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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal proceedings and crime

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     bay
    -0.64
    DEN
    -0.62
    REC
    -0.62
     variance
    -0.60
     bud
    -0.59
     href
    -0.59
     blackout
    -0.58
    WD
    -0.58
     Blaz
    -0.58
    EV
    -0.57
    POSITIVE LOGITS
    rane
    1.23
    rome
    1.14
    orus
    1.07
    schild
    1.06
    ocolate
    1.02
    lear
    1.01
    ambers
    0.99
    ocobo
    0.95
    inese
    0.92
    lain
    0.92
    Act Density 0.017%

    No Known Activations