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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social interaction and personal reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amd
    -0.16
    eron
    -0.14
     lim
    -0.14
     subject
    -0.14
    ̣
    -0.14
    amt
    -0.14
    ần
    -0.14
     subjects
    -0.14
     letter
    -0.13
    ondo
    -0.13
    POSITIVE LOGITS
    uden
    0.19
    zza
    0.17
    ÑĨин
    0.17
    ytt
    0.15
     اÙĦØ°Ùĩ
    0.15
    oug
    0.15
    łģ
    0.15
    iyim
    0.15
     Coupe
    0.14
    اÛĮاÙĨ
    0.14
    Act Density 0.036%

    No Known Activations