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

    Neuronpedia

    INDEX
    Explanations

    sentences related to personal beliefs or values

    oai_token-act-pair · gpt-3.5-turbo

    frequent references to "life" and its various conditions and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wi
    -0.65
     Hayden
    -0.63
     Preston
    -0.62
    yip
    -0.58
    arat
    -0.58
    azines
    -0.58
     repeatedly
    -0.57
    hops
    -0.56
     shops
    -0.55
     fielded
    -0.54
    POSITIVE LOGITS
    edly
    0.93
    enment
    0.81
    same
    0.77
    ATION
    0.75
    itarian
    0.75
    edIn
    0.74
     brunt
    0.73
    ATIONS
    0.73
    iously
    0.73
    ité
    0.73
    Act Density 0.375%

    No Known Activations