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

    Neuronpedia

    INDEX
    Explanations

    instances where actions, events, or themes are being continued or persisted

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to continuity and influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.73
    sters
    -0.68
    shaw
    -0.67
     coefficients
    -0.67
    uton
    -0.66
    asio
    -0.63
    usercontent
    -0.62
    istan
    -0.61
    pload
    -0.61
    utenant
    -0.60
    POSITIVE LOGITS
     tradition
    1.16
     trend
    0.98
     downward
    0.89
     conversation
    0.86
     journey
    0.86
     saga
    0.84
     pursuit
    0.83
     uninterrupted
    0.83
     momentum
    0.83
     unab
    0.81
    Act Density 0.114%

    No Known Activations