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

    Neuronpedia

    INDEX
    Explanations

    comparisons between different entities or conditions

    oai_token-act-pair · gpt-3.5-turbo

    the word "those" and variations related to comparisons or analogies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Karn
    -0.64
    ENSE
    -0.62
     Mori
    -0.61
    LD
    -0.58
     EMS
    -0.57
     Sammy
    -0.56
     Universe
    -0.56
     Syd
    -0.55
     Stadium
    -0.55
    Luck
    -0.55
    POSITIVE LOGITS
    hots
    0.78
    notations
    0.76
    20439
    0.75
     prevailing
    0.74
     sket
    0.73
     pertaining
    0.71
     belonging
    0.68
     imposed
    0.67
    acons
    0.65
     indexed
    0.65
    Act Density 0.071%

    No Known Activations