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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aller
    -0.17
    Ư
    -0.15
    zion
    -0.15
    idot
    -0.15
    iglia
    -0.15
     Huffman
    -0.14
    ektor
    -0.14
    icari
    -0.14
    ppo
    -0.14
     Consolid
    -0.14
    POSITIVE LOGITS
     late
    0.14
     Rebellion
    0.14
    estatus
    0.14
    orious
    0.14
    /native
    0.13
     vind
    0.13
    _prefix
    0.13
    ton
    0.13
    adden
    0.13
     ton
    0.13
    Act Density 0.004%

    No Known Activations