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

    Neuronpedia

    INDEX
    Explanations

    quantitative measurements and statistical analyses related to experimental results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lbs
    -0.16
     Bath
    -0.15
    igin
    -0.15
    iseum
    -0.15
    iece
    -0.15
    ÑĥлÑı
    -0.14
    uben
    -0.14
     Fav
    -0.14
    igi
    -0.14
     fine
    -0.14
    POSITIVE LOGITS
    à¤Łà¤°
    0.17
    ETF
    0.16
    ncoder
    0.16
    Cipher
    0.15
    missive
    0.14
    quip
    0.14
     Sentinel
    0.14
     um
    0.13
     Cipher
    0.13
    è³¢
    0.13
    Act Density 0.229%

    No Known Activations