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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate examination or scrutiny

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éru
    -0.17
    oped
    -0.16
    inky
    -0.16
    oli
    -0.15
    rdf
    -0.15
    ÑĪев
    -0.15
    QRST
    -0.14
     traced
    -0.14
    ìĮ
    -0.14
    hei
    -0.13
    POSITIVE LOGITS
     look
    0.38
     closer
    0.33
    look
    0.31
    clo
    0.29
     Clo
    0.28
     peak
    0.27
     close
    0.25
     Look
    0.25
     dek
    0.24
    Look
    0.24
    Act Density 0.028%

    No Known Activations