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

    Neuronpedia

    INDEX
    Explanations

    nouns related to digital and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oldt
    -0.19
     اÙĦرÙħزÙĬØ©
    -0.19
    Ùĭ
    -0.19
    ÅĽmy
    -0.18
    'nın
    -0.18
    ein
    -0.17
    ÑģÑıÑĤ
    -0.17
    ÙĭØĮ
    -0.17
    ught
    -0.16
    hoo
    -0.16
    POSITIVE LOGITS
    ny
    0.33
    ом
    0.32
    Ñĭ
    0.32
    ÑĬ
    0.30
    nya
    0.29
    ов
    0.28
    овÑĭй
    0.26
    ian
    0.25
    om
    0.25
    Ñĩик
    0.25
    Act Density 0.074%

    No Known Activations