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

    Neuronpedia

    INDEX
    Explanations

    questions related to specific topics or entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that inquire about specific topics or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ornings
    -0.85
    alde
    -0.83
    chairs
    -0.82
    adoes
    -0.82
    classes
    -0.80
    runs
    -0.79
    months
    -0.78
    aunts
    -0.77
    hops
    -0.77
    sheets
    -0.76
    POSITIVE LOGITS
     difference
    1.16
     significance
    1.14
     Difference
    1.00
     takeaway
    0.99
     purpose
    0.96
     reperc
    0.95
     point
    0.94
     rationale
    0.94
     biggest
    0.93
     optimum
    0.93
    Act Density 0.074%

    No Known Activations