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

    Neuronpedia

    INDEX
    Explanations

    possessive forms and associative phrases related to identity or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.03
    2:0.16
    3:0.10
    4:0.06
    5:0.11
    6:0.04
    7:0.04
    8:0.06
    9:0.13
    10:0.10
    11:0.04
    Negative Logits
    pak
    -1.50
    rex
    -1.48
    romy
    -1.44
    HK
    -1.33
    issan
    -1.28
    arget
    -1.26
    eland
    -1.25
    weather
    -1.23
    icut
    -1.23
    rete
    -1.22
    POSITIVE LOGITS
     Manifest
    1.34
    liest
    1.33
    Winged
    1.29
     unification
    1.29
     Directory
    1.27
     revolutions
    1.25
    ItemTracker
    1.24
     theorem
    1.20
     Enlightenment
    1.20
     annotations
    1.19
    Act Density 0.119%

    No Known Activations