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

    Neuronpedia

    INDEX
    Explanations

    words related to social or institutional critique and the impact of societal structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    XObject
    -0.15
    nze
    -0.14
    atas
    -0.14
    954
    -0.14
     practition
    -0.14
    ansom
    -0.13
    osen
    -0.13
    .synthetic
    -0.13
    783
    -0.13
    ACHER
    -0.13
    POSITIVE LOGITS
    enheim
    0.17
    aginator
    0.16
    imus
    0.16
     Uns
    0.15
    ãĥ§
    0.14
    stood
    0.14
     gu
    0.14
     Nations
    0.14
     cy
    0.13
     Cousins
    0.13
    Act Density 0.011%

    No Known Activations