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

    Neuronpedia

    INDEX
    Explanations

    terms related to diversity, such as different races, sexual orientations, religions, and nationalities

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to identity and diversity characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.81
    omorphic
    -0.65
     guiActiveUn
    -0.64
    ĵĺ
    -0.62
    chwitz
    -0.62
     proble
    -0.60
     glim
    -0.59
    heast
    -0.58
     mathemat
    -0.58
    iple
    -0.57
    POSITIVE LOGITS
     etc
    1.03
     huh
    0.71
     Jr
    0.69
     preferably
    0.65
     aka
    0.64
     alas
    0.64
     although
    0.62
    etc
    0.61
     albeit
    0.61
     respectively
    0.60
    Act Density 1.119%

    No Known Activations