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

    Neuronpedia

    INDEX
    Explanations

    terms related to criminal investigations and police work

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascript
    -0.86
    ternity
    -0.85
    iness
    -0.83
    ruary
    -0.82
    weed
    -0.81
    nery
    -0.81
    atron
    -0.80
    hooting
    -0.80
    mas
    -0.78
    chery
    -0.78
    POSITIVE LOGITS
     agents
    0.86
     Factors
    0.78
     agent
    0.78
     professions
    0.76
     Governors
    0.74
     Countries
    0.73
     bidder
    0.73
     sectors
    0.73
     entities
    0.72
    iaries
    0.70
    Act Density 0.190%

    No Known Activations