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

    Neuronpedia

    INDEX
    Explanations

    adverbs and expressions denoting uncertainty or opinion such as 'kind of' and 'I think'

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     karet
    -0.50
    Val
    -0.47
     rokok
    -0.46
    FDRE
    -0.45
    }}]{
    -0.45
    Value
    -0.44
    AIT
    -0.44
    PointSize
    -0.43
    Ast
    -0.43
    Met
    -0.42
    POSITIVE LOGITS
     impractica
    0.83
     liberality
    0.75
     sorta
    0.73
     unce
    0.71
     unlaw
    0.70
     mortgagee
    0.65
     viciss
    0.64
     ingrat
    0.64
     shewn
    0.64
    Genau
    0.63
    Act Density 0.116%

    No Known Activations