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

    Neuronpedia

    INDEX
    Explanations

    nouns related to various groups, items, or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifter
    -0.16
    ÃŃda
    -0.15
    cke
    -0.15
    arga
    -0.15
    Ñīин
    -0.14
    anzi
    -0.14
    adia
    -0.14
    toi
    -0.13
    legg
    -0.13
    leon
    -0.13
    POSITIVE LOGITS
     Syndrome
    0.17
     syndrome
    0.16
     Synd
    0.15
    身ä¸Ĭ
    0.15
    oen
    0.15
     synd
    0.14
     Thur
    0.14
    phant
    0.14
     Introduction
    0.13
    uers
    0.13
    Act Density 0.356%

    No Known Activations