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

    Neuronpedia

    INDEX
    Explanations

    terms related to personal injury and liability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    clared
    -0.15
    .unregister
    -0.15
    reffen
    -0.14
    asje
    -0.14
    ivar
    -0.14
    abeth
    -0.14
    سات
    -0.14
     klin
    -0.14
    cest
    -0.14
    tridge
    -0.14
    POSITIVE LOGITS
     slip
    0.28
     premises
    0.28
     personal
    0.27
     Wrong
    0.25
     Personal
    0.24
     Neg
    0.23
     brain
    0.23
     WRONG
    0.23
     Slip
    0.23
     negligence
    0.23
    Act Density 0.102%

    No Known Activations