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

    Neuronpedia

    INDEX
    Explanations

    web links and URLs

    oai_token-act-pair · gpt-3.5-turbo

    URLs and other digital content references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inev
    -0.79
     corruption
    -0.79
     dehydration
    -0.76
     diseng
    -0.75
     charm
    -0.74
     hindsight
    -0.73
     redress
    -0.72
     regeneration
    -0.72
     inexpl
    -0.72
     cruise
    -0.72
    POSITIVE LOGITS
    sbm
    0.95
    https
    0.95
    ONSORED
    0.95
    ï¸ı
    0.93
    ¯¯
    0.92
    é¾įåĸļ士
    0.91
    姫
    0.91
    forums
    0.90
    Contribut
    0.90
    Market
    0.89
    Act Density 0.157%

    No Known Activations