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

    Neuronpedia

    INDEX
    Explanations

    references to governmental authority and control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucid
    -0.16
    lama
    -0.16
     «
    -0.15
     («
    -0.15
     mainstream
    -0.15
    072
    -0.15
    olutely
    -0.15
     dot
    -0.14
    220
    -0.14
    ế
    -0.14
    POSITIVE LOGITS
     Cheat
    0.16
    erli
    0.16
    oling
    0.15
     Dish
    0.15
    yd
    0.15
    iture
    0.14
    rtl
    0.14
    @n
    0.14
    utral
    0.14
     htons
    0.14
    Act Density 0.080%

    No Known Activations