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

    Neuronpedia

    INDEX
    Explanations

    terms related to makeup and cleanliness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     intptr
    -0.69
    lific
    -0.55
    <?
    -0.53
     raf
    -0.52
    Appendix
    -0.49
    retudo
    -0.48
    Raf
    -0.47
     Hano
    -0.47
     Archipelago
    -0.47
    fromnode
    -0.47
    POSITIVE LOGITS
     dust
    0.82
    Makeup
    0.78
     Makeup
    0.76
    Dust
    0.72
     dirt
    0.71
     Dust
    0.70
     makeup
    0.70
    dust
    0.68
     DUST
    0.67
     AssemblyVersion
    0.67
    Act Density 0.157%

    No Known Activations