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

    Neuronpedia

    INDEX
    Explanations

    words related to underground activities or settings

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "under" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ£
    -0.83
     Tik
    -0.73
     Edison
    -0.72
    IER
    -0.71
    andowski
    -0.70
    ILY
    -0.70
    eln
    -0.69
     Retrieved
    -0.69
    ilial
    -0.68
    illac
    -0.67
    POSITIVE LOGITS
    graduate
    1.08
    cover
    1.01
    dogs
    1.01
    whelming
    1.01
    wear
    0.98
    lings
    0.98
    pants
    0.96
    ground
    0.96
    lying
    0.96
    cuts
    0.92
    Act Density 0.036%

    No Known Activations