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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives and expressions of appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.81
     enfans
    -0.79
     varandra
    -0.75
     skolan
    -0.75
     zijne
    -0.75
     ainfi
    -0.73
     noastre
    -0.70
     fotografico
    -0.69
     plufieurs
    -0.69
     quæ
    -0.67
    POSITIVE LOGITS
     SwiftUI
    0.65
     autorytatywna
    0.64
    ᅠ
    0.63
     huh
    0.62
    RegressionTest
    0.59
     chance
    0.58
    SpringBootTest
    0.58
     nice
    0.57
     bravo
    0.56
     VIAF
    0.56
    Act Density 0.499%

    No Known Activations