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

    Neuronpedia

    INDEX
    Explanations

    punctuation used in quotes and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Plugin
    -0.15
    okane
    -0.14
    362
    -0.14
     Roose
    -0.14
    odal
    -0.13
    ete
    -0.13
    ate
    -0.13
    alen
    -0.13
    sburg
    -0.13
    illis
    -0.13
    POSITIVE LOGITS
    undi
    0.16
    abox
    0.15
    roperty
    0.15
    ocup
    0.15
    uml
    0.14
    ipher
    0.14
    rik
    0.14
     URLRequest
    0.14
    dsa
    0.14
     Tou
    0.14
    Act Density 0.003%

    No Known Activations