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

    Neuronpedia

    INDEX
    Explanations

    references to large quantities or numerical values, particularly those involving the word "thousand."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iger
    -0.16
    inz
    -0.15
    lee
    -0.15
    umin
    -0.15
    ou
    -0.14
    ault
    -0.14
    che
    -0.14
    icon
    -0.14
    avia
    -0.13
    ud
    -0.13
    POSITIVE LOGITS
    ths
    0.25
    aires
    0.19
    naire
    0.18
    naires
    0.18
    th
    0.17
    lerce
    0.17
    ibase
    0.17
    ToOne
    0.17
    fold
    0.17
    PLUS
    0.16
    Act Density 0.058%

    No Known Activations