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

    Neuronpedia

    INDEX
    Explanations

    words indicating significant importance or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orex
    -0.15
    dül
    -0.14
    emean
    -0.14
    gere
    -0.14
    ERGE
    -0.14
    kü
    -0.14
    plevel
    -0.14
    anus
    -0.13
    PLUGIN
    -0.13
    cribe
    -0.13
    POSITIVE LOGITS
    ly
    0.19
    notes
    0.16
    /key
    0.16
    ../../../
    0.16
    mente
    0.16
    erus
    0.15
    ãģ¦
    0.14
     ingredient
    0.14
    ï¸
    0.14
    lops
    0.14
    Act Density 0.055%

    No Known Activations