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

    Neuronpedia

    INDEX
    Explanations

    references to types of tiles and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apo
    -0.18
    assen
    -0.16
     LOD
    -0.15
    wed
    -0.14
    ropol
    -0.14
    ship
    -0.14
    UNDLE
    -0.14
    nder
    -0.13
     wo
    -0.13
     migr
    -0.13
    POSITIVE LOGITS
    illisecond
    0.19
    antro
    0.16
    ilim
    0.15
    ebra
    0.15
    stile
    0.15
    iš
    0.14
    .Commands
    0.14
    pell
    0.14
    hetto
    0.14
    à¤Ĩर
    0.14
    Act Density 0.012%

    No Known Activations