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

    Neuronpedia

    INDEX
    Explanations

    the name "Tyrone" mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    the word "one"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lished
    -0.88
     actionGroup
    -0.80
    yrinth
    -0.79
    rador
    -0.79
    iosity
    -0.77
    achusetts
    -0.76
    awaru
    -0.75
    ruary
    -0.74
    lishes
    -0.74
    rawler
    -0.72
    POSITIVE LOGITS
    gger
    0.97
    lihood
    0.89
    xus
    0.85
     Tone
    0.83
    llo
    0.82
    xit
    0.81
     Hundred
    0.77
    lli
    0.77
    horn
    0.76
     Bucc
    0.74
    Act Density 0.031%

    No Known Activations