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

    Neuronpedia

    INDEX
    Explanations

    words or parts of words containing the letters "ss"

    oai_token-act-pair · gpt-3.5-turbo

    words related to numerous secretive or hidden elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ£
    -0.73
    TPP
    -0.69
    merce
    -0.66
     PKK
    -0.62
    few
    -0.62
     tranqu
    -0.62
    paralle
    -0.62
    hyde
    -0.62
    phrine
    -0.62
     Ebola
    -0.61
    POSITIVE LOGITS
    ault
    1.13
    ystem
    1.00
    ession
    0.99
    alid
    0.98
    ometimes
    0.94
    alon
    0.92
    andra
    0.90
    essions
    0.89
    omething
    0.89
    ippi
    0.88
    Act Density 0.012%

    No Known Activations