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

    Neuronpedia

    INDEX
    Explanations

    legal and criminal-related terms and scenarios

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     cues
    -0.71
     moderates
    -0.70
    esh
    -0.69
    wagon
    -0.69
     outputs
    -0.68
     pins
    -0.68
     pier
    -0.67
     taught
    -0.66
     selves
    -0.66
     filters
    -0.66
    POSITIVE LOGITS
     court
    1.21
     favor
    1.21
    jury
    1.17
     lieu
    1.08
     favour
    1.07
     case
    1.02
    charge
    1.01
     cases
    1.00
     conjunction
    0.99
     vitro
    0.98
    Act Density 0.145%

    No Known Activations