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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating love and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llib
    -0.15
     newVal
    -0.15
    /Internal
    -0.15
    ety
    -0.15
    lington
    -0.14
    ấn
    -0.14
    uale
    -0.14
    maker
    -0.14
    getic
    -0.14
    abad
    -0.14
    POSITIVE LOGITS
    ORB
    0.16
    ahy
    0.16
     fray
    0.14
     Gör
    0.14
    ãĥªãĥ¼
    0.14
    éĢł
    0.14
    UY
    0.14
     tack
    0.14
    gré
    0.14
    éģĹ
    0.14
    Act Density 0.012%

    No Known Activations