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

    Neuronpedia

    INDEX
    Explanations

    sentences ending with a specific format of the word 's'

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Tours
    -0.80
     Sev
    -0.69
     RN
    -0.69
     Salon
    -0.67
     Sources
    -0.65
     Moff
    -0.61
     Alexandria
    -0.61
     Marshal
    -0.60
     Talks
    -0.60
     Mobil
    -0.60
    POSITIVE LOGITS
    uddenly
    1.23
    lightly
    1.14
    pecially
    1.13
    omew
    1.10
    ELF
    1.04
    ometimes
    1.00
    ustainable
    1.00
    atisf
    0.94
    outhern
    0.94
    leeve
    0.90
    Act Density 0.140%

    No Known Activations