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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and indicators of emphasis in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erness
    -0.75
    soDeliveryDate
    -0.74
    SHA
    -0.71
    taboola
    -0.69
    quartered
    -0.69
    è¦ļéĨĴ
    -0.69
    cause
    -0.69
    ierrez
    -0.63
    ITNESS
    -0.63
    ulic
    -0.62
    POSITIVE LOGITS
     RP
    0.64
     Troll
    0.63
     Predators
    0.62
     Ital
    0.61
     Overt
    0.60
     Kaine
    0.60
     Exposure
    0.60
     Ammo
    0.59
     Wealth
    0.59
     Tweet
    0.59
    Act Density 0.129%

    No Known Activations