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

    Neuronpedia

    INDEX
    Explanations

    references to familiarity or recognition of concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     estekak
    -0.53
    IsMutable
    -0.51
    ècie
    -0.44
    erapeutics
    -0.41
     dAtA
    -0.41
     ویکی‌پدیا
    -0.38
    balleur
    -0.38
     religione
    -0.37
    brities
    -0.37
     rarity
    -0.37
    POSITIVE LOGITS
     familiar
    1.34
    familiar
    1.22
    Familiar
    1.00
     Familiar
    0.96
     familiare
    0.73
     familiarize
    0.72
     familières
    0.71
     unfamiliar
    0.69
     accustomed
    0.68
     знако
    0.68
    Act Density 0.239%

    No Known Activations