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

    Neuronpedia

    INDEX
    Explanations

    phrases related to research and academic investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loh
    -0.08
    idak
    -0.08
    vla
    -0.07
    798
    -0.06
    chter
    -0.06
    TYPO
    -0.06
    ovah
    -0.06
    pesan
    -0.06
    oran
    -0.06
    chts
    -0.06
    POSITIVE LOGITS
     interest
    0.09
     Interest
    0.09
    Interest
    0.09
    interest
    0.07
     interested
    0.07
    ylie
    0.07
    Ã¶ÄŁ
    0.07
     ê´Ģìĭ¬
    0.07
     interesse
    0.07
    research
    0.07
    Act Density 0.030%

    No Known Activations