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

    Neuronpedia

    INDEX
    Explanations

    phrases related to security breaches and numbers in technical contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    iosyn
    -0.70
    rir
    -0.70
     Seym
    -0.66
     Ago
    -0.65
    authent
    -0.64
    ¬¼
    -0.62
    iot
    -0.62
    ussian
    -0.60
    atever
    -0.60
    anan
    -0.60
    POSITIVE LOGITS
     varies
    1.57
     depends
    1.34
     exceeds
    1.27
     vary
    1.18
     multiplied
    1.07
     outweigh
    1.06
     decreases
    1.03
     differs
    1.03
     depended
    1.00
     decreased
    0.97
    Act Density 0.294%

    No Known Activations