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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Ross."

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Ross."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rious
    -0.78
     à¨
    -0.72
    ACTED
    -0.68
     conspicuous
    -0.66
    lder
    -0.65
    brance
    -0.65
    rous
    -0.64
    ulhu
    -0.64
    ع
    -0.64
    ILE
    -0.63
    POSITIVE LOGITS
    bach
    1.04
    etti
    1.02
    inson
    0.95
    olini
    0.92
    lyn
    0.87
    aunders
    0.85
    andowski
    0.85
    iter
    0.82
    igon
    0.81
    dale
    0.79
    Act Density 0.031%

    No Known Activations