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

    Neuronpedia

    INDEX
    Explanations

    adjectives and adverbs related to quality and recommendation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ücken
    -0.16
    ityEngine
    -0.14
    ield
    -0.14
    astos
    -0.14
    mour
    -0.14
    idine
    -0.14
     arsch
    -0.14
     Malk
    -0.14
    ardon
    -0.14
    fram
    -0.14
    POSITIVE LOGITS
    kem
    0.17
    oly
    0.17
    ki
    0.15
    illum
    0.15
    /etc
    0.15
    urse
    0.14
    lew
    0.14
    uesta
    0.14
    k
    0.14
    ommen
    0.14
    Act Density 0.057%

    No Known Activations