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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¬ãĥ¼
    -0.15
    OSH
    -0.15
    elig
    -0.14
    ÑĸлÑĸ
    -0.14
    insky
    -0.14
    andidate
    -0.13
    strup
    -0.13
    isol
    -0.13
    .jpa
    -0.13
    alone
    -0.13
    POSITIVE LOGITS
    ICA
    0.17
    رÙħ
    0.15
    pon
    0.15
    .cloudflare
    0.15
    STACK
    0.15
     Nut
    0.15
     Hao
    0.14
    Ñħа
    0.14
     nut
    0.14
    andom
    0.14
    Act Density 0.109%

    No Known Activations