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

    Neuronpedia

    INDEX
    Explanations

    phrases with the word "victims" and high emotional relevance

    oai_token-act-pair · gpt-3.5-turbo

    references to victims of abuse or violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ATIONAL
    -0.80
    leaf
    -0.71
    OVA
    -0.71
     monarchy
    -0.63
     Marqu
    -0.62
    aul
    -0.62
    66666666
    -0.61
    oard
    -0.61
     Plat
    -0.60
    andel
    -0.59
    POSITIVE LOGITS
     victims
    1.32
     Victims
    1.32
     Victim
    1.03
     victim
    0.98
     victimized
    0.97
     survivors
    0.89
     Survivors
    0.88
    vict
    0.87
    sels
    0.86
     perpetrators
    0.80
    Act Density 0.012%

    No Known Activations