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

    Neuronpedia

    INDEX
    Explanations

    references to titles or phrases containing the word "Last."

    oai_token-act-pair · gpt-3.5-turbo

    references to "Last" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nai
    -0.78
    mble
    -0.78
    OPLE
    -0.75
    pecially
    -0.67
    ologne
    -0.64
    Jr
    -0.63
    kered
    -0.63
    hement
    -0.63
     positively
    -0.62
    ettings
    -0.62
    POSITIVE LOGITS
     Testament
    0.97
     Chance
    0.94
     Gleaming
    0.92
     gasp
    0.90
     Resort
    0.89
     Refuge
    0.87
     Frontier
    0.82
     Exit
    0.82
    Pass
    0.81
     Days
    0.81
    Act Density 0.024%

    No Known Activations