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

    Neuronpedia

    INDEX
    Explanations

    mentions of pairs of people or entities

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" frequently appearing in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :[
    -0.76
    natureconservancy
    -0.76
    :(
    -0.73
    Deal
    -0.71
    bub
    -0.70
    >[
    -0.69
    Versions
    -0.69
    æĥ
    -0.66
    bo
    -0.65
    .*
    -0.63
    POSITIVE LOGITS
     therefore
    1.01
     then
    0.94
     vice
    0.92
     thus
    0.90
     thence
    0.90
     consequently
    0.87
    rogen
    0.84
    rogens
    0.83
     hence
    0.82
    chard
    0.81
    Act Density 0.977%

    No Known Activations