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

    Neuronpedia

    INDEX
    Explanations

    mentions of violent events or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    references to human rights violations and related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NX
    -0.62
    10000
    -0.61
     Proper
    -0.61
     ENT
    -0.61
    ////////////////
    -0.59
     Omn
    -0.58
    omorph
    -0.58
    200000
    -0.58
     Folder
    -0.57
     stere
    -0.56
    POSITIVE LOGITS
     crackdown
    0.93
     blamed
    0.90
     intensified
    0.86
     militants
    0.84
     accuse
    0.83
     strained
    0.82
     fears
    0.82
     sparking
    0.81
     deepening
    0.81
     worsening
    0.81
    Act Density 1.041%

    No Known Activations