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

    Neuronpedia

    INDEX
    Explanations

    fragments related to informal written communication

    oai_token-act-pair · gpt-3.5-turbo

    elements related to official communications or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shortages
    -0.78
     Flavoring
    -0.75
    ievers
    -0.69
    effic
    -0.69
     frontier
    -0.68
     diseases
    -0.66
     laboratories
    -0.64
     strugg
    -0.63
     battled
    -0.63
     mutants
    -0.63
    POSITIVE LOGITS
     excerpts
    1.10
     reprinted
    1.07
     excerpt
    1.03
     circulated
    1.02
     published
    0.99
    itled
    0.98
     summar
    0.98
     ital
    0.93
     titled
    0.91
     retweet
    0.89
    Act Density 0.630%

    No Known Activations