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

    Neuronpedia

    INDEX
    Explanations

    declarative statements about measurements, conditions, and comparisons across different subjects or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avis
    -0.18
    å¹³æĪIJ
    -0.15
    insky
    -0.15
    inand
    -0.14
    ivery
    -0.14
     eskort
    -0.14
    ocuk
    -0.14
    stras
    -0.14
    اÙĨÙĩ
    -0.13
    pone
    -0.13
    POSITIVE LOGITS
    olle
    0.16
     Anast
    0.15
     Morrison
    0.15
    doctrine
    0.14
    summary
    0.14
    asio
    0.14
    _bm
    0.14
    è¢ĸ
    0.14
     Mah
    0.14
    QUIT
    0.14
    Act Density 0.020%

    No Known Activations