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
    erved
    -0.16
     founding
    -0.16
    .embedding
    -0.15
    istributed
    -0.15
     ****************************************
    -0.15
    iž
    -0.15
    linky
    -0.14
    ÑĤÑİ
    -0.14
    дÑı
    -0.14
    anche
    -0.14
    POSITIVE LOGITS
     birth
    0.30
     born
    0.29
     conceptual
    0.25
     developed
    0.25
    born
    0.24
     dream
    0.24
    Birth
    0.23
    birth
    0.22
    -born
    0.21
    develop
    0.21
    Act Density 0.128%

    No Known Activations