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

    Neuronpedia

    INDEX
    Explanations

    words related to individuals and their achievements or characteristics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    soever
    -0.68
    Recent
    -0.64
    mare
    -0.64
    upon
    -0.63
    :{
    -0.62
    lol
    -0.61
    conn
    -0.61
    `
    -0.59
    BR
    -0.59
    ories
    -0.59
    POSITIVE LOGITS
    geries
    1.08
    ked
    1.06
     instance
    1.05
     example
    1.05
    gery
    0.99
    bidden
    0.99
     starters
    0.89
    gettable
    0.85
    aging
    0.85
     whom
    0.82
    Act Density 0.138%

    No Known Activations