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

    Neuronpedia

    INDEX
    Explanations

    terms related to regulations and legislative processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñıж
    -0.14
    Subsystem
    -0.13
    assen
    -0.13
    ronics
    -0.12
    yses
    -0.12
    ertools
    -0.12
    avit
    -0.12
    ../../../
    -0.12
    ift
    -0.12
    tml
    -0.12
    POSITIVE LOGITS
     itself
    0.46
    åıĬåħ¶
    0.22
     themselves
    0.21
    ’s
    0.20
    's
    0.20
     herself
    0.20
     ÙĨÙģسÙĩ
    0.19
     kendisi
    0.17
    aviest
    0.17
     himself
    0.17
    Act Density 0.607%

    No Known Activations