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

    Neuronpedia

    INDEX
    Explanations

    numerical rankings or positions in lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inan
    -0.15
    oldt
    -0.14
    zman
    -0.14
    enko
    -0.14
    Unchecked
    -0.14
     Brilliant
    -0.14
    chief
    -0.14
    ISIBLE
    -0.14
     Jud
    -0.13
    .ft
    -0.13
    POSITIVE LOGITS
    irty
    0.18
    oca
    0.16
     Cah
    0.15
    apos
    0.15
    rupt
    0.15
    -largest
    0.14
    overall
    0.14
    ãĥ¼ãĥª
    0.14
     overall
    0.13
     ÐĹаÑħ
    0.13
    Act Density 0.023%

    No Known Activations