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

    Neuronpedia

    INDEX
    Explanations

    terms related to significant events, important figures, and controversial topics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to controversy and popularity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orthy
    -0.87
    osponsors
    -0.86
    thia
    -0.83
    utics
    -0.79
    redits
    -0.78
    terness
    -0.74
    illance
    -0.74
    yers
    -0.74
    atu
    -0.72
    AAAA
    -0.72
    POSITIVE LOGITS
     acronym
    0.77
     anti
    0.75
     annual
    0.74
     Southern
    0.74
     industrial
    0.73
     trio
    0.73
     interior
    0.72
     arena
    0.71
     duo
    0.71
     underground
    0.70
    Act Density 0.268%

    No Known Activations