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

    Neuronpedia

    INDEX
    Explanations

    numerical expressions related to data and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oks
    -0.16
    otton
    -0.14
    heit
    -0.14
    zimmer
    -0.14
    kaar
    -0.14
    avery
    -0.14
    lease
    -0.14
    ERVER
    -0.13
    elden
    -0.13
    aland
    -0.13
    POSITIVE LOGITS
     Vacc
    0.16
    onium
    0.15
    ondo
    0.15
    onn
    0.15
    dhcp
    0.15
    é¾Ħ
    0.15
    aret
    0.15
    unci
    0.14
    462
    0.14
    acon
    0.14
    Act Density 0.057%

    No Known Activations