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

    Neuronpedia

    INDEX
    Explanations

    concepts related to blame and accountability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    оÑģÑĮ
    -0.16
    ÑģÑĮ
    -0.16
    ummer
    -0.15
    ocene
    -0.14
    renom
    -0.14
    pee
    -0.14
    ums
    -0.14
    berger
    -0.14
    еÑĢÑĤи
    -0.14
    Ñİ
    -0.13
    POSITIVE LOGITS
    uvw
    0.17
    uv
    0.16
    enna
    0.15
    aks
    0.14
    ár
    0.14
    osp
    0.14
    Ïģθ
    0.13
    akin
    0.13
    δη
    0.13
     GANG
    0.13
    Act Density 0.068%

    No Known Activations