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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of cities and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.24
    3:0.04
    4:0.06
    5:0.03
    6:0.05
    7:0.11
    8:0.03
    9:0.03
    10:0.21
    11:0.12
    Negative Logits
    worldly
    -1.46
     haunt
    -1.43
     flashbacks
    -1.36
    orr
    -1.33
     glimps
    -1.33
    lasses
    -1.33
    ーテ
    -1.32
     classmates
    -1.30
    translation
    -1.29
    00200000
    -1.28
    POSITIVE LOGITS
    Flag
    1.72
    ossier
    1.48
     determines
    1.46
    llor
    1.45
     unilaterally
    1.42
    Count
    1.42
    ependence
    1.41
    pires
    1.40
    unity
    1.36
     sovereign
    1.35
    Act Density 0.018%

    No Known Activations