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

    Neuronpedia

    INDEX
    Explanations

    concepts related to practices and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arte
    -0.15
    upe
    -0.15
    ACES
    -0.15
    arty
    -0.14
    pagen
    -0.14
    gewater
    -0.14
     Å
    -0.14
    ÑĬ
    -0.14
    енко
    -0.14
    oop
    -0.13
    POSITIVE LOGITS
    iler
    0.17
    ctp
    0.16
    ãģķãģ¾
    0.15
    ominated
    0.15
    igne
    0.15
    ÑĨем
    0.14
    ÑıÑĤ
    0.14
    BALL
    0.14
    ialog
    0.14
    OME
    0.14
    Act Density 0.386%

    No Known Activations