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

    Neuronpedia

    INDEX
    Explanations

    phrases related to collection, gathering, and accumulation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    forth
    -0.79
    pher
    -0.79
    witz
    -0.72
    ellen
    -0.67
     submer
    -0.65
    ned
    -0.64
    ffe
    -0.62
     coasts
    -0.62
     Kardashian
    -0.58
     understands
    -0.57
    POSITIVE LOGITS
     signatures
    0.97
    ennial
    0.85
    ivist
    0.84
     royalties
    0.82
    ively
    0.80
    ibles
    0.79
    orate
    0.78
    ertation
    0.77
    collect
    0.74
     Collect
    0.74
    Act Density 0.031%

    No Known Activations