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

    Neuronpedia

    INDEX
    Explanations

    words related to completion or totalness

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of completeness or totality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    maid
    -0.79
    hops
    -0.78
    paces
    -0.75
    GES
    -0.74
    spr
    -0.73
    ////
    -0.73
    */(
    -0.72
    osi
    -0.72
    anners
    -0.71
    tags
    -0.68
    POSITIVE LOGITS
     strangers
    1.19
     stranger
    1.09
     disregard
    1.05
     beginners
    0.99
     meltdown
    0.97
     annihilation
    0.97
     domination
    0.96
     lack
    0.94
     blackout
    0.92
     contradiction
    0.89
    Act Density 0.060%

    No Known Activations