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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating an intention to discuss or analyze a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iest
    -0.18
    516
    -0.15
     spectrum
    -0.15
    ises
    -0.14
     Highlights
    -0.14
    iri
    -0.14
    골
    -0.14
    514
    -0.14
    LM
    -0.13
    áj
    -0.13
    POSITIVE LOGITS
     briefly
    0.15
    utherland
    0.15
    zy
    0.15
    brief
    0.15
     lets
    0.14
    Ñĩим
    0.14
    Brief
    0.14
     Sass
    0.14
     Grade
    0.14
    çak
    0.14
    Act Density 0.363%

    No Known Activations