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

    Neuronpedia

    INDEX
    Explanations

    significant or important entities, often denoted by capitalization or elevated context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocom
    -0.18
    LinkId
    -0.16
     Ethnic
    -0.16
    æ£
    -0.15
    á»ģn
    -0.15
    enin
    -0.14
    ulos
    -0.14
    _menus
    -0.14
    .hex
    -0.14
    eniz
    -0.14
    POSITIVE LOGITS
    lei
    0.16
     trans
    0.16
     Shock
    0.15
    é¹
    0.15
    assi
    0.15
    Shock
    0.15
    _tran
    0.14
     Saunders
    0.14
     Murray
    0.14
    grim
    0.14
    Act Density 0.020%

    No Known Activations