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

    Neuronpedia

    INDEX
    Explanations

    frequently appearing high-value numeric references or indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ullan
    -0.18
    abus
    -0.15
    ackage
    -0.15
    éĸĭ
    -0.14
    zsche
    -0.14
    egas
    -0.14
    ves
    -0.14
     Bates
    -0.14
     te
    -0.14
    æ
    -0.14
    POSITIVE LOGITS
    aret
    0.18
    ious
    0.15
    uida
    0.15
    oru
    0.15
    aksi
    0.15
    iden
    0.15
    Ãļ
    0.14
    üss
    0.14
    ereg
    0.14
    iously
    0.14
    Act Density 0.000%

    No Known Activations