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

    Neuronpedia

    INDEX
    Explanations

    instances where "be" is used, particularly in the context of actions, contributions, or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "be" or "-" and precedes certain words

    np_acts-logits-general · gemini-2.0-flash

    words starting with be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TextInputType
    -0.61
    CLAS
    -0.60
    newArrayList
    -0.58
    MetaObject
    -0.58
    存于互联网档案馆
    -0.57
    üyük
    -0.55
    kheim
    -0.55
    complexType
    -0.54
    archiviato
    -0.54
    ￣)
    -0.52
    POSITIVE LOGITS
     autorytatywna
    0.57
     otomatig
    0.54
     Meksiku
    0.54
    Демографія
    0.45
     lägga
    0.44
     tartalomajánló
    0.44
    featureID
    0.42
    thing
    0.42
    sej
    0.42
    tager
    0.42
    Act Density 0.668%

    No Known Activations