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

    Neuronpedia

    INDEX
    Explanations

    phrases related to locations or movements

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating upward movement or progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Koreans
    -0.61
     Dot
    -0.60
    wives
    -0.60
    lords
    -0.58
    bats
    -0.58
    Shift
    -0.57
    lass
    -0.57
     Procedure
    -0.56
     White
    -0.55
     Ratings
    -0.55
    POSITIVE LOGITS
    ometimes
    0.83
    psey
    0.72
    raf
    0.71
    oS
    0.69
    isible
    0.68
    =-=-
    0.67
    Downloadha
    0.67
    weekly
    0.66
    adelphia
    0.66
    asper
    0.66
    Act Density 0.948%

    No Known Activations