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

    Neuronpedia

    INDEX
    Explanations

    terms related to chemical processes or reactions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to processes or actions that end in 'ation'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.79
    micro
    -0.66
     mic
    -0.66
     disparate
    -0.63
    tiny
    -0.62
     darn
    -0.61
    é¾įå
    -0.61
     ADA
    -0.60
    IDENT
    -0.60
    Dim
    -0.59
    POSITIVE LOGITS
    ation
    1.13
    ary
    1.03
    ality
    0.96
    hower
    0.93
    ations
    0.88
    eering
    0.86
    eus
    0.86
    ally
    0.85
    naire
    0.82
    staking
    0.77
    Act Density 0.024%

    No Known Activations