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

    Neuronpedia

    INDEX
    Explanations

    names of a specific person

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "za."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lessly
    -0.97
    LESS
    -0.77
    Īè
    -0.70
    ramer
    -0.70
    bread
    -0.69
    folk
    -0.67
     satell
    -0.66
    ritional
    -0.66
     glim
    -0.65
    amental
    -0.65
    POSITIVE LOGITS
    emon
    0.90
    ombies
    0.85
    quez
    0.84
     Motorsport
    0.83
    ombie
    0.80
    illes
    0.79
    fter
    0.78
    eta
    0.77
    ption
    0.76
    plin
    0.76
    Act Density 0.033%

    No Known Activations