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

    Neuronpedia

    INDEX
    Explanations

    words related to stealth or subtlety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erase
    -0.17
    796
    -0.17
    747
    -0.16
    quam
    -0.15
    readcrumb
    -0.15
    794
    -0.15
    SES
    -0.14
    ruh
    -0.14
    cri
    -0.14
    aversal
    -0.14
    POSITIVE LOGITS
    uth
    0.29
    azy
    0.24
    UTH
    0.24
    aze
    0.23
    dd
    0.21
     Sle
    0.20
    AZE
    0.19
    ight
    0.18
    igh
    0.17
    emo
    0.16
    Act Density 0.004%

    No Known Activations