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

    Neuronpedia

    INDEX
    Explanations

    phrases related to accountability and structured processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pied
    -0.15
    .camel
    -0.15
    oran
    -0.15
    avn
    -0.14
    rien
    -0.14
    ROME
    -0.14
     /
    -0.14
     n
    -0.14
    .BorderFactory
    -0.14
    iegel
    -0.13
    POSITIVE LOGITS
    setQuery
    0.16
    vt
    0.14
    addtogroup
    0.14
    olie
    0.14
    aphore
    0.13
    ime
    0.13
     Dollar
    0.13
    ë¯
    0.13
    ----------</
    0.13
    ï¼Ł
    0.13
    Act Density 0.066%

    No Known Activations