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

    Neuronpedia

    INDEX
    Explanations

    uppercase words that indicate the start of a sentence or phrase

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "The."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    poke
    -0.75
    asonic
    -0.70
    eno
    -0.67
    ccoli
    -0.66
    dding
    -0.65
    iffe
    -0.64
    insk
    -0.62
    imi
    -0.62
    ito
    -0.62
    ea
    -0.62
    POSITIVE LOGITS
    oret
    1.27
     latter
    1.12
     simplest
    0.99
     biggest
    0.90
     aforementioned
    0.89
     earliest
    0.88
     Economist
    0.87
     remainder
    0.85
     largest
    0.85
    resa
    0.85
    Act Density 0.325%

    No Known Activations