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

    Neuronpedia

    INDEX
    Explanations

    numerical values expressed with a decimal point

    oai_token-act-pair · gpt-3.5-turbo

    sentences that contain decimal numbers or numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     enthusi
    -0.70
     battered
    -0.64
     travelers
    -0.64
     Raf
    -0.63
     traveler
    -0.61
     Aj
    -0.60
     tom
    -0.59
     Baton
    -0.58
     buggy
    -0.58
    Äĩ
    -0.58
    POSITIVE LOGITS
    70710
    1.16
    002
    1.05
    0001
    1.04
    005
    1.04
    05
    1.04
    025
    1.03
    125
    1.01
    000000
    1.01
    75
    1.01
    9999
    1.00
    Act Density 0.054%

    No Known Activations