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

    Neuronpedia

    INDEX
    Explanations

    references to pyramids

    oai_token-act-pair · gpt-3.5-turbo

    references to pyramids and related structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesota
    -0.75
    ously
    -0.73
    ILY
    -0.72
    DERR
    -0.69
     Despair
    -0.63
    eous
    -0.62
     Hitman
    -0.62
     undone
    -0.61
     Hearts
    -0.59
    åŃIJ
    -0.58
    POSITIVE LOGITS
    ramids
    1.68
    ramid
    1.52
    rote
    1.31
    ongyang
    1.24
    romancer
    1.13
    rites
    1.08
    gm
    1.06
    rex
    1.04
    gments
    1.01
    chedel
    1.00
    Act Density 0.020%

    No Known Activations