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
    qli
    -0.15
    .mvp
    -0.15
    pty
    -0.14
    âng
    -0.14
    oland
    -0.14
    Äĥr
    -0.14
    辺
    -0.14
    ovna
    -0.14
    ropsych
    -0.14
    spender
    -0.13
    POSITIVE LOGITS
    baugh
    0.18
    kowski
    0.16
    iskey
    0.15
     Fu
    0.14
    owski
    0.14
    wine
    0.14
    alla
    0.14
    rud
    0.13
    ise
    0.13
    wor
    0.13
    Act Density 0.310%

    No Known Activations