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

    Neuronpedia

    INDEX
    Explanations

    references to pre-existing items or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to established or pre-existing items, systems, or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oner
    -0.78
    psy
    -0.76
    ertodd
    -0.73
    otta
    -0.72
    ÃŃa
    -0.68
     Plane
    -0.67
     Mahjong
    -0.66
    hon
    -0.65
    walk
    -0.65
    ousse
    -0.64
    POSITIVE LOGITS
    existing
    1.00
    ãĤ´
    0.90
    IRE
    0.90
     existing
    0.90
     exting
    0.86
    Interstitial
    0.77
     compr
    0.74
     subscribed
    0.72
    entials
    0.71
     defences
    0.68
    Act Density 0.016%

    No Known Activations