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

    Neuronpedia

    INDEX
    Explanations

    mentions of violent incidents such as shootings and attacks

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     effe
    -1.03
     wien
    -1.00
     ?...
    -0.96
     strick
    -0.95
     !...
    -0.94
     reluct
    -0.93
     affor
    -0.90
     suscep
    -0.90
     erad
    -0.89
     vhs
    -0.88
    POSITIVE LOGITS
     month
    0.62
     week
    0.61
     consecu
    0.57
     consecutive
    0.57
     within
    0.55
    month
    0.55
    Kelebihan
    0.54
    película
    0.53
    Imágenes
    0.52
     doña
    0.51
    Act Density 0.299%

    No Known Activations