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

    Neuronpedia

    INDEX
    Explanations

    words related to health and safety concerns

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social and health disparities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įåĸļ士
    -0.56
    upon
    -0.51
    ihil
    -0.49
     understatement
    -0.49
     Advocate
    -0.48
     Canaver
    -0.48
    ommel
    -0.46
    æĸ¹
    -0.45
     Solitaire
    -0.44
    Beg
    -0.44
    POSITIVE LOGITS
     or
    0.96
     and
    0.80
    /
    0.70
     &
    0.68
     etc
    0.66
    ModLoader
    0.65
    /
    0.60
     livest
    0.54
    ................................................................
    0.52
    ®,
    0.51
    Act Density 1.029%

    No Known Activations