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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and asterisks, indicating lists or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uli
    -0.14
    agraph
    -0.14
    kea
    -0.13
    ursed
    -0.13
     Hòa
    -0.13
    rak
    -0.13
    ults
    -0.13
    .af
    -0.13
    omain
    -0.13
    king
    -0.13
    POSITIVE LOGITS
    ilig
    0.19
    zb
    0.17
    PB
    0.15
     Invent
    0.15
    bsd
    0.14
     scand
    0.14
    dre
    0.14
    ilog
    0.14
    .Attribute
    0.14
    lá
    0.14
    Act Density 0.031%

    No Known Activations