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

    Neuronpedia

    INDEX
    Explanations

    the letter "O" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to the character 'O'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -1.04
    terday
    -0.91
    ãĥ¼ãĥĨ
    -0.81
    ãĥķ
    -0.78
     wip
    -0.76
     Refugees
    -0.73
    âķIJ
    -0.72
    ãĤ¼ãĤ¦ãĤ¹
    -0.72
     Dickinson
    -0.70
     sinks
    -0.70
    POSITIVE LOGITS
    mbudsman
    1.13
    atmeal
    1.09
    AK
    1.07
    lean
    1.06
    oga
    1.03
    vernight
    1.03
    mbuds
    1.01
    bey
    0.99
    ober
    0.98
    oh
    0.98
    Act Density 0.027%

    No Known Activations