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

    Neuronpedia

    INDEX
    Explanations

    keywords related to criminal investigations or police work

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of investigators in a context related to inquiry or investigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.79
    ãĤª
    -0.65
    church
    -0.65
    noxious
    -0.65
    yards
    -0.64
    Prev
    -0.63
     Pradesh
    -0.63
    birth
    -0.63
    lord
    -0.62
    np
    -0.62
    POSITIVE LOGITS
     probing
    0.94
     investigator
    0.92
     investigating
    0.91
     subpoen
    0.88
     uncovered
    0.80
     confir
    0.78
     conclud
    0.78
     tampering
    0.75
     investigation
    0.75
     investigates
    0.74
    Act Density 0.023%

    No Known Activations