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

    Neuronpedia

    INDEX
    Explanations

    phrases related to opinions or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -1.20
    évaluateur
    -1.08
     transfieras
    -1.05
     EconPapers
    -1.03
     nonUne
    -0.94
     surla
    -0.91
     Савезне
    -0.91
     المعيارى
    -0.90
    GEBURTSDATUM
    -0.87
    afficheront
    -0.87
    POSITIVE LOGITS
    '
    0.58
     su
    0.47
    til
    0.44
    ार्थ
    0.44
     بأنه
    0.43
     directly
    0.43
    ’
    0.43
    tuples
    0.43
    ↵
    0.43
    不
    0.42
    Act Density 0.740%

    No Known Activations