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

    Neuronpedia

    INDEX
    Explanations

    references to space and gravity-related phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    तर
    -0.16
    CLU
    -0.15
     ëĭ¤ìļ´ë°Ľê¸°
    -0.15
    å¾ĴæŃ©
    -0.14
     Weinstein
    -0.14
    åĿĽ
    -0.14
     KAR
    -0.14
    jez
    -0.14
     kar
    -0.14
    EGA
    -0.14
    POSITIVE LOGITS
    oux
    0.17
    sak
    0.16
    unas
    0.15
    bane
    0.15
     itself
    0.15
     payload
    0.14
    .inject
    0.14
    upon
    0.14
     Fur
    0.14
     Lang
    0.13
    Act Density 0.005%

    No Known Activations