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

    Neuronpedia

    INDEX
    Explanations

    comparisons and contrasts between different subjects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AffineTransform
    -0.15
    itzer
    -0.15
     Cumhur
    -0.14
    agher
    -0.14
    plat
    -0.14
    été
    -0.13
    exels
    -0.13
    acock
    -0.13
    usher
    -0.13
    ubat
    -0.13
    POSITIVE LOGITS
     comparison
    1.09
     compare
    0.99
     comparisons
    0.96
     Comparison
    0.94
    comparison
    0.91
     comparing
    0.91
     compares
    0.89
     Compare
    0.88
    compare
    0.88
    Comparison
    0.86
    Act Density 0.446%

    No Known Activations