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

    Neuronpedia

    INDEX
    Explanations

    references to legal theories and their discussion in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.82
    ValueStyle
    -0.80
    ſelben
    -0.75
    DockStyle
    -0.72
    ConstraintMaker
    -0.70
    <unused3>
    -0.70
    -0.70
    <unused43>
    -0.70
    <unused16>
    -0.70
    [@BOS@]
    -0.70
    POSITIVE LOGITS
     clients
    0.56
     Theory
    0.51
     theory
    0.50
    Theory
    0.49
     teoría
    0.41
     теории
    0.40
    Clientes
    0.39
     darbu
    0.39
    ClientId
    0.38
     dė
    0.38
    Act Density 0.295%

    No Known Activations