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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criminal activity and law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    references to criminals and criminal activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zl
    -0.66
    orse
    -0.65
    bid
    -0.64
    ww
    -0.63
    chron
    -0.61
    intend
    -0.61
    /+
    -0.61
    ories
    -0.60
    ctive
    -0.59
    Wo
    -0.59
    POSITIVE LOGITS
     criminals
    1.03
     offenders
    0.96
     gangs
    0.89
     prey
    0.88
     offend
    0.88
     mastermind
    0.87
     trespass
    0.85
     infring
    0.84
     offender
    0.80
     smugglers
    0.78
    Act Density 0.012%

    No Known Activations