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

    Neuronpedia

    INDEX
    Explanations

    specific nouns or terms that are associated with various contexts or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ̣
    -0.16
    ìĥĿ
    -0.15
    ↵
    -0.15
     kvin
    -0.15
    ert
    -0.15
    ERT
    -0.14
    æĺĩ
    -0.14
     Erotik
    -0.13
     Shawn
    -0.13
    468
    -0.13
    POSITIVE LOGITS
    legg
    0.18
    ós
    0.15
    faction
    0.15
    ÑĢаÑĩ
    0.15
    ataka
    0.14
    emain
    0.14
    .ib
    0.14
    ãģĸ
    0.14
    .Horizontal
    0.14
    lla
    0.14
    Act Density 0.014%

    No Known Activations