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

    Neuronpedia

    INDEX
    Explanations

    references to large sums of money or wealth metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ral
    -0.17
    ÑĢÑıд
    -0.15
    allas
    -0.15
    352
    -0.14
    512
    -0.14
    eking
    -0.14
    大åħ¨
    -0.14
    ulan
    -0.14
    lish
    -0.13
    OWN
    -0.13
    POSITIVE LOGITS
    aires
    0.43
    aire
    0.38
    naire
    0.31
    -dollar
    0.28
    naires
    0.28
    ths
    0.26
    th
    0.22
    -plus
    0.22
    fold
    0.22
    aired
    0.21
    Act Density 0.044%

    No Known Activations