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

    Neuronpedia

    INDEX
    Explanations

    concepts related to legal responsibility and liability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dán
    -0.15
     Susp
    -0.15
    moz
    -0.15
    Susp
    -0.15
    ÑĩиÑħ
    -0.14
    earned
    -0.14
    atica
    -0.14
    emouth
    -0.14
    erty
    -0.14
    iesel
    -0.14
    POSITIVE LOGITS
     liability
    0.28
     liable
    0.25
     responsibility
    0.25
     Liability
    0.24
     liabilities
    0.23
    -li
    0.23
     absorb
    0.21
    责任
    0.21
     LIABILITY
    0.21
     respons
    0.20
    Act Density 0.158%

    No Known Activations