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

    Neuronpedia

    INDEX
    Explanations

    encoded characters or symbols that indicate significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -0.15
     Fern
    -0.15
     Lyon
    -0.14
     Madrid
    -0.14
     Meadows
    -0.14
     Bra
    -0.13
     Aub
    -0.13
     VID
    -0.13
     Tate
    -0.13
     Buckingham
    -0.13
    POSITIVE LOGITS
     Genius
    0.32
     Next
    0.27
     Panama
    0.25
     cell
    0.24
     GEN
    0.23
    Next
    0.23
     iphone
    0.22
    .Gen
    0.22
     genius
    0.22
    Pu
    0.22
    Act Density 0.003%

    No Known Activations