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

    Neuronpedia

    INDEX
    Explanations

    legal terms and court-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to legal terms and courts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plet
    -0.76
     newcom
    -0.72
     advoc
    -0.68
     tremend
    -0.68
     awa
    -0.68
     Citiz
    -0.67
     arrang
    -0.66
    arella
    -0.66
     BUS
    -0.65
    vana
    -0.64
    POSITIVE LOGITS
    ulhu
    0.67
    lain
    0.65
     fame
    0.65
     Commissioners
    0.64
     GHz
    0.63
    Enlarge
    0.62
    gio
    0.61
     Basin
    0.61
     forks
    0.60
     kHz
    0.59
    Act Density 0.158%

    No Known Activations