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

    Neuronpedia

    INDEX
    Explanations

    references to footnotes and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ITHER
    -0.16
    ãĥ³ãĤ¯
    -0.15
    otify
    -0.15
    agne
    -0.15
    оÑĢÑĤ
    -0.15
    ãĥļ
    -0.14
    raits
    -0.13
    ilter
    -0.13
     Mug
    -0.13
    iert
    -0.13
    POSITIVE LOGITS
    \Collections
    0.14
     wer
    0.14
     RPM
    0.14
    /english
    0.14
    -urlencoded
    0.14
     invent
    0.13
    Ka
    0.13
    imonial
    0.13
    λιά
    0.13
    ứng
    0.13
    Act Density 0.006%

    No Known Activations