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

    Neuronpedia

    INDEX
    Explanations

    terms related to accountability and oversight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     billig
    -0.15
    ohon
    -0.15
    jvu
    -0.15
    ãĥ¬ãĥĥãĥĪ
    -0.15
    ildo
    -0.14
    bla
    -0.14
    olie
    -0.14
    munition
    -0.14
    eldo
    -0.14
    etti
    -0.14
    POSITIVE LOGITS
    ound
    0.17
    ounds
    0.16
    ez
    0.16
    iez
    0.15
    argin
    0.15
     Gib
    0.14
    oulder
    0.14
    unts
    0.14
     unde
    0.14
    Found
    0.14
    Act Density 0.029%

    No Known Activations