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

    Neuronpedia

    INDEX
    Explanations

    numerical references or identifiers related to scientific publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    laus
    -0.18
    rieve
    -0.15
    stad
    -0.15
    tega
    -0.15
    ../
    -0.15
    äºĮäºĮ
    -0.15
    ../../../
    -0.15
    anca
    -0.15
    okus
    -0.15
    nell
    -0.14
    POSITIVE LOGITS
    nd
    0.34
    -thirds
    0.26
    ï¸ı
    0.22
    nder
    0.20
     dozen
    0.20
    gether
    0.18
    ehir
    0.17
    arily
    0.16
     thirds
    0.15
    nds
    0.15
    Act Density 0.451%

    No Known Activations