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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating the frequency or prevalence of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SGlobal
    -0.15
    ÑĤаж
    -0.14
    inerary
    -0.14
    clud
    -0.14
    liers
    -0.14
    รม
    -0.14
    itecture
    -0.13
    isters
    -0.13
    rong
    -0.13
    adan
    -0.13
    POSITIVE LOGITS
     times
    0.38
    -times
    0.29
    times
    0.28
    æŶåĢĻ
    0.25
     people
    0.24
    人ãģ¯
    0.24
     vezes
    0.23
     studies
    0.21
    Times
    0.21
     modern
    0.21
    Act Density 0.166%

    No Known Activations