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

    Neuronpedia

    INDEX
    Explanations

    phrases related to characterizing and describing phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    出版年
    -0.63
    
    -0.62
     ddelweddau
    -0.62
    verwijspagina
    -0.56
    يميديا
    -0.56
    transQ
    -0.55
     Taktlose
    -0.54
     étoit
    -0.54
    توض
    -0.53
    +#+#
    -0.53
    POSITIVE LOGITS
     hallmark
    0.59
    ESTONE
    0.57
     Wissenschaften
    0.53
    />";
    0.52
    ArrayType
    0.52
    ség
    0.52
     breed
    0.51
    ARDO
    0.51
    不然
    0.50
    mbic
    0.50
    Act Density 0.418%

    No Known Activations