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

    Neuronpedia

    INDEX
    Explanations

    phrases with the word "of" followed by numerical values or indicators of quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤĪãģĨãģ«
    -0.17
    ylon
    -0.16
    æĥħ
    -0.15
    ãĤĪãģĨãģª
    -0.15
    ovation
    -0.15
    ãģ®ãģ¯
    -0.14
    ship
    -0.14
    ãĥ¼ãĤ¸
    -0.14
    大
    -0.14
    illo
    -0.14
    POSITIVE LOGITS
     course
    0.31
    course
    0.28
    ft
    0.28
    ften
    0.26
    ertas
    0.26
    lox
    0.25
    icina
    0.25
    ffset
    0.24
    iciálnÃŃ
    0.23
    sted
    0.23
    Act Density 0.173%

    No Known Activations