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

    Neuronpedia

    INDEX
    Explanations

    words related to ink

    oai_token-act-pair · gpt-3.5-turbo

    references to ink-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ£
    -0.77
     goose
    -0.71
    ODUCT
    -0.68
    ccording
    -0.61
    ãĥ¼ãĥ³
    -0.60
    Interstitial
    -0.60
     Âł Âł Âł Âł Âł Âł Âł Âł
    -0.60
     emb
    -0.60
     foundation
    -0.58
     Âł Âł Âł Âł
    -0.57
    POSITIVE LOGITS
    edin
    1.04
    erman
    1.00
    iewicz
    0.98
    holes
    0.97
    ering
    0.97
    hole
    0.96
    ery
    0.92
    ansen
    0.91
    erm
    0.88
    erton
    0.88
    Act Density 0.047%

    No Known Activations