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

    Neuronpedia

    INDEX
    Explanations

    verbs related to construction or creation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "build" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kov
    -0.70
    nery
    -0.69
    present
    -0.67
    dos
    -0.67
    zee
    -0.66
    Ĥİ
    -0.65
    ????????
    -0.65
    my
    -0.63
    mia
    -0.63
    tm
    -0.62
    POSITIVE LOGITS
     bridges
    1.17
     Bridges
    1.09
     rapport
    0.95
     relationships
    0.89
     friendships
    0.85
     prototypes
    0.84
     trust
    0.83
     dams
    0.82
     alliances
    0.81
     momentum
    0.80
    Act Density 0.056%

    No Known Activations