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

    Neuronpedia

    INDEX
    Explanations

    references to community events or gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gentle
    -0.20
     gent
    -0.17
    gent
    -0.16
    ór
    -0.15
     exit
    -0.14
    vig
    -0.14
    nger
    -0.14
     return
    -0.14
    uplic
    -0.14
     stopping
    -0.14
    POSITIVE LOGITS
     settle
    0.18
     immediately
    0.18
    initial
    0.17
    sett
    0.17
     settling
    0.17
    ãģĻãģIJ
    0.17
    >Welcome
    0.16
     settled
    0.16
     settles
    0.16
     initial
    0.16
    Act Density 0.161%

    No Known Activations