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

    Neuronpedia

    INDEX
    Explanations

    expressions of indecision and political affiliation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èm
    -0.19
    ÙģÙĤ
    -0.15
    iglia
    -0.15
    ternet
    -0.15
    allery
    -0.14
    itsu
    -0.14
    rellas
    -0.14
    GAN
    -0.14
    tml
    -0.14
    ocus
    -0.14
    POSITIVE LOGITS
     switch
    0.17
     Sons
    0.16
    emek
    0.15
     switched
    0.14
     switching
    0.14
    switch
    0.14
     joins
    0.14
    301
    0.14
     join
    0.14
    642
    0.14
    Act Density 0.277%

    No Known Activations