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

    Neuronpedia

    INDEX
    Explanations

    terms related to anti-something products or concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to anti-technology or anti-product positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     marches
    -0.75
    nces
    -0.74
     Klux
    -0.73
     precincts
    -0.70
    aturdays
    -0.69
     embraces
    -0.69
     interviews
    -0.69
     democratically
    -0.68
    aturday
    -0.67
     Reich
    -0.67
    POSITIVE LOGITS
    inflammatory
    0.97
    absor
    0.94
    hazard
    0.93
    gravity
    0.93
    cheat
    0.92
    avoid
    0.92
    orb
    0.91
    vir
    0.87
    destruct
    0.87
    oxide
    0.87
    Act Density 0.063%

    No Known Activations