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

    Neuronpedia

    INDEX
    Explanations

    instances of violent actions or incidents

    oai_token-act-pair · gpt-3.5-turbo

    instances of violent actions performed by individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     largeDownload
    -0.84
    Specific
    -0.84
    BSD
    -0.76
    ertain
    -0.76
    SPONSORED
    -0.74
    ahead
    -0.69
     ende
    -0.68
    hesion
    -0.68
    ettle
    -0.68
    determination
    -0.68
    POSITIVE LOGITS
     virtue
    0.98
    products
    0.82
     multiplying
    0.79
     afar
    0.78
     passers
    0.78
     bandits
    0.76
     mobs
    0.76
     gunfire
    0.76
     outsiders
    0.70
     someone
    0.70
    Act Density 0.135%

    No Known Activations