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

    Neuronpedia

    INDEX
    Explanations

    words related to criminal history or records

    oai_token-act-pair · gpt-3.5-turbo

    terms related to criminal backgrounds and psychological profiles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     batches
    -0.67
     Sessions
    -0.60
    ulp
    -0.60
    ighth
    -0.58
     glacier
    -0.58
     Byr
    -0.57
    Safety
    -0.56
    INC
    -0.56
     Kell
    -0.55
     Byrne
    -0.55
    POSITIVE LOGITS
     comparable
    0.76
     whatsoever
    0.73
     knack
    0.73
     aspirations
    0.72
    aries
    0.71
    abilities
    0.70
     distinguishing
    0.68
    daq
    0.68
     compared
    0.67
     fetish
    0.66
    Act Density 0.463%

    No Known Activations