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

    Neuronpedia

    INDEX
    Explanations

    references to suffering and related topics

    oai_token-act-pair · gpt-3.5-turbo

    references to suffering and its impacts on individuals and society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sure
    -0.65
    eton
    -0.64
    sports
    -0.62
     Mafia
    -0.60
     Shots
    -0.60
     Collider
    -0.59
     lev
    -0.59
    clear
    -0.59
    uren
    -0.59
    smoking
    -0.58
    POSITIVE LOGITS
     inflicted
    0.91
    lehem
    0.80
     Palest
    0.79
    ansson
    0.77
    lessly
    0.76
     endured
    0.74
     Nadu
    0.74
    hani
    0.73
     suffered
    0.73
     horribly
    0.72
    Act Density 0.021%

    No Known Activations