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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "here" and related phrases indicating presence or navigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ToLeft
    -0.16
    ndata
    -0.15
    ween
    -0.15
    etri
    -0.15
    ÙĦات
    -0.15
     íĮĮìĿ¼ì²¨ë¶Ģ
    -0.14
    anki
    -0.14
    AttributeValue
    -0.14
    uta
    -0.14
    assis
    -0.14
    POSITIVE LOGITS
    oods
    0.17
     Woods
    0.16
    ood
    0.15
    pliant
    0.14
     Gul
    0.14
    rength
    0.14
     Sadd
    0.14
    _nth
    0.13
     Albert
    0.13
     deadliest
    0.13
    Act Density 0.005%

    No Known Activations