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

    Neuronpedia

    INDEX
    Explanations

    specific phrases or structures indicative of qualitative descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istrovstvÃŃ
    -0.07
     ayn
    -0.07
    iesel
    -0.07
     attention
    -0.07
    PageRoute
    -0.07
    онÑĮ
    -0.07
     Lump
    -0.07
    antas
    -0.06
    ConverterFactory
    -0.06
    ÑĥÑĩа
    -0.06
    POSITIVE LOGITS
    stoff
    0.07
    ìŀIJìĿ¸
    0.06
    érie
    0.06
    彦
    0.06
    cek
    0.06
    å½
    0.06
     Sing
    0.06
    ause
    0.06
    ehr
    0.06
    Ìģ
    0.06
    Act Density 0.026%

    No Known Activations