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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating simplicity or ease of use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lus
    -0.16
    rve
    -0.15
    ús
    -0.15
    abwe
    -0.15
    stdClass
    -0.14
    วà¸Ļ
    -0.14
    elop
    -0.14
    inki
    -0.14
    ugi
    -0.14
    eru
    -0.14
    POSITIVE LOGITS
    plorer
    0.16
    «
    0.15
     afl
    0.15
    aja
    0.14
    aise
    0.14
     retro
    0.14
    kara
    0.14
     Eisen
    0.13
    arter
    0.13
     Yue
    0.13
    Act Density 0.028%

    No Known Activations