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

    Neuronpedia

    INDEX
    Explanations

    violent or intense actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to violent incidents and their associated entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ensures
    -0.62
     ensured
    -0.61
     recourse
    -0.60
    monary
    -0.58
     Earn
    -0.57
    utory
    -0.56
    ribes
    -0.55
    athon
    -0.55
     Dietary
    -0.55
     avoids
    -0.55
    POSITIVE LOGITS
     unfold
    1.17
     firsthand
    0.99
     emerge
    0.85
     unfolding
    0.82
     coming
    0.82
     trending
    0.81
     flickering
    0.81
     emanating
    0.81
     looming
    0.80
     crumble
    0.78
    Act Density 0.589%

    No Known Activations