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

    Neuronpedia

    INDEX
    Explanations

    email addresses

    oai_token-act-pair · gpt-3.5-turbo

    email addresses or identifiers within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rebellion
    -0.76
     Characters
    -0.75
     Liberia
    -0.75
     Rwanda
    -0.73
     Ethiopian
    -0.73
     Houses
    -0.73
     Senegal
    -0.72
     Units
    -0.72
     System
    -0.71
     ESC
    -0.71
    POSITIVE LOGITS
    bryce
    1.23
    maxwell
    1.16
    anders
    1.14
    arry
    1.11
    john
    1.11
    smith
    1.09
    onest
    1.06
    iott
    1.05
    brown
    1.04
    anton
    1.02
    Act Density 0.075%

    No Known Activations