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

    Neuronpedia

    INDEX
    Explanations

    adverbs and expressions indicating surprise or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     /*#__
    -0.59
     insensible
    -0.58
     Varian
    -0.57
    Mediator
    -0.56
     dsg
    -0.55
     Athene
    -0.55
     WrestleMania
    -0.54
     thefe
    -0.54
     Cual
    -0.54
    THISDAY
    -0.53
    POSITIVE LOGITS
    )]
    0.63
    nocześnie
    0.61
     AssemblyTitle
    0.59
     gynhyrchwyd
    0.59
    Aiheesta
    0.58
    unately
    0.57
    culously
    0.56
    好在
    0.55
    UnitTesting
    0.55
    残念ながら
    0.54
    Act Density 0.360%

    No Known Activations