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

    Neuronpedia

    INDEX
    Explanations

    dates, durations, and events related to endings or conclusions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate events or transitions, particularly endings and their contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.76
    Magikarp
    -0.70
     Aware
    -0.66
     screenshots
    -0.64
    arthy
    -0.64
    ants
    -0.64
    ints
    -0.64
    ighters
    -0.63
    esis
    -0.62
     loft
    -0.61
    POSITIVE LOGITS
     pregnancies
    0.82
     prematurely
    0.82
     pregnancy
    0.78
     hostilities
    0.78
     captivity
    0.76
    clusively
    0.71
    angering
    0.71
     loop
    0.70
     pointless
    0.69
     abruptly
    0.68
    Act Density 0.176%

    No Known Activations