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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating long-standing feelings or desires

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WO
    -0.18
    aktu
    -0.17
     Red
    -0.16
    ieux
    -0.15
    insi
    -0.15
     Ment
    -0.15
     Merry
    -0.15
     USDA
    -0.15
    ilis
    -0.14
     Ze
    -0.14
    POSITIVE LOGITS
    RYPT
    0.17
    ÅĻen
    0.15
    elt
    0.15
    رÙĪد
    0.15
    andır
    0.14
    aland
    0.14
    vae
    0.14
    Ãły
    0.14
    ãģ¼
    0.14
    ãĥĥãĥĪ
    0.14
    Act Density 0.247%

    No Known Activations