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

    Neuronpedia

    INDEX
    Explanations

    names with specific initials followed by a single-digit activation value

    oai_token-act-pair · gpt-3.5-turbo

    proper names, specifically initials and surnames of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MSG
    -0.81
     neon
    -0.69
    ModLoader
    -0.67
    Women
    -0.67
     TMZ
    -0.67
     TVs
    -0.66
     charity
    -0.66
    knit
    -0.65
     governing
    -0.65
     prime
    -0.64
    POSITIVE LOGITS
    linger
    1.10
    isson
    1.08
    essler
    1.07
    antz
    0.99
    isner
    0.98
    iggins
    0.98
    utsch
    0.97
    ullivan
    0.96
    ould
    0.96
    orman
    0.95
    Act Density 0.146%

    No Known Activations