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

    Neuronpedia

    INDEX
    Explanations

    instances where actions are being taken or enabled by specific measures or techniques

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to encouragement and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Revival
    -0.67
     Ake
    -0.65
    erence
    -0.65
     disappointment
    -0.63
     Saunders
    -0.62
     Lies
    -0.58
    Winged
    -0.58
     Harding
    -0.58
     Heisman
    -0.57
     irony
    -0.57
    POSITIVE LOGITS
     effectively
    1.01
     efficiently
    0.92
     able
    0.88
     automatically
    0.87
    forth
    0.86
     ensured
    0.83
     streng
    0.77
     empowered
    0.76
     confidently
    0.76
     gradually
    0.75
    Act Density 0.490%

    No Known Activations