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

    Neuronpedia

    INDEX
    Explanations

    phrases that express cumulative actions or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orges
    -0.16
    責
    -0.15
    ÙĪØ·
    -0.14
    amar
    -0.14
    266
    -0.14
    agina
    -0.14
    riority
    -0.13
    orge
    -0.13
    å»
    -0.13
    ury
    -0.13
    POSITIVE LOGITS
     Paulo
    0.15
    iland
    0.15
    onn
    0.15
     Jobs
    0.15
    643
    0.14
     Mali
    0.14
    497
    0.14
    ESIS
    0.14
    sov
    0.14
     ÑĢа
    0.13
    Act Density 0.208%

    No Known Activations