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

    Neuronpedia

    INDEX
    Explanations

    instances of people named or with the title "Editor"

    oai_token-act-pair · gpt-3.5-turbo

    the letter 's' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leilan
    -0.65
    Buzz
    -0.62
     Pwr
    -0.62
     jog
    -0.61
    yz
    -0.61
     multiplication
    -0.59
     floppy
    -0.57
     Hedge
    -0.57
     Galile
    -0.57
     repetition
    -0.57
    POSITIVE LOGITS
    wered
    1.01
    ources
    1.01
    hips
    0.99
    perse
    0.99
    orship
    0.95
    nyder
    0.94
    ional
    0.94
    alty
    0.90
    ister
    0.90
    linger
    0.90
    Act Density 0.170%

    No Known Activations