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

    Neuronpedia

    INDEX
    Explanations

    specific mentions or details within texts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.86
    thood
    -0.76
    aver
    -0.73
    brance
    -0.70
    osphere
    -0.70
    anguages
    -0.70
    lua
    -0.69
    imeter
    -0.66
    catentry
    -0.65
     ç¥ŀ
    -0.64
    POSITIVE LOGITS
     how
    1.41
     firsthand
    1.26
     why
    1.08
     tales
    1.06
     instances
    1.03
     harrowing
    1.03
     anecdotes
    1.01
     dozens
    1.00
     allegations
    0.98
     numerous
    0.98
    Act Density 0.190%

    No Known Activations