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

    Neuronpedia

    INDEX
    Explanations

    references to society or social terms

    oai_token-act-pair · gpt-3.5-turbo

    references to social structures or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fluorescent
    -0.72
     knocking
    -0.67
     stump
    -0.65
     ultrasound
    -0.62
     vomit
    -0.62
     recall
    -0.62
     blast
    -0.60
     lamb
    -0.60
    ++++
    -0.60
     invasive
    -0.60
    POSITIVE LOGITS
    ieties
    1.53
    iety
    1.52
    ietal
    1.48
    keye
    1.29
    cer
    1.24
    iet
    1.19
    ionics
    1.05
    ivil
    0.97
    io
    0.92
    ethe
    0.90
    Act Density 0.027%

    No Known Activations