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

    Neuronpedia

    INDEX
    Explanations

    questions starting with "how" or "what" related to various topics

    oai_token-act-pair · gpt-3.5-turbo

    questions and phrases related to methods and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Mi
    -0.78
    room
    -0.71
    ulic
    -0.70
    Tour
    -0.64
    lich
    -0.64
    erc
    -0.59
    cade
    -0.58
    1994
    -0.58
    Rum
    -0.56
     1976
    -0.56
    POSITIVE LOGITS
     thereof
    1.02
     consequ
    0.95
     accordingly
    0.92
     alike
    0.88
    soever
    0.87
    abouts
    0.87
     consequently
    0.84
     thereto
    0.79
     therein
    0.76
     versa
    0.76
    Act Density 0.125%

    No Known Activations