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

    Neuronpedia

    INDEX
    Explanations

    sentences enclosed with special characters 'Ċ' and words related to authority or formal settings

    oai_token-act-pair · gpt-3.5-turbo

    instances of strong emotional expressions or significant statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     undermin
    -0.68
     proport
    -0.67
     newcom
    -0.62
    senal
    -0.59
     citiz
    -0.59
     occas
    -0.57
    minist
    -0.57
    mbuds
    -0.56
     grid
    -0.55
     indoors
    -0.55
    POSITIVE LOGITS
    ↵
    0.76
    Interstitial
    0.74
    "...
    0.69
    inventoryQuantity
    0.66
    "(
    0.66
     "$
    0.65
     "\
    0.64
    CVE
    0.63
     "(
    0.63
    "
    0.62
    Act Density 0.503%

    No Known Activations