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

    Neuronpedia

    INDEX
    Explanations

    mentions or references to surplus, especially in the context of money or resources

    oai_token-act-pair · gpt-3.5-turbo

    mentions of surplus resources or assets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Brist
    -0.73
    icably
    -0.73
    ichen
    -0.73
    oland
    -0.70
    endez
    -0.69
    usra
    -0.69
    ocol
    -0.68
    ographed
    -0.68
    omed
    -0.68
    olog
    -0.68
    POSITIVE LOGITS
     surplus
    1.07
    lys
    0.67
    cy
    0.67
    llor
    0.67
     multiplier
    0.65
     delta
    0.64
     stash
    0.64
     accrued
    0.63
    ebin
    0.62
    intendent
    0.62
    Act Density 0.009%

    No Known Activations