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

    Neuronpedia

    INDEX
    Explanations

    numerical patterns in text

    oai_token-act-pair · gpt-3.5-turbo

    dates in various formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.82
    inations
    -0.75
    ocene
    -0.69
    inately
    -0.68
    oaded
    -0.68
    ographed
    -0.67
    agues
    -0.65
     disadvant
    -0.64
    inates
    -0.62
    imentary
    -0.62
    POSITIVE LOGITS
    000000
    0.82
    enced
    0.82
    09
    0.79
    st
    0.77
    07
    0.73
    041
    0.73
    00000000
    0.72
    06
    0.70
    031
    0.70
    08
    0.70
    Act Density 0.041%

    No Known Activations