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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "be" in various forms

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

    Follows "be" or "Bec"

    np_acts-logits-general · gemini-2.0-flash

    because, beveled, believed, behest, befitting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.71
     faſt
    -0.62
     tranſ
    -0.60
     themſelves
    -0.60
    رشف
    -0.60
     canst
    -0.60
     ſeveral
    -0.60
     ſever
    -0.58
    tidaknya
    -0.57
     pleaſure
    -0.57
    POSITIVE LOGITS
    cause
    0.67
    havior
    0.62
     Roskov
    0.61
    CloseOperation
    0.58
    ológica
    0.52
    MigrationBuilder
    0.51
    CAUSE
    0.51
     cause
    0.50
     juridiques
    0.50
    Cause
    0.49
    Act Density 0.106%

    No Known Activations