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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing alternatives or oppositional concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illa
    -0.17
     Nest
    -0.16
    ä¸Ķ
    -0.16
    reece
    -0.16
    uckle
    -0.14
    èĥŀ
    -0.14
     Lar
    -0.14
    raz
    -0.14
    ring
    -0.14
    imus
    -0.14
    POSITIVE LOGITS
     Wenger
    0.17
    orders
    0.17
    _Abstract
    0.15
    DDR
    0.15
     taj
    0.14
    ptron
    0.14
    iot
    0.14
    å°ģ
    0.14
    _<?
    0.14
    ýt
    0.14
    Act Density 0.025%

    No Known Activations