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

    Neuronpedia

    INDEX
    Explanations

    text related to controversial and important societal issues or topics

    oai_token-act-pair · gpt-3.5-turbo

    key political issues and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DOS
    -0.69
    oufl
    -0.69
    bah
    -0.68
    blast
    -0.67
    trak
    -0.65
    enko
    -0.65
    oxic
    -0.65
    ylene
    -0.65
    antam
    -0.64
    lah
    -0.63
    POSITIVE LOGITS
     imaginable
    1.15
     happening
    0.93
     involving
    0.89
     affecting
    0.88
     relating
    0.84
     occasion
    0.79
     pertaining
    0.78
     occurring
    0.77
     pursuits
    0.77
     arising
    0.77
    Act Density 0.557%

    No Known Activations