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

    Neuronpedia

    INDEX
    Explanations

    words related to preempting actions

    oai_token-act-pair · gpt-3.5-turbo

    words related to prevention and preemptive actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leaf
    -0.68
     Za
    -0.66
    WAYS
    -0.64
     Trend
    -0.64
    been
    -0.62
    wine
    -0.59
    rien
    -0.59
     Soda
    -0.59
     Es
    -0.58
    Interstitial
    -0.58
    POSITIVE LOGITS
    ively
    1.30
    eenth
    0.96
    ress
    0.92
    resses
    0.91
    uously
    0.91
     preempt
    0.89
    alos
    0.89
    empt
    0.88
    uous
    0.88
    ive
    0.87
    Act Density 0.031%

    No Known Activations