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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal proceedings and entities involved in cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -1.11
     Monfieur
    -0.93
     Jefus
    -0.92
     Majefty
    -0.89
     purpoſe
    -0.88
     myſelf
    -0.87
     Reſ
    -0.86
     Houſe
    -0.85
     fubject
    -0.84
     Perſ
    -0.83
    POSITIVE LOGITS
     really
    0.60
    ’
    0.57
     especially
    0.52
    ,
    0.51
     might
    0.51
     should
    0.50
     wouldn
    0.47
     shouldn
    0.47
     certainly
    0.46
     too
    0.46
    Act Density 0.516%

    No Known Activations