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

    Neuronpedia

    INDEX
    Explanations

    phrases related to fundamental aspects or components

    oai_token-act-pair · gpt-3.5-turbo

    words related to foundational concepts or principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.88
    pload
    -0.68
    wb
    -0.64
    govtrack
    -0.63
    soDeliveryDate
    -0.61
    neapolis
    -0.61
    hiba
    -0.60
    ifter
    -0.60
     highest
    -0.59
    sters
    -0.58
    POSITIVE LOGITS
    arium
    1.12
    ament
    1.08
    als
    0.95
    aments
    0.94
    edly
    0.93
    ation
    0.87
    ary
    0.86
    ations
    0.84
    alist
    0.82
    ally
    0.80
    Act Density 0.017%

    No Known Activations