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

    Neuronpedia

    INDEX
    Explanations

    references to geographical regions and financial terms

    oai_token-act-pair · gpt-3.5-turbo

    references to regions, particularly those related to international trade and policy issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azeera
    -0.66
    houn
    -0.65
    beit
    -0.63
    ITED
    -0.62
     swear
    -0.60
     %%
    -0.59
    lessly
    -0.59
     Breach
    -0.58
    idential
    -0.58
    blance
    -0.58
    POSITIVE LOGITS
    Sax
    0.75
    Yang
    0.71
    terness
    0.62
     Romans
    0.60
    yang
    0.60
     tantal
    0.59
     princess
    0.59
    Egypt
    0.58
    dam
    0.57
    cellent
    0.57
    Act Density 0.362%

    No Known Activations