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

    Neuronpedia

    INDEX
    Explanations

    references to lists and categorization of items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oyal
    -0.14
    御
    -0.14
    dos
    -0.14
    lder
    -0.14
    byn
    -0.14
     èĩ
    -0.13
    rava
    -0.13
    -BEGIN
    -0.13
    iants
    -0.13
    ERN
    -0.13
    POSITIVE LOGITS
     everything
    0.20
     everywhere
    0.19
    everything
    0.18
    unnable
    0.17
     tudo
    0.17
     anything
    0.16
     Everything
    0.16
    eb
    0.16
    iko
    0.16
    Anything
    0.15
    Act Density 0.212%

    No Known Activations