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

    Neuronpedia

    INDEX
    Explanations

    specific proper nouns related to organizations, people, and technical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    довлет
    -0.66
     disambiguazione
    -0.61
     tilf
    -0.59
    unmodifiable
    -0.58
    Viitteet
    -0.58
     mellett
    -0.55
    clerView
    -0.54
    ANDUM
    -0.54
    İstinadlar
    -0.54
     wijze
    -0.53
    POSITIVE LOGITS
     Cla
    0.73
    cla
    0.68
     CLA
    0.68
    Cla
    0.67
    AddTagHelper
    0.65
    DockStyle
    0.64
     distraction
    0.62
     Kla
    0.62
     cla
    0.58
     clamped
    0.58
    Act Density 2.026%

    No Known Activations