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

    Neuronpedia

    INDEX
    Explanations

    verbs related to starting or initiating actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases and concepts related to initiating actions or projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Emin
    -0.71
    ancies
    -0.71
    uve
    -0.71
     Debor
    -0.69
    afety
    -0.68
    quickShipAvailable
    -0.68
    izen
    -0.68
     Sins
    -0.67
    è¯
    -0.66
    BuyableInstoreAndOnline
    -0.66
    POSITIVE LOGITS
    starter
    1.19
    strap
    1.04
    starting
    1.01
    boxing
    0.94
    tails
    0.91
    started
    0.91
    start
    0.87
    sticks
    0.82
     kicking
    0.79
     kick
    0.77
    Act Density 0.015%

    No Known Activations