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

    Neuronpedia

    INDEX
    Explanations

    referential phrases or articles that signify people, particularly in legal or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adiens
    -0.17
    oment
    -0.17
    ãĥ¼ãĥį
    -0.17
    arring
    -0.15
    éd
    -0.15
    ÑģÑĤан
    -0.14
    ologne
    -0.14
    ouse
    -0.14
    wend
    -0.14
    iye
    -0.14
    POSITIVE LOGITS
    ikh
    0.16
    änn
    0.16
    quet
    0.15
    loff
    0.15
    çļ
    0.14
    fer
    0.14
    ardy
    0.14
     Dh
    0.14
    addock
    0.14
    eut
    0.13
    Act Density 0.069%

    No Known Activations