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

    Neuronpedia

    INDEX
    Explanations

    titles, mentions, or descriptions related to a principal figure in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "principal" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aughs
    -0.82
    razil
    -0.67
    irc
    -0.67
    lihood
    -0.66
    azes
    -0.65
    YN
    -0.65
    asca
    -0.65
    etimes
    -0.64
    aving
    -0.64
    lex
    -0.64
    POSITIVE LOGITS
    ipal
    1.17
     Principal
    1.12
     principal
    0.96
    ority
    0.93
    Princ
    0.92
    ially
    0.81
    ities
    0.80
     Component
    0.78
    iple
    0.76
    inguished
    0.76
    Act Density 0.009%

    No Known Activations