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

    Neuronpedia

    INDEX
    Explanations

    mentions of pop culture references

    oai_token-act-pair · gpt-3.5-turbo

    references to films or performances that are notable or evoke strong reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izons
    -0.87
     organisations
    -0.72
    foundation
    -0.70
    independent
    -0.68
    ources
    -0.68
     brokers
    -0.67
     salaries
    -0.67
     fiat
    -0.66
     membership
    -0.66
     Ports
    -0.66
    POSITIVE LOGITS
     parody
    1.24
     spoof
    1.20
     featuring
    1.18
     depicting
    1.09
     reminiscent
    1.09
     titled
    1.09
     hilarious
    1.07
     humorous
    1.07
     sung
    1.07
     clip
    1.02
    Act Density 0.779%

    No Known Activations