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

    Neuronpedia

    INDEX
    Explanations

    capitalized occurrences of the word "Bew" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yen
    -0.17
     Tro
    -0.15
    inary
    -0.15
    ÙĨاÙĨ
    -0.15
    iphy
    -0.15
     wage
    -0.14
    سر
    -0.14
    ptic
    -0.14
    URNS
    -0.14
    ieren
    -0.14
    POSITIVE LOGITS
    ilder
    0.28
    itched
    0.24
    itch
    0.21
     bew
    0.18
    кеÑĤ
    0.18
    ITCH
    0.18
    ild
    0.18
    autiful
    0.17
    egend
    0.17
    ailing
    0.17
    Act Density 0.006%

    No Known Activations