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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols indicating the end of thoughts or questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    engo
    -0.16
    rud
    -0.15
    undy
    -0.15
    anian
    -0.14
    elog
    -0.14
    Ế
    -0.14
    verts
    -0.14
    é§Ĩ
    -0.14
    tright
    -0.14
    pedia
    -0.14
    POSITIVE LOGITS
     tens
    0.15
     Spicer
    0.15
     pi
    0.14
    tn
    0.14
    uard
    0.14
    ritte
    0.14
    еÑĢж
    0.14
     Tent
    0.14
     ÏĢ
    0.14
     kim
    0.14
    Act Density 0.001%

    No Known Activations