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

    Neuronpedia

    INDEX
    Explanations

    expressions of blame and accountability regarding societal or systemic issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istrovstvÃŃ
    -0.15
     konkrét
    -0.15
     Wet
    -0.15
    ìĹ´
    -0.14
     sö
    -0.14
     rek
    -0.14
    /screen
    -0.14
    hots
    -0.14
    PRESSION
    -0.14
     imp
    -0.13
    POSITIVE LOGITS
    ernal
    0.17
    rale
    0.17
     Bark
    0.16
    erner
    0.14
     dane
    0.14
     Kidd
    0.14
    .crm
    0.14
    ulis
    0.14
    ument
    0.14
    isses
    0.14
    Act Density 1.079%

    No Known Activations