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

    Neuronpedia

    INDEX
    Explanations

    numbers indicating measurements, quantities, or statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to statistics or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵Âł
    -0.64
     aisle
    -0.58
    ":"/
    -0.57
     neighb
    -0.55
     Opp
    -0.55
    heter
    -0.53
     fors
    -0.52
     Heb
    -0.52
     parted
    -0.51
     cooper
    -0.50
    POSITIVE LOGITS
     lakh
    1.00
    ,
    0.77
    0000
    0.77
     thousand
    0.75
    İĭ
    0.74
     million
    0.72
    000
    0.68
    Merit
    0.67
    ADRA
    0.66
    00000
    0.65
    Act Density 0.086%

    No Known Activations