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

    Neuronpedia

    INDEX
    Explanations

    directives related to search queries and data retrieval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     numbering
    -0.17
    zan
    -0.16
    rof
    -0.14
    cratch
    -0.14
    alet
    -0.14
    à¹Īà¹Ģà¸Ľ
    -0.14
    raki
    -0.14
    appen
    -0.13
    oken
    -0.13
    aleb
    -0.13
    POSITIVE LOGITS
     advanced
    0.28
     Advanced
    0.28
     refined
    0.26
    Advanced
    0.26
     refine
    0.25
     refining
    0.25
     Boolean
    0.25
    advanced
    0.25
     keyword
    0.24
     exact
    0.23
    Act Density 0.116%

    No Known Activations