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

    Neuronpedia

    INDEX
    Explanations

    references to detention or prisoner camps, particularly related to war and political prisoners

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.45
    entingan
    -0.40
     dynamism
    -0.39
     perlas
    -0.38
     tärke
    -0.36
    praia
    -0.36
     azulejos
    -0.35
     humanidade
    -0.35
     interesado
    -0.35
     accéder
    -0.35
    POSITIVE LOGITS
     Camps
    0.75
     camps
    0.74
     camp
    0.69
    camps
    0.63
    Билгалдахарш
    0.63
     Camp
    0.63
     Detention
    0.60
     Rehab
    0.54
     FetchType
    0.54
    Camp
    0.53
    Act Density 0.539%

    No Known Activations