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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negative issues or problems

    oai_token-act-pair · gpt-3.5-turbo

    references to negative conditions or issues affecting society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ials
    -0.80
    dp
    -0.78
    ettel
    -0.77
    ibling
    -0.77
    earchers
    -0.76
    initions
    -0.76
    Streamer
    -0.75
    ynthesis
    -0.74
    edar
    -0.74
    ndra
    -0.71
    POSITIVE LOGITS
     plague
    1.42
     plag
    0.93
     Plague
    0.93
     scourge
    0.87
     blight
    0.84
     infect
    0.79
    bugs
    0.78
    bug
    0.77
     swarm
    0.76
     Nost
    0.75
    Act Density 0.011%

    No Known Activations