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

    Neuronpedia

    INDEX
    Explanations

    terms related to burglaries

    oai_token-act-pair · gpt-3.5-turbo

    terms related to burglary and criminal activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shr
    -0.91
    utical
    -0.86
    LESS
    -0.79
    toggle
    -0.77
    travel
    -0.76
    usha
    -0.75
    hair
    -0.75
    acebook
    -0.74
    generic
    -0.74
    apa
    -0.71
    POSITIVE LOGITS
     burgl
    1.31
     burg
    1.21
     burglary
    1.21
     spree
    0.92
     alarms
    0.86
     robbery
    0.82
     alarm
    0.80
     homicide
    0.76
     suspects
    0.75
     stalk
    0.74
    Act Density 0.011%

    No Known Activations