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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "of," indicating a focus on prepositional phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovation
    -0.16
    kip
    -0.15
    olem
    -0.14
    agger
    -0.14
    ãĥ¼ãĤ¸
    -0.14
    ovÄĽ
    -0.14
    æĥħ
    -0.14
    ability
    -0.14
    t
    -0.14
    raph
    -0.14
    POSITIVE LOGITS
     course
    0.30
    iciálnÃŃ
    0.28
    icial
    0.28
    sted
    0.26
    course
    0.26
    ertas
    0.26
    icers
    0.25
    entimes
    0.24
    ft
    0.24
    lox
    0.24
    Act Density 0.108%

    No Known Activations