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

    Neuronpedia

    INDEX
    Explanations

    references to legal proceedings and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     debuted
    -0.71
     pioneered
    -0.67
     effortlessly
    -0.66
     tended
    -0.66
     embodied
    -0.63
     famously
    -0.63
     premiered
    -0.63
     Originally
    -0.62
     experimented
    -0.62
     Unle
    -0.61
    POSITIVE LOGITS
     forensic
    0.96
    Charges
    0.88
     negligence
    0.87
     Forensic
    0.85
    Investigators
    0.85
     extradition
    0.84
    Detect
    0.84
     perjury
    0.84
     prosecutors
    0.84
     prosecution
    0.81
    Act Density 0.635%

    No Known Activations