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

    Neuronpedia

    INDEX
    Explanations

    terms related to residents and residency status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    дав
    -0.17
    resse
    -0.16
    anic
    -0.15
    Ù
    -0.15
    eron
    -0.15
    urer
    -0.15
    zes
    -0.15
    ument
    -0.14
    ži
    -0.14
    pra
    -0.14
    POSITIVE LOGITS
    ials
    0.19
    .Generated
    0.16
    evil
    0.15
    unan
    0.15
    ibo
    0.15
    hip
    0.15
    alty
    0.15
    íĦ¸
    0.15
    ãģ¡ãģ¯
    0.15
    ally
    0.15
    Act Density 0.023%

    No Known Activations