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

    Neuronpedia

    INDEX
    Explanations

    references to historical events related to concentration camps and the Holocaust

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Damage
    -0.16
    okin
    -0.16
     booth
    -0.15
    _damage
    -0.15
     Hakk
    -0.15
    ollah
    -0.14
    swick
    -0.14
    ẹn
    -0.14
    -League
    -0.14
     damage
    -0.14
    POSITIVE LOGITS
     camps
    0.50
     camp
    0.49
     Camp
    0.39
    camp
    0.32
     concentration
    0.31
    Camp
    0.30
     Concent
    0.27
     Lager
    0.27
     intern
    0.25
     labor
    0.24
    Act Density 0.033%

    No Known Activations