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

    Neuronpedia

    INDEX
    Explanations

    the word "gone."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "gone" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    course
    -0.66
    aire
    -0.66
    ounters
    -0.65
    ellation
    -0.65
    FIG
    -0.65
    Sol
    -0.64
     glim
    -0.63
    eering
    -0.62
    sure
    -0.62
    ãĥ´ãĤ¡
    -0.61
    POSITIVE LOGITS
     overboard
    0.92
     Gone
    0.81
     viral
    0.80
     Away
    0.80
     unnoticed
    0.80
     Bye
    0.79
     bye
    0.78
     forever
    0.75
     extinct
    0.74
    oe
    0.74
    Act Density 0.026%

    No Known Activations