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

    Neuronpedia

    INDEX
    Explanations

    references to individuals described as outsiders

    oai_token-act-pair · gpt-3.5-turbo

    references to outsiders and their perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Stock
    -0.80
    rol
    -0.75
    rams
    -0.73
     Parenthood
    -0.67
    Dep
    -0.67
    bal
    -0.66
    onder
    -0.65
    raz
    -0.65
    eline
    -0.64
    ãĥª
    -0.63
    POSITIVE LOGITS
     outsider
    1.34
     outsiders
    1.09
     Outs
    0.93
     onlook
    0.78
     insiders
    0.75
     newcomer
    0.74
     "$:/
    0.73
    ixir
    0.72
    atform
    0.70
    worldly
    0.70
    Act Density 0.009%

    No Known Activations