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

    Neuronpedia

    INDEX
    Explanations

    strings that appear to be random numbers, timestamps, and symbols

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and associated numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     behavi
    -0.52
     undermin
    -0.46
     conflic
    -0.45
     entreprene
    -0.44
     exha
    -0.44
     streaks
    -0.44
     metic
    -0.43
     apparel
    -0.42
     infiltr
    -0.42
     bolst
    -0.42
    POSITIVE LOGITS
    1967
    0.52
    shall
    0.51
    1970
    0.50
    6666
    0.50
    1999
    0.49
    2000
    0.49
    2500
    0.49
    imon
    0.49
    1950
    0.48
    right
    0.48
    Act Density 1.338%

    No Known Activations