     necessarily
    0.19
     nor
    0.18
     deter
    0.17
     trusted
    0.16
    alim
    0.16
     content
    0.16
     Nor
    0.15
     nÃło
    0.15
    éĤ£ä¹Ī
    0.15
    Act Density 0.054%

    No Known Activations