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

    Neuronpedia

    INDEX
    Explanations

    instances of structured or formal references and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     TMPro
    -0.17
    彦
    -0.16
    одо
    -0.15
    à¹Ĥà¸Ļ
    -0.15
    adj
    -0.15
     Barcl
    -0.14
    umps
    -0.14
    ä»ķ
    -0.14
    ç§
    -0.14
     Voor
    -0.14
    POSITIVE LOGITS
    館
    0.17
    uka
    0.16
    αι
    0.16
     Osman
    0.15
    ICT
    0.15
    din
    0.15
    ICA
    0.14
    eking
    0.14
    ائÙĤ
    0.14
     OEM
    0.14
    Act Density 0.034%

    No Known Activations