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

    Neuronpedia

    INDEX
    Explanations

    references to premises liability and legal claims related to injury

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elsen
    -0.17
    clared
    -0.15
    regunta
    -0.15
    reffen
    -0.14
    loquent
    -0.14
    GST
    -0.14
    .unregister
    -0.14
    tridge
    -0.14
    ihu
    -0.14
    arden
    -0.14
    POSITIVE LOGITS
     settlements
    0.28
     settlement
    0.27
     premises
    0.26
     personal
    0.25
     slip
    0.24
     Settlement
    0.24
     Wrong
    0.23
     Personal
    0.23
     WRONG
    0.23
    wrong
    0.23
    Act Density 0.112%

    No Known Activations