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

    Neuronpedia

    INDEX
    Explanations

    expressions of political criticism or accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingly
    -0.15
    ÑģÑĤвоÑĢ
    -0.15
    inet
    -0.14
     Ukra
    -0.14
    ụ
    -0.14
    loon
    -0.14
    reek
    -0.14
    wire
    -0.14
     ÑĤка
    -0.14
    uario
    -0.13
    POSITIVE LOGITS
     clo
    0.15
     Miz
    0.15
    IZ
    0.14
     closet
    0.14
    olumn
    0.14
     ch
    0.14
    OLT
    0.14
    æĶ
    0.14
     camel
    0.14
    jem
    0.14
    Act Density 0.095%

    No Known Activations