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

    Neuronpedia

    INDEX
    Explanations

    references to academic journals and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     minded
    -0.16
     ucfirst
    -0.15
    oundation
    -0.15
     Juliet
    -0.15
     toolbox
    -0.14
    iful
    -0.14
     Giul
    -0.13
     Pill
    -0.13
    ework
    -0.13
    Jets
    -0.13
    POSITIVE LOGITS
    ournals
    0.27
    OURNAL
    0.26
    AMA
    0.25
    oun
    0.23
     Applied
    0.23
     Experimental
    0.22
    ournal
    0.22
     American
    0.20
     Korean
    0.20
     Cleaner
    0.20
    Act Density 0.017%

    No Known Activations