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

    Neuronpedia

    INDEX
    Explanations

    phrases related to location or direction

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases indicating movement or action involving multiple entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osate
    -0.77
    sers
    -0.77
    hler
    -0.73
    ï¸ı
    -0.73
    letes
    -0.73
    enegger
    -0.71
    ocally
    -0.70
    ansson
    -0.69
    wcs
    -0.68
    aldi
    -0.68
    POSITIVE LOGITS
     hurry
    0.79
     pockets
    0.74
     pocket
    0.73
     haste
    0.71
     drawer
    0.71
     cavity
    0.70
     stead
    0.70
    asonic
    0.69
     vicinity
    0.68
     stra
    0.67
    Act Density 0.147%

    No Known Activations