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

    Neuronpedia

    INDEX
    Explanations

    concepts related to optimization and performance evaluation in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.75
    astia
    -0.72
     houſe
    -0.71
     Houſe
    -0.71
     purpoſe
    -0.71
     AssemblyVersion
    -0.70
     itſelf
    -0.69
     Reſ
    -0.69
     Perfon
    -0.68
     Majefty
    -0.67
    POSITIVE LOGITS
    دانشنامهٔ
    0.61
    setVerticalGroup
    0.55
    idelity
    0.44
    SBATCH
    0.43
     Vikipedi
    0.42
    ze
    0.42
    \
    0.42
    یه
    0.42
     Opens
    0.41
     infla
    0.40
    Act Density 0.488%

    No Known Activations