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

    Neuronpedia

    INDEX
    Explanations

    descriptive adjectives and their associations with unique attributes or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     opgenomen
    -0.39
     heiligen
    -0.33
     úpl
    -0.33
     apprécié
    -0.32
     appréci
    -0.32
     kayna
    -0.32
    ERTE
    -0.32
    춰
    -0.31
     kumpulan
    -0.31
    special
    -0.31
    POSITIVE LOGITS
    ScopeManager
    0.65
    0.58
    awtextra
    0.57
    enterOuterAlt
    0.57
    
    0.56
    :+:
    0.55
    BeginInit
    0.55
    EndInit
    0.54
     CreateTagHelper
    0.53
    RTLR
    0.53
    Act Density 0.971%

    No Known Activations