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

    Neuronpedia

    INDEX
    Explanations

    terms relating to erection and barriers, particularly in the context of dysfunction or societal impediments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.09
    3:0.22
    4:0.02
    5:0.05
    6:0.08
    7:0.11
    8:0.07
    9:0.11
    10:0.07
    11:0.08
    Negative Logits
    ieri
    -1.26
    esson
    -1.18
    emo
    -1.13
    ère
    -1.12
    atti
    -1.08
    uddin
    -1.07
    heit
    -1.07
    ammy
    -1.06
    henko
    -1.04
    aki
    -1.03
    POSITIVE LOGITS
     abl
    1.28
     prost
    1.12
     resil
    1.04
     rudimentary
    1.02
     contrace
    1.00
     makeshift
    0.99
     antennas
    0.99
    conservancy
    0.99
    ectomy
    0.98
     retract
    0.97
    Act Density 0.001%

    No Known Activations