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

    Neuronpedia

    INDEX
    Explanations

    citations of academic works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tin
    -0.16
    rance
    -0.15
    lander
    -0.15
     Phones
    -0.15
    lett
    -0.14
    лекÑģанд
    -0.14
    辦
    -0.14
    abeth
    -0.14
     ethnicity
    -0.14
    lyph
    -0.14
    POSITIVE LOGITS
     Suz
    0.15
    hc
    0.14
    à¸Ķร
    0.14
    ÑģÑĤа
    0.14
    =back
    0.14
    ##_
    0.14
    æij
    0.14
     SpoleÄį
    0.13
     ÑĪÑĤ
    0.13
    964
    0.13
    Act Density 0.013%

    No Known Activations