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
    New Auto-Interp
    Negative Logits
    seau
    -0.17
    ctal
    -0.17
    ocache
    -0.16
    atsu
    -0.16
    acades
    -0.15
    иÑĨин
    -0.15
     Sect
    -0.15
    sembler
    -0.15
    bsolute
    -0.14
    ctr
    -0.14
    POSITIVE LOGITS
     Rosen
    0.17
    ardless
    0.16
    EO
    0.15
     ανά
    0.14
    vatel
    0.14
    isch
    0.14
    aliz
    0.14
     Turk
    0.14
    formed
    0.14
    ignKey
    0.13
    Act Density 0.080%

    No Known Activations