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

    Neuronpedia

    INDEX
    Explanations

    phrases that encourage exploration or further action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OLLOW
    -0.15
     Himself
    -0.15
    dea
    -0.15
    st
    -0.14
    folk
    -0.14
     essence
    -0.14
    soever
    -0.13
    xies
    -0.13
    sten
    -0.13
    zon
    -0.13
    POSITIVE LOGITS
    æ¸ħæ¥ļ
    0.15
    istrovstvÃŃ
    0.15
    :.:
    0.14
    leyen
    0.14
    ABCDE
    0.14
    sbin
    0.14
    åľ°ä¸ĭ
    0.14
    erce
    0.13
     Spi
    0.13
    uto
    0.13
    Act Density 0.013%

    No Known Activations