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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _singleton
    -0.17
    rál
    -0.15
    mah
    -0.15
    à¸Ļะ
    -0.15
    zac
    -0.14
     Sinclair
    -0.14
    olini
    -0.14
    ÑĢÑĥÑĤ
    -0.14
    yum
    -0.14
    ná
    -0.14
    POSITIVE LOGITS
    laus
    0.32
    law
    0.29
    lav
    0.28
    ÅĤaw
    0.28
    isl
    0.28
    лав
    0.25
    islav
    0.23
     law
    0.21
    sl
    0.21
    lava
    0.21
    Act Density 0.029%

    No Known Activations