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

    Neuronpedia

    INDEX
    Explanations

    news headlines with political references

    oai_token-act-pair · gpt-3.5-turbo

    hyphenated phrases or elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    halla
    -0.81
     locality
    -0.77
     tremend
    -0.77
    ioch
    -0.72
     tradem
    -0.71
     volunte
    -0.70
     carbohyd
    -0.70
    oit
    -0.69
    itiz
    -0.69
    emort
    -0.68
    POSITIVE LOGITS
     Thousands
    1.33
     Hundreds
    1.29
     Dozens
    1.25
     Nearly
    1.24
     Former
    1.17
     Scientists
    1.17
     Protesters
    1.14
     Tens
    1.14
     Newly
    1.13
     Several
    1.12
    Act Density 0.046%

    No Known Activations