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

    Neuronpedia

    INDEX
    Explanations

    words or phrases in a specific language, likely related to a cultural or regional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.90
    เหร
    -0.86
    contentLoaded
    -0.83
     старости
    -0.78
    ViewFeatures
    -0.76
    таратура
    -0.74
    awtextra
    -0.73
    Autoritní
    -0.73
    gameserver
    -0.72
     Paglinawan
    -0.70
    POSITIVE LOGITS
    󠁢
    0.56
    ณ์
    0.56
    ก
    0.55
     enää
    0.54
    songwriter
    0.53
    sproz
    0.51
    OrNil
    0.51
     aikaa
    0.50
    ษ
    0.48
    heartedly
    0.48
    Act Density 0.008%

    No Known Activations