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

    Neuronpedia

    INDEX
    Explanations

    references to characters and themes from popular media or entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Slf
    -0.14
    ControlEvents
    -0.14
    kc
    -0.14
    ë§ĮëĤ¨
    -0.14
     reli
    -0.14
    iddle
    -0.14
    bih
    -0.14
    _sleep
    -0.13
    екаÑĢ
    -0.13
    471
    -0.13
    POSITIVE LOGITS
     Sent
    0.32
     Power
    0.31
     Ranger
    0.29
     Rangers
    0.28
     ranger
    0.27
    Sent
    0.27
     SENT
    0.26
    Power
    0.25
     sent
    0.25
     MMP
    0.24
    Act Density 0.003%

    No Known Activations