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

    Neuronpedia

    INDEX
    Explanations

    phrases or words that indicate a relationship to rules or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NV
    -0.17
    tract
    -0.15
    اتÙĩ
    -0.15
    cre
    -0.15
    wa
    -0.15
    mgr
    -0.14
    adow
    -0.14
    خاÙĨ
    -0.14
    han
    -0.14
     Deposit
    -0.14
    POSITIVE LOGITS
    905
    0.15
    ä¸ĬãģĮ
    0.15
    tls
    0.15
    Scalars
    0.15
    451
    0.15
    èįĴ
    0.14
    ickle
    0.14
     Levin
    0.14
    pkg
    0.14
    hlen
    0.14
    Act Density 0.002%

    No Known Activations