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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social relationships and interactions, particularly in the context of language and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.02
    2:0.10
    3:0.11
    4:0.07
    5:0.03
    6:0.07
    7:0.03
    8:0.05
    9:0.08
    10:0.07
    11:0.22
    Negative Logits
    cms
    -1.57
    ーティ
    -1.56
    DragonMagazine
    -1.55
    lar
    -1.54
     Boise
    -1.50
    clus
    -1.49
    fest
    -1.46
    Ult
    -1.44
    baugh
    -1.42
     beck
    -1.41
    POSITIVE LOGITS
    vidia
    1.70
    olar
    1.63
    ":[{"
    1.57
    hiba
    1.57
    >[
    1.51
    agos
    1.47
    "},
    1.46
    immune
    1.46
    "],
    1.45
    imus
    1.43
    Act Density 0.021%

    No Known Activations