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

    Neuronpedia

    INDEX
    Explanations

    information related to criminal incidents

    oai_token-act-pair · gpt-3.5-turbo

    mentions of victims in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leaf
    -0.69
    aeda
    -0.69
    OPLE
    -0.69
    andel
    -0.66
     authoritarian
    -0.65
     taxing
    -0.64
    CLASSIFIED
    -0.64
     monarchy
    -0.64
    ATIONAL
    -0.64
    ooks
    -0.63
    POSITIVE LOGITS
    vict
    0.89
     victim
    0.84
    istics
    0.80
     Victim
    0.80
     victims
    0.79
     inflicted
    0.77
     Victims
    0.77
    Vict
    0.77
    izer
    0.77
    izers
    0.76
    Act Density 0.023%

    No Known Activations