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

    Neuronpedia

    INDEX
    Explanations

    assertions about risks and inequalities affecting marginalized groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umpt
    -0.18
    atto
    -0.17
    anie
    -0.16
    dy
    -0.16
    orce
    -0.15
    sett
    -0.15
    .DependencyInjection
    -0.14
     Salv
    -0.14
    ÏģηÏĥη
    -0.14
    pite
    -0.14
    POSITIVE LOGITS
    eron
    0.20
    erd
    0.15
    abis
    0.15
    eri
    0.15
     suddenly
    0.15
    enes
    0.14
    erus
    0.14
    Ñĩини
    0.14
     Nuggets
    0.14
    Äįin
    0.13
    Act Density 0.320%

    No Known Activations