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

    Neuronpedia

    INDEX
    Explanations

    phrases including the letters "ss" repeated sequentially

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ass" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ£
    -0.76
    TPP
    -0.74
    scope
    -0.65
    tin
    -0.64
    paralle
    -0.64
    ts
    -0.63
    Äĩ
    -0.62
    ãĤ§
    -0.61
    judicial
    -0.61
     Imran
    -0.59
    POSITIVE LOGITS
    ault
    1.07
    ometimes
    1.07
    alid
    1.06
    ystem
    1.04
    ession
    1.01
    assin
    0.97
    ippi
    0.93
    oci
    0.93
    omething
    0.91
    andra
    0.91
    Act Density 0.012%

    No Known Activations