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

    Neuronpedia

    INDEX
    Explanations

    adjectives and their modifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kus
    -0.16
    /UIKit
    -0.16
    nak
    -0.15
    .tt
    -0.14
    inary
    -0.13
    ìĿĦ
    -0.13
    ariance
    -0.13
    ниÑĨÑĮ
    -0.13
    à§ĩ
    -0.13
    th
    -0.13
    POSITIVE LOGITS
    ÑģÑĤÑİ
    0.17
    ackers
    0.15
    atsu
    0.15
    orsk
    0.14
    abant
    0.14
     Cory
    0.14
     Coch
    0.14
    ryn
    0.14
     Rifle
    0.13
    ooke
    0.13
    Act Density 0.116%

    No Known Activations