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

    Neuronpedia

    INDEX
    Explanations

    terms related to societal structures and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.20
    pagen
    -0.16
    oup
    -0.16
    inta
    -0.16
    ů
    -0.15
    ewood
    -0.15
    outs
    -0.15
    orns
    -0.15
     unw
    -0.14
    escort
    -0.14
    POSITIVE LOGITS
    erto
    0.17
    ãģķãģ¾
    0.17
    iler
    0.15
    ominated
    0.15
    etto
    0.15
     Guil
    0.15
    _CLIP
    0.15
    olas
    0.14
    OME
    0.14
    ÛĮدÛĮ
    0.14
    Act Density 0.402%

    No Known Activations