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

    Neuronpedia

    INDEX
    Explanations

    instances of the symbol or term "is" indicating existence or presence in a variety of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.03
    2:0.12
    3:0.04
    4:0.09
    5:0.02
    6:0.43
    7:0.03
    8:0.04
    9:0.03
    10:0.05
    11:0.06
    Negative Logits
    phrine
    -1.53
    uador
    -1.48
    zeb
    -1.40
    arters
    -1.33
    INAL
    -1.31
    assad
    -1.29
    osure
    -1.18
    azeera
    -1.17
    idav
    -1.17
    idon
    -1.16
    POSITIVE LOGITS
    龍契士
    1.48
     worshipped
    1.36
     belonged
    1.32
     embodies
    1.29
    founded
    1.25
     belongs
    1.19
     Powered
    1.18
     spawned
    1.17
     CoC
    1.16
     sprung
    1.15
    Act Density 0.246%

    No Known Activations