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

    Neuronpedia

    INDEX
    Explanations

    occurrences of physical violence and assault

    oai_token-act-pair · gpt-3.5-turbo

    instances of violence or physical harm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Labor
    -0.71
     ethic
    -0.64
    istries
    -0.64
    FK
    -0.63
    alities
    -0.63
    hang
    -0.62
    lore
    -0.61
    ARE
    -0.60
    Us
    -0.59
     formation
    -0.59
    POSITIVE LOGITS
    ĸļ
    0.94
     aback
    0.91
     by
    0.80
     hostage
    0.79
     merciless
    0.78
     unintention
    0.71
    quished
    0.71
     Sapphire
    0.70
    ô
    0.70
     unfairly
    0.69
    Act Density 0.208%

    No Known Activations