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

    Neuronpedia

    INDEX
    Explanations

    the word "be" in various contexts and grammatical forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulumi
    -0.18
    oriously
    -0.17
    _attachments
    -0.16
    aign
    -0.15
    /compiler
    -0.14
    UNCH
    -0.14
    nesday
    -0.14
    ä¿Ĺ
    -0.13
    uggage
    -0.13
    åij³
    -0.13
    POSITIVE LOGITS
     sure
    0.40
     fore
    0.28
     warned
    0.28
     advised
    0.26
     Sure
    0.26
     prepared
    0.25
     aware
    0.25
     patient
    0.24
    sure
    0.23
     assured
    0.22
    Act Density 0.028%

    No Known Activations