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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate relational or emotional connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loff
    -0.19
    eling
    -0.18
    owing
    -0.16
     legisl
    -0.15
    jo
    -0.14
    engo
    -0.14
    indre
    -0.14
    cing
    -0.14
    oley
    -0.13
    (æľ¨
    -0.13
    POSITIVE LOGITS
    adel
    0.18
    olib
    0.15
    ts
    0.15
     Kushner
    0.14
    tsy
    0.14
     lucky
    0.14
    0.14
    usercontent
    0.14
    /kubernetes
    0.14
    ãĤ¦ãĥĪ
    0.14
    Act Density 0.010%

    No Known Activations