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

    Neuronpedia

    INDEX
    Explanations

    terms related to specific names or places

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific location or entity named "Hind."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynthesis
    -0.77
    è¦ļéĨĴ
    -0.77
    ãĥ¯
    -0.76
    76561
    -0.73
    ailability
    -0.70
    osponsors
    -0.70
    oker
    -0.68
    ãĤ£
    -0.67
    ylum
    -0.66
    isable
    -0.65
    POSITIVE LOGITS
    sight
    1.22
    ering
    1.00
    shire
    0.91
    rance
    0.88
    quarters
    0.87
    erella
    0.86
     Hind
    0.82
    nesses
    0.80
    say
    0.78
    ered
    0.75
    Act Density 0.036%

    No Known Activations