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

    Neuronpedia

    INDEX
    Explanations

    references to job promotions and professional roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .mj
    -0.17
    ictim
    -0.15
    anter
    -0.14
    :flex
    -0.14
    .translation
    -0.14
    è¹
    -0.13
    Ïģι
    -0.13
    ÑĨвеÑĤ
    -0.13
    è½½
    -0.13
    nob
    -0.13
    POSITIVE LOGITS
    pto
    0.17
    quist
    0.16
    ppers
    0.15
    addock
    0.15
     Phy
    0.15
     Tam
    0.15
    ppard
    0.14
    leys
    0.14
    phony
    0.14
    Leaders
    0.14
    Act Density 0.069%

    No Known Activations