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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" in various tenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     certainly
    -0.17
    lej
    -0.14
    çĺ
    -0.14
     probably
    -0.14
    lover
    -0.14
    ival
    -0.14
     rất
    -0.14
    uga
    -0.14
    probably
    -0.13
     quite
    -0.13
    POSITIVE LOGITS
     вдÑĢÑĥг
    0.24
     yoksa
    0.20
     _______,
    0.18
     varsa
    0.17
     somehow
    0.17
     indeed
    0.17
    amed
    0.16
    maal
    0.16
     OTHERWISE
    0.16
    ëĿ¼ëıĦ
    0.16
    Act Density 0.129%

    No Known Activations