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

    Neuronpedia

    INDEX
    Explanations

    functional words that indicate relationships or dependencies in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hood
    -0.17
     Hood
    -0.17
     hood
    -0.17
    ledo
    -0.16
    etta
    -0.16
    chant
    -0.15
     Hollow
    -0.15
    GINE
    -0.15
     Dos
    -0.15
    utter
    -0.15
    POSITIVE LOGITS
    _consts
    0.14
    abbr
    0.14
    RTC
    0.14
     nh
    0.14
    854
    0.13
    994
    0.13
    гÑĢа
    0.13
    èħ¹
    0.13
    RG
    0.13
     Garrison
    0.13
    Act Density 0.002%

    No Known Activations