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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of "primordial" or derived from it

    oai_token-act-pair · gpt-3.5-turbo

    references to primitive concepts or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UGE
    -0.81
    phia
    -0.79
    IGH
    -0.79
    wrapper
    -0.75
     Graveyard
    -0.72
     Hanson
    -0.69
    pez
    -0.68
     Dangerous
    -0.67
     Cheong
    -0.64
     Schwar
    -0.64
    POSITIVE LOGITS
    ordial
    1.20
    itives
    1.09
    ality
    0.94
    lest
    0.93
    rose
    0.87
    eless
    0.86
    eenth
    0.84
    essential
    0.84
    nis
    0.83
    ling
    0.82
    Act Density 0.027%

    No Known Activations