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

    Neuronpedia

    INDEX
    Explanations

    the verb "be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jis
    -0.60
    endenza
    -0.55
     proberen
    -0.54
     ơi
    -0.54
    ресто
    -0.53
    XmlAccessType
    -0.53
     tuyến
    -0.53
    jíma
    -0.53
    もった
    -0.52
    isesti
    -0.52
    POSITIVE LOGITS
     soyez
    0.88
     להיות
    0.85
    ToBe
    0.82
     être
    0.79
    Be
    0.78
     ddelweddau
    0.75
    Будь
    0.74
    NotBe
    0.72
    0.70
    être
    0.70
    Act Density 0.193%

    No Known Activations