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

    Neuronpedia

    INDEX
    Explanations

    terms related to architecture and design principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rof
    -0.19
     frais
    -0.15
    enery
    -0.15
    328
    -0.14
     Minds
    -0.14
    enic
    -0.14
     estimates
    -0.14
    style
    -0.13
    Ú©ÙĪ
    -0.13
    ÑĸÑĤÑĥ
    -0.13
    POSITIVE LOGITS
     circulation
    0.23
     datum
    0.20
     volumes
    0.18
     parti
    0.18
    /site
    0.17
     fen
    0.17
    SITE
    0.17
     cant
    0.16
     Datum
    0.16
    Hack
    0.16
    Act Density 0.224%

    No Known Activations