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

    Neuronpedia

    INDEX
    Explanations

    verbs and prepositions related to relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aga
    -0.17
    esk
    -0.17
    лиÑĤ
    -0.15
    essel
    -0.15
    adv
    -0.15
    ãĥ£
    -0.15
    omon
    -0.15
    apis
    -0.14
     nackte
    -0.14
    lient
    -0.14
    POSITIVE LOGITS
    еди
    0.16
     вÑĤоÑĢ
    0.15
    PUR
    0.15
    ificio
    0.15
    OMEM
    0.15
    roduced
    0.15
     Edwin
    0.14
     вÑĢемÑı
    0.14
     мне
    0.14
    isode
    0.14
    Act Density 0.008%

    No Known Activations