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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate reasoning, motivation, and the justification for actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dew
    -0.17
    astle
    -0.17
    otas
    -0.17
    oose
    -0.15
     Schl
    -0.15
    undle
    -0.14
    lak
    -0.14
    elon
    -0.13
    _glob
    -0.13
    eries
    -0.13
    POSITIVE LOGITS
    edException
    0.14
    CORD
    0.14
    igaret
    0.14
    odesk
    0.14
    สม
    0.14
    人ãģ¯
    0.14
    witch
    0.14
    ÑģÑıÑĤ
    0.14
     баг
    0.14
     bát
    0.13
    Act Density 0.166%

    No Known Activations