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

    Neuronpedia

    INDEX
    Explanations

    phrases related to economics and politics

    oai_token-act-pair · gpt-3.5-turbo

    topics related to social and political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     IPM
    -0.74
    ovy
    -0.65
    !:
    -0.64
    uala
    -0.63
    rising
    -0.63
    etheless
    -0.62
    GGGG
    -0.61
     Seym
    -0.60
    ivating
    -0.60
    cause
    -0.59
    POSITIVE LOGITS
     lacks
    1.13
     exists
    1.10
     resides
    1.10
     hadn
    1.09
     hasn
    1.06
     existed
    1.03
     relies
    1.03
     cannot
    1.02
     dominates
    0.99
     isn
    0.98
    Act Density 0.542%

    No Known Activations