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

    Neuronpedia

    INDEX
    Explanations

    phrases related to individual rights and information requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ãłi
    -0.18
    unger
    -0.16
    ãĥ«ãĥī
    -0.15
     dispens
    -0.15
    stab
    -0.14
    OfDay
    -0.14
     خبر
    -0.14
    _trap
    -0.13
    PERT
    -0.13
    ãĥªãĥ³ãĤ°
    -0.13
    POSITIVE LOGITS
     exercise
    0.24
     exercised
    0.23
     Exercise
    0.22
     exerc
    0.22
     rect
    0.20
     exercising
    0.20
    Exercise
    0.19
     Rect
    0.18
     lodge
    0.17
    exercise
    0.17
    Act Density 0.012%

    No Known Activations