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

    Neuronpedia

    INDEX
    Explanations

    instances of tags and categories within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilen
    -0.17
    ĢìĿ´
    -0.15
    èĤ²
    -0.15
    bral
    -0.14
    à¹Ĥà¸Ĺ
    -0.14
    .CO
    -0.14
    iban
    -0.14
    SI
    -0.14
    abo
    -0.13
    scripts
    -0.13
    POSITIVE LOGITS
     Archive
    0.20
     Archives
    0.20
     archive
    0.19
    arp
    0.18
     archives
    0.17
    rchive
    0.17
    ged
    0.16
    Archive
    0.16
     Jay
    0.15
    hled
    0.14
    Act Density 0.007%

    No Known Activations