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

    Neuronpedia

    INDEX
    Explanations

    references to alignment and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CoreData
    -1.08
    ंदीखरीदारी
    -1.03
    Jeografia
    -0.93
     Fanny
    -0.87
     NSCoder
    -0.87
    expandindo
    -0.87
    
    -0.84
    bewerken
    -0.84
     "..\..\..\
    -0.83
     GDR
    -0.82
    POSITIVE LOGITS
    align
    1.62
     align
    1.53
     Align
    1.39
     alignment
    1.34
     aligns
    1.33
     aligning
    1.33
     ALIGN
    1.32
    Align
    1.29
     Alignment
    1.28
    alignment
    1.26
    Act Density 0.141%

    No Known Activations