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

    Neuronpedia

    INDEX
    Explanations

    mentions of the Holocaust and related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _mx
    -0.17
    éĨ
    -0.17
    ekk
    -0.16
    erville
    -0.15
     knull
    -0.15
    lector
    -0.15
    mán
    -0.14
    omain
    -0.14
    çģ£
    -0.14
    kili
    -0.14
    POSITIVE LOGITS
     Holocaust
    0.47
     Auschwitz
    0.40
     hol
    0.37
     Yad
    0.36
     Sho
    0.35
    Hol
    0.35
     Jewish
    0.34
     survivor
    0.32
     Jews
    0.31
    ocaust
    0.29
    Act Density 0.095%

    No Known Activations