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

    Neuronpedia

    INDEX
    Explanations

    instances of the phrase "to be" and related phrases indicating obligation or expectation

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

    to be followed by action verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     crochê
    -0.42
     ocurrió
    -0.41
    kijken
    -0.41
    शि
    -0.41
    bender
    -0.40
     estekak
    -0.39
     penjelasan
    -0.38
    adalupe
    -0.38
    casila
    -0.38
     murieron
    -0.37
    POSITIVE LOGITS
     muſt
    0.52
     ſhould
    0.51
     Must
    0.51
     ſhall
    0.50
     shall
    0.49
    دانشنامهٔ
    0.47
     deverá
    0.47
     fhall
    0.47
    Must
    0.46
     MUST
    0.46
    Act Density 0.026%

    No Known Activations