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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and significant named entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥ³
    -0.18
    oldemort
    -0.17
    ocale
    -0.15
    θη
    -0.15
    ong
    -0.15
    etten
    -0.15
     Vak
    -0.14
    okus
    -0.14
     Elev
    -0.14
    iface
    -0.14
    POSITIVE LOGITS
    inant
    0.16
    rut
    0.16
    binations
    0.15
     indexed
    0.15
     åĥ
    0.15
     indexes
    0.15
     indexing
    0.15
    jer
    0.14
    lut
    0.14
    inate
    0.14
    Act Density 0.003%

    No Known Activations