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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical concepts or names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "el" in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ItemTracker
    -0.89
     nomine
    -0.79
     Debor
    -0.69
    displayText
    -0.67
     eclipse
    -0.65
    SourceFile
    -0.65
     antioxid
    -0.65
     conclud
    -0.64
    uyomi
    -0.64
     fortun
    -0.62
    POSITIVE LOGITS
    izabeth
    1.15
    baum
    1.05
    uxe
    0.95
    ounge
    0.94
    bach
    0.92
    ibrary
    0.92
    ength
    0.91
    ution
    0.87
    ayer
    0.87
    oad
    0.87
    Act Density 0.026%

    No Known Activations