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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of titles

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "titles" in contexts related to media or entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ITH
    -0.75
    gm
    -0.71
    ndum
    -0.70
     Alto
    -0.65
     Rasmussen
    -0.62
     SS
    -0.61
     Tucker
    -0.61
     intestine
    -0.61
     Common
    -0.59
     Hoffman
    -0.59
    POSITIVE LOGITS
     titles
    1.28
    manship
    1.00
    title
    0.93
    marks
    0.90
    paces
    0.86
     title
    0.84
    itles
    0.84
    ãĥĩ
    0.80
    ¥µ
    0.79
    Hunt
    0.79
    Act Density 0.011%

    No Known Activations