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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the option to continue reading more content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    habi
    -0.15
    istique
    -0.15
    eos
    -0.14
    ÑĢоп
    -0.14
    initializer
    -0.14
    dba
    -0.14
    ãĥ¼ãĤ¹ãĥĪ
    -0.14
    untu
    -0.14
    resh
    -0.14
    opsy
    -0.14
    POSITIVE LOGITS
    aul
    0.15
     Madden
    0.15
    CA
    0.14
    ub
    0.14
     Russo
    0.14
     Doch
    0.14
    RT
    0.14
    -et
    0.13
     unf
    0.13
    puties
    0.13
    Act Density 0.003%

    No Known Activations