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

    Neuronpedia

    INDEX
    Explanations

    terms associated with economic and social impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    надлеж
    -0.15
     Decompiled
    -0.14
    ness
    -0.14
    à¸ķรว
    -0.14
    lesia
    -0.14
    волÑı
    -0.14
    (strtolower
    -0.13
    .Butter
    -0.13
    ESSAGE
    -0.13
    unifu
    -0.13
    POSITIVE LOGITS
    ulp
    0.15
    ż
    0.14
     Hopkins
    0.13
    him
    0.13
     versions
    0.13
    abled
    0.13
    auer
    0.13
    ecal
    0.13
     local
    0.13
    otal
    0.13
    Act Density 0.180%

    No Known Activations