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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating capability or potential

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

    the auxiliary verb "can" followed by "be" in passive voice constructions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.40
    RenderAtEndOf
    -0.31
    HtmlAttribute
    -0.30
     logistique
    -0.30
    ponses
    -0.30
    try
    -0.29
     Beliefs
    -0.28
     try
    -0.28
    出版年
    -0.27
     []:
    -0.27
    POSITIVE LOGITS
    migrationBuilder
    0.73
     be
    0.62
     kasarigan
    0.60
    ########.
    0.57
    rabaya
    0.54
     variously
    0.52
     vary
    0.52
     sometimes
    0.52
     optionally
    0.50
    المناصب
    0.50
    Act Density 0.341%

    No Known Activations