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

    Neuronpedia

    INDEX
    Explanations

    terms related to accessibility for individuals with disabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dirty
    -0.14
     Draws
    -0.14
    .hr
    -0.13
     поÑħ
    -0.13
    é¥
    -0.13
    redi
    -0.13
     jug
    -0.13
    licer
    -0.13
     Held
    -0.13
    è£Ĥ
    -0.13
    POSITIVE LOGITS
    kara
    0.18
     mobility
    0.15
    리ìĸ´
    0.15
     backward
    0.15
    tesy
    0.14
     mouth
    0.14
    çIJ
    0.14
    ãĥªãĤ¢
    0.14
    ứng
    0.13
     melted
    0.13
    Act Density 0.013%

    No Known Activations