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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "name" and phrases indicating a small number or selection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anio
    -0.19
    anan
    -0.18
    rim
    -0.15
    ÙĨدÙĩ
    -0.15
    420
    -0.15
    oen
    -0.15
    ynes
    -0.14
    ipa
    -0.14
    hai
    -0.14
    à¹ģà¸Ļ
    -0.14
    POSITIVE LOGITS
    agle
    0.16
     Magazine
    0.16
    uhn
    0.16
    ziel
    0.15
    esson
    0.14
     forg
    0.14
    xsd
    0.14
    ived
    0.14
     magazine
    0.14
    eref
    0.13
    Act Density 0.008%

    No Known Activations