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

    Neuronpedia

    INDEX
    Explanations

    instances of important data or key metrics within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bust
    -0.15
    ossa
    -0.15
    661
    -0.15
    roof
    -0.15
    loyment
    -0.14
    eka
    -0.14
    éri
    -0.14
     Crush
    -0.14
    oub
    -0.14
    Allocator
    -0.14
    POSITIVE LOGITS
     Schro
    0.15
    essen
    0.15
    inas
    0.15
    elli
    0.15
     McGregor
    0.14
     ì¶ľìŀ¥
    0.14
    ainen
    0.14
    çIJ´
    0.14
    \OptionsResolver
    0.14
     heavy
    0.14
    Act Density 0.007%

    No Known Activations