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

    Neuronpedia

    INDEX
    Explanations

    intensifiers that enhance the degree of an adjective or adverb

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -1.17
     whoſe
    -1.11
     Efq
    -1.04
    Geplaatst
    -1.03
    ISupport
    -1.02
     ſche
    -0.97
     poffible
    -0.96
     Jefus
    -0.95
     becauſe
    -0.95
     tartalomajánló
    -0.94
    POSITIVE LOGITS
     quite
    2.79
    quite
    2.26
     Quite
    2.07
    Quite
    2.03
     fairly
    1.69
     very
    1.65
     bastante
    1.51
     pretty
    1.37
     extremely
    1.34
     ganske
    1.32
    Act Density 0.121%

    No Known Activations