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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" in various tenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ubi
    -0.17
    endoza
    -0.15
    é¦Ĩ
    -0.15
    amburger
    -0.14
    fixed
    -0.14
    enate
    -0.13
    ива
    -0.13
    -alt
    -0.13
    ondon
    -0.13
    ocha
    -0.13
    POSITIVE LOGITS
     profile
    0.24
     recognized
    0.21
     Ñĥд
    0.21
     twice
    0.21
     honored
    0.21
     recently
    0.21
     fet
    0.20
     voted
    0.20
     named
    0.20
     featured
    0.20
    Act Density 0.048%

    No Known Activations