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

    Neuronpedia

    INDEX
    Explanations

    words related to functionality or operation

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the function or operation of various systems or technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Deaths
    -0.60
    ede
    -0.59
     Ending
    -0.59
    gart
    -0.57
     Venture
    -0.56
    etus
    -0.56
     Returning
    -0.56
     parting
    -0.56
     Consortium
    -0.55
    ibi
    -0.55
    POSITIVE LOGITS
     differently
    1.08
     primarily
    1.07
     mainly
    1.02
     ident
    0.99
     seamlessly
    0.98
     similarly
    0.93
     principally
    0.92
     beautifully
    0.91
     wonderfully
    0.91
     chiefly
    0.91
    Act Density 0.193%

    No Known Activations