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

    Neuronpedia

    INDEX
    Explanations

    dates written in the format "Month day" (e.g., "Aug 9")

    oai_token-act-pair · gpt-3.5-turbo

    dates, particularly those in August

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unfor
    -0.71
     bottleneck
    -0.69
    OGR
    -0.67
     NIC
    -0.65
     charged
    -0.64
     unpre
    -0.63
    éĹĺ
    -0.60
     deaf
    -0.59
    merce
    -0.59
     isolate
    -0.58
    POSITIVE LOGITS
    mented
    1.19
    mentation
    1.03
    enture
    0.92
    aret
    0.89
    Aug
    0.89
    sburg
    0.88
    iors
    0.83
    ital
    0.80
     Aug
    0.80
    rals
    0.80
    Act Density 0.006%

    No Known Activations