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

    Neuronpedia

    INDEX
    Explanations

    references to a specific term with variations, possibly related to a brand, product, or organization

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Go" and its variations, indicating a focus on specific content or references related to the "Go" brand or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    creen
    -0.88
    ament
    -0.76
    ussen
    -0.70
     Horus
    -0.67
     ceilings
    -0.67
    ipation
    -0.67
    uctor
    -0.65
    uracy
    -0.65
    terday
    -0.64
    ullah
    -0.63
    POSITIVE LOGITS
    lems
    1.10
    verning
    1.04
    ogly
    1.00
    etz
    0.96
    ogl
    0.94
    Daddy
    0.93
    vt
    0.84
    ethe
    0.83
    ogle
    0.81
    og
    0.78
    Act Density 0.046%

    No Known Activations