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

    Neuronpedia

    INDEX
    Explanations

    words related to launching or starting something, especially in the context of activities or events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Emin
    -0.92
    uve
    -0.84
     Explorer
    -0.68
    rians
    -0.67
    ational
    -0.67
    é¾į
    -0.66
    MIN
    -0.64
    afety
    -0.63
    Error
    -0.62
    xual
    -0.62
    POSITIVE LOGITS
    starter
    1.31
    boxing
    1.16
    started
    0.98
    starting
    0.95
    haw
    0.90
    strap
    0.89
    tails
    0.88
    sticks
    0.86
    start
    0.85
    stick
    0.83
    Act Density 0.666%

    No Known Activations