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

    Neuronpedia

    INDEX
    Explanations

    references to different forms of the word "si."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ttes
    -0.83
    worthiness
    -0.82
    ICA
    -0.71
    worn
    -0.67
    side
    -0.66
    landish
    -0.66
    lain
    -0.65
    rals
    -0.63
     EVs
    -0.63
    tails
    -0.63
    POSITIVE LOGITS
    pling
    1.21
    ples
    1.02
    plings
    0.97
    pler
    0.90
    plin
    0.82
    enza
    0.82
    iple
    0.82
    ylum
    0.78
    plane
    0.77
    ption
    0.77
    Act Density 0.005%

    No Known Activations