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

    Neuronpedia

    INDEX
    Explanations

    instances of numbers and their variations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a range or variability in quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ESE
    -0.72
    Synopsis
    -0.63
    tackle
    -0.60
    reviewed
    -0.60
     Redmond
    -0.59
    /"
    -0.59
    Street
    -0.58
    ãĤ´ãĥ³
    -0.58
    ergic
    -0.56
    Place
    -0.56
    POSITIVE LOGITS
    acles
    1.16
    acle
    1.11
    chard
    1.10
    ific
    0.99
    acular
    0.96
    nam
    0.92
    ifice
    0.90
     so
    0.87
    phan
    0.86
    chid
    0.85
    Act Density 0.034%

    No Known Activations