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

    Neuronpedia

    INDEX
    Explanations

    hyperlinks or calls to action within text

    oai_token-act-pair · gpt-3.5-turbo

    calls to action encouraging resource exploration or information access

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vernment
    -0.72
     destro
    -0.71
    */(
    -0.66
    ãĥĻ
    -0.65
    ciating
    -0.64
    cept
    -0.62
    essed
    -0.62
    æѦ
    -0.61
     peripher
    -0.61
    kered
    -0.61
    POSITIVE LOGITS
     Contact
    0.69
    asia
    0.65
    ande
    0.64
     Adobe
    0.62
     Preservation
    0.62
     Hemp
    0.59
     Ov
    0.57
    contact
    0.56
     Dice
    0.56
     AFC
    0.56
    Act Density 0.112%

    No Known Activations