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

    Neuronpedia

    INDEX
    Explanations

    anything related to inflammation or inflation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to inflammation and inflated conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quartered
    -0.76
    hill
    -0.72
    arij
    -0.72
    stood
    -0.71
     distingu
    -0.71
    ician
    -0.70
    etheless
    -0.68
    icians
    -0.67
    endez
    -0.66
     Massacre
    -0.65
    POSITIVE LOGITS
     inflated
    1.08
     infl
    0.88
    uating
    0.84
    uations
    0.83
    ulative
    0.82
    oster
    0.76
     prices
    0.75
    urized
    0.72
     eg
    0.72
    uated
    0.71
    Act Density 0.044%

    No Known Activations