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

    Neuronpedia

    INDEX
    Explanations

    references to national or ethnic identities related to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oku
    -0.17
    anela
    -0.15
    £¼
    -0.15
    vinc
    -0.14
    358
    -0.14
    ialect
    -0.14
    elin
    -0.14
     utrecht
    -0.14
    ocs
    -0.14
    amera
    -0.14
    POSITIVE LOGITS
     alive
    0.15
    æ¶
    0.14
    yasal
    0.14
    NotAllowed
    0.14
    //===
    0.14
    æĻ¯
    0.14
    VERR
    0.14
     Lump
    0.14
     blindness
    0.14
     th
    0.13
    Act Density 0.024%

    No Known Activations