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

    Neuronpedia

    INDEX
    Explanations

    negations and phrases that indicate absence or lack

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aron
    -0.17
    ãģĹãģŁ
    -0.16
    ãģĹãģ¾ãģ£ãģŁ
    -0.15
    ãģ«ãģªãģ£ãģŁ
    -0.15
     ÑģделаÑĤÑĮ
    -0.15
    λÏī
    -0.15
    amber
    -0.14
    Ñĸли
    -0.14
    \↵
    -0.14
    ãĤĮãģŁ
    -0.14
    POSITIVE LOGITS
    DBC
    0.17
    одÑĥ
    0.16
     à¤ķरत
    0.15
    558
    0.15
    azy
    0.15
    dle
    0.14
    ulu
    0.14
    ÑĭваÑĤÑĮ
    0.14
    LEX
    0.14
    abant
    0.14
    Act Density 0.087%

    No Known Activations