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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to technology, including drones and autonomous vehicles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various types of technology and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mble
    -0.95
    lished
    -0.73
    */(
    -0.72
    quished
    -0.68
    insula
    -0.67
    ieri
    -0.65
    swer
    -0.64
    bsite
    -0.63
    ichita
    -0.63
    itored
    -0.62
    POSITIVE LOGITS
     warfare
    0.83
    Semitism
    0.80
    ism
    0.75
     fatigue
    0.73
     therapies
    0.72
     supremacy
    0.70
     environments
    0.69
     interactions
    0.69
     versus
    0.69
     policing
    0.69
    Act Density 0.691%

    No Known Activations