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

    Neuronpedia

    INDEX
    Explanations

    references to geopolitical entities and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \Migrations
    -0.18
    ÑģеÑĢ
    -0.16
    اض
    -0.15
    iaux
    -0.15
    Gram
    -0.14
     gram
    -0.14
    unar
    -0.14
    ForSegue
    -0.14
    èīĩ
    -0.13
    iliz
    -0.13
    POSITIVE LOGITS
    eteria
    0.16
     Kral
    0.15
     denen
    0.15
    ibt
    0.15
    ami
    0.14
    ekim
    0.14
    кÑĥ
    0.14
    225
    0.13
    åı¯
    0.13
    atra
    0.13
    Act Density 0.039%

    No Known Activations