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

    Neuronpedia

    INDEX
    Explanations

    phrases and information related to criminal activities and legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mal
    -0.14
    anou
    -0.14
    antal
    -0.14
    anela
    -0.14
    thew
    -0.13
    ARED
    -0.13
    rrha
    -0.13
    ÏĦί
    -0.13
    thalm
    -0.13
     maybe
    -0.13
    POSITIVE LOGITS
     then
    0.15
    abant
    0.14
    verb
    0.14
    037
    0.14
    cod
    0.14
    vara
    0.14
    lez
    0.13
    egie
    0.13
    eniable
    0.13
     miêu
    0.13
    Act Density 0.093%

    No Known Activations