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

    Neuronpedia

    INDEX
    Explanations

    phrases that reference plans, structures, or summaries, particularly those related to outlines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ply
    -0.16
    oly
    -0.15
    plier
    -0.15
    è¨
    -0.15
     bond
    -0.15
    etail
    -0.14
    าะ
    -0.14
    th
    -0.14
    ITO
    -0.14
    zel
    -0.14
    POSITIVE LOGITS
    rech
    0.15
    .scalablytyped
    0.15
    ters
    0.15
     reels
    0.15
    رÛĮز
    0.15
    itori
    0.14
    ennon
    0.14
    homepage
    0.14
     McCartney
    0.14
    aking
    0.14
    Act Density 0.020%

    No Known Activations