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

    Neuronpedia

    INDEX
    Explanations

    dates or times when certain regulations or events will take effect

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the implementation or coming into force of laws or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Grove
    -0.72
    gex
    -0.65
    Hop
    -0.65
     Crus
    -0.64
     rooft
    -0.59
    asca
    -0.59
     Cortex
    -0.59
     Passion
    -0.58
     Frog
    -0.57
    Plot
    -0.57
    POSITIVE LOGITS
    uated
    1.04
    uate
    1.03
    uating
    1.01
    uation
    1.00
    ional
    0.86
    angering
    0.84
    uates
    0.84
    iveness
    0.83
    abilities
    0.83
    ually
    0.83
    Act Density 0.024%

    No Known Activations