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

    Neuronpedia

    INDEX
    Explanations

    instances of comparison terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enosine
    -0.53
    genheim
    -0.50
    anthene
    -0.48
    Jacksonville
    -0.47
    House
    -0.47
    BIÉN
    -0.46
    Dermott
    -0.46
    estones
    -0.46
    inghouse
    -0.45
    jsonwebtoken
    -0.45
    POSITIVE LOGITS
     comparison
    1.01
     compares
    0.92
     comparing
    0.92
     compare
    0.89
     Comparison
    0.88
     comparisons
    0.88
     Compare
    0.85
     Comparing
    0.85
    comparison
    0.85
     COMPARISON
    0.84
    Act Density 0.268%

    No Known Activations