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

    Neuronpedia

    INDEX
    Explanations

    various forms of the verb "to be" and its construction in sentences indicating conditions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     traumat
    -0.17
    .Selenium
    -0.16
    Ŀ
    -0.15
    igner
    -0.15
    urette
    -0.15
    aire
    -0.15
    inte
    -0.15
    uxe
    -0.15
    ocity
    -0.14
    Unnamed
    -0.14
    POSITIVE LOGITS
     candidates
    0.19
     prescribed
    0.19
     diag
    0.18
    gb
    0.17
     fitted
    0.17
     overdue
    0.16
    diag
    0.16
    pdf
    0.16
     continent
    0.15
    retain
    0.15
    Act Density 0.134%

    No Known Activations