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

    Neuronpedia

    INDEX
    Explanations

    words related to events or actions that happen at a certain point in time

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a progression or outcome over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lua
    -0.80
    atures
    -0.69
    artisan
    -0.66
    yet
    -0.66
    teen
    -0.65
     Crusader
    -0.65
    che
    -0.64
    VK
    -0.63
    emen
    -0.63
    roller
    -0.62
    POSITIVE LOGITS
     culmin
    0.91
     succumb
    0.88
     settle
    0.81
     assimil
    0.80
     succumbed
    0.80
     migrate
    0.79
    icably
    0.79
     succeed
    0.78
     converge
    0.78
     dwind
    0.78
    Act Density 0.023%

    No Known Activations