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

    Neuronpedia

    INDEX
    Explanations

    references to the largest entities in various categories

    oai_token-act-pair · gpt-3.5-turbo

    references to entities or subjects that hold the title of "largest" in their respective categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jad
    -0.82
    chy
    -0.77
    bara
    -0.74
    bel
    -0.73
    fen
    -0.73
    earth
    -0.72
    onto
    -0.72
    work
    -0.72
    yang
    -0.71
    onso
    -0.70
    POSITIVE LOGITS
    gest
    0.96
     (>
    0.89
     scale
    0.87
     intestine
    0.86
     shareholder
    0.83
     creditor
    0.79
     swath
    0.78
     quantities
    0.76
     earners
    0.74
    achusetts
    0.74
    Act Density 0.027%

    No Known Activations