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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases related to commands and instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arf
    -0.15
    ingu
    -0.15
    uary
    -0.15
    zee
    -0.15
    angles
    -0.15
    amik
    -0.15
    éric
    -0.14
    quo
    -0.14
    uti
    -0.14
     plu
    -0.14
    POSITIVE LOGITS
    mekte
    0.14
    Jet
    0.14
    Ø´ÙĨ
    0.14
     Jet
    0.13
    enburg
    0.13
     blasted
    0.13
     Cobb
    0.13
    sources
    0.13
    .btnSave
    0.13
     lazy
    0.13
    Act Density 0.001%

    No Known Activations