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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various forms of violent crimes and injustices, especially those involving sexual abuse, assault, and murder

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the abuse and exploitation of vulnerable groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lopp
    -0.62
    uncture
    -0.62
    MODE
    -0.59
    bernatorial
    -0.58
    endish
    -0.57
    Spl
    -0.56
    eme
    -0.56
    atility
    -0.56
     charm
    -0.55
    isdom
    -0.55
    POSITIVE LOGITS
     residing
    1.00
    folk
    0.99
     abroad
    0.98
     alike
    0.94
     enshr
    0.93
     perpetrated
    0.90
     fleeing
    0.84
     victimized
    0.82
     detained
    0.82
     occurring
    0.82
    Act Density 0.258%

    No Known Activations