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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships or connections among entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏĦολ
    -0.15
     Brilliant
    -0.15
     bench
    -0.15
    ogle
    -0.14
    toy
    -0.13
    idak
    -0.13
    (LP
    -0.13
    каÑģ
    -0.13
     Mev
    -0.13
    XM
    -0.13
    POSITIVE LOGITS
    kup
    0.16
    pun
    0.15
    hoa
    0.15
    isy
    0.15
    pk
    0.15
    oli
    0.15
    poon
    0.15
    åѤ
    0.15
    AVIS
    0.14
    宿
    0.14
    Act Density 0.039%

    No Known Activations