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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "including."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UTERS
    -0.16
    ushima
    -0.14
    eres
    -0.14
    ubl
    -0.14
    etter
    -0.13
    LOCKS
    -0.13
     اÙĦتØŃ
    -0.13
     unst
    -0.13
    Sans
    -0.12
     accel
    -0.12
    POSITIVE LOGITS
    ané
    0.20
    ücken
    0.16
    parated
    0.16
     Lionel
    0.15
    tid
    0.14
    wil
    0.14
    mand
    0.14
    mond
    0.14
     Lover
    0.14
    isplay
    0.14
    Act Density 0.033%

    No Known Activations