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

    Neuronpedia

    INDEX
    Explanations

    phrases related to online sharing or publication

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating inclusion or references to external sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tis
    -0.90
    ecast
    -0.84
    meric
    -0.80
    chool
    -0.78
    uel
    -0.75
    riger
    -0.74
     Flavoring
    -0.70
    ertain
    -0.70
    esters
    -0.70
    dom
    -0.69
    POSITIVE LOGITS
     references
    1.24
     quotes
    1.22
     phrases
    1.17
     descriptions
    1.13
     excerpts
    1.13
     slogans
    1.10
     statements
    1.09
     wording
    1.08
     disclaimer
    1.07
     disclaim
    1.07
    Act Density 0.375%

    No Known Activations