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

    Neuronpedia

    INDEX
    Explanations

    references to various projects or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ricks
    -0.16
    awan
    -0.16
    quer
    -0.16
    keit
    -0.15
    iting
    -0.15
    upo
    -0.15
    rut
    -0.15
    rum
    -0.15
    ROP
    -0.15
    ities
    -0.14
    POSITIVE LOGITS
    ors
    0.20
    ively
    0.19
    ive
    0.17
    ivism
    0.17
    utenberg
    0.17
     Gutenberg
    0.16
    oppable
    0.16
    elli
    0.15
    ácil
    0.15
    matic
    0.14
    Act Density 0.057%

    No Known Activations