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

    Neuronpedia

    INDEX
    Explanations

    phrases related to detection and sensory experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.02
    2:0.06
    3:0.21
    4:0.02
    5:0.03
    6:0.06
    7:0.09
    8:0.07
    9:0.15
    10:0.07
    11:0.14
    Negative Logits
    arsity
    -1.18
    enment
    -1.15
    装
    -1.14
    hement
    -1.12
    ヘ
    -1.11
    )=(
    -1.10
     Cube
    -1.06
    GBT
    -1.06
    ��
    -1.05
    ailand
    -1.04
    POSITIVE LOGITS
    mouth
    1.22
     toxins
    1.10
     noses
    1.09
     gaping
    1.07
     pulse
    1.06
    rows
    1.05
     neurot
    1.05
     sniff
    1.04
     mustard
    1.03
     juices
    1.01
    Act Density 0.002%

    No Known Activations