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

    Neuronpedia

    INDEX
    Explanations

    phrases related to urgent changes and improvements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nor
    -0.17
    veloper
    -0.15
    REFERRED
    -0.15
    okane
    -0.14
    atcher
    -0.14
    estre
    -0.14
    inaire
    -0.14
    nor
    -0.14
    HER
    -0.14
    ivant
    -0.14
    POSITIVE LOGITS
     ground
    0.15
    itto
    0.14
     Gui
    0.14
    _RESERVED
    0.14
    ühl
    0.13
    oze
    0.13
    xFE
    0.13
    ç´Ļ
    0.13
    ports
    0.13
     hogy
    0.13
    Act Density 0.533%

    No Known Activations