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

    Neuronpedia

    INDEX
    Explanations

    mentions of violence, casualties, and loss of life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.61
    pausal
    -0.55
    XtraGrid
    -0.54
     phases
    -0.52
    ="<?
    -0.51
    PRWEB
    -0.51
    Reactivity
    -0.49
    HasIndex
    -0.49
     phase
    -0.48
    ="<?=
    -0.48
    POSITIVE LOGITS
     deaths
    0.99
     death
    0.87
     fatalities
    0.81
     Deaths
    0.81
     casualties
    0.79
     killings
    0.77
    death
    0.75
     morti
    0.74
     murders
    0.72
     DEATH
    0.72
    Act Density 0.249%

    No Known Activations