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

    Neuronpedia

    INDEX
    Explanations

    punctuation and function words in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uers
    -0.15
    UED
    -0.15
    imbus
    -0.15
    jeme
    -0.14
     Flynn
    -0.14
    iffs
    -0.14
    sei
    -0.14
     âĶ
    -0.14
    anza
    -0.14
    lij
    -0.13
    POSITIVE LOGITS
    дом
    0.15
     pis
    0.15
    atum
    0.15
    ÑģÑıÑĩ
    0.14
    ulumi
    0.13
    uges
    0.13
    лÑĥж
    0.13
     pec
    0.13
    isure
    0.13
    ativas
    0.13
    Act Density 0.618%

    No Known Activations