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

    Neuronpedia

    INDEX
    Explanations

    phrases or references related to "troopers."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lef
    -0.18
    ums
    -0.17
    urnal
    -0.16
    nge
    -0.15
    zioni
    -0.15
    rý
    -0.15
    mits
    -0.15
    lam
    -0.15
    rov
    -0.15
    urm
    -0.15
    POSITIVE LOGITS
    dden
    0.28
    ppo
    0.23
    opers
    0.23
    UBLE
    0.22
    oper
    0.21
     tro
    0.21
    isi
    0.20
     Tro
    0.20
    oping
    0.20
    Tro
    0.19
    Act Density 0.010%

    No Known Activations