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

    Neuronpedia

    INDEX
    Explanations

    symbols, punctuation, and common abbreviations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itize
    -0.19
    arr
    -0.16
    arda
    -0.15
     Nicol
    -0.15
     ARR
    -0.14
    ndo
    -0.14
    icha
    -0.14
    rub
    -0.14
    ave
    -0.14
    aru
    -0.13
    POSITIVE LOGITS
    ampo
    0.17
    atoon
    0.16
    ÃĹ</
    0.15
    enberg
    0.15
    achten
    0.15
    Qed
    0.15
    InMillis
    0.15
    centers
    0.15
    enheim
    0.14
    quot
    0.14
    Act Density 0.095%

    No Known Activations