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

    Neuronpedia

    INDEX
    Explanations

    references to the word "Lemon" and its variations

    oai_token-act-pair · gpt-3.5-turbo

    specific names or references, particularly those associated with a particular individual or character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨ
    -0.84
    ãģ¦
    -0.72
    ================================================================
    -0.65
     à¨
    -0.64
    CLASSIFIED
    -0.64
    ÙIJ
    -0.63
    Christ
    -0.63
    ãĥ¼ãĥĨãĤ£
    -0.62
     Sakura
    -0.62
     Tant
    -0.62
    POSITIVE LOGITS
    ike
    1.01
    ongo
    0.96
    enko
    0.95
    rade
    0.94
    isine
    0.94
    iris
    0.91
    roots
    0.90
    eny
    0.89
    uz
    0.87
    rov
    0.87
    Act Density 0.027%

    No Known Activations