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

    Neuronpedia

    INDEX
    Explanations

    terms related to claims and findings in academic or scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -0.80
    verwijspagina
    -0.76
     auroit
    -0.74
     ſta
    -0.74
     ainfi
    -0.72
     Reſ
    -0.71
     purpoſe
    -0.71
     EconPapers
    -0.71
     faſt
    -0.70
     للمعارف
    -0.69
    POSITIVE LOGITS
     missing
    0.50
     Chosen
    0.43
     desired
    0.43
     projected
    0.43
     accepted
    0.41
     Missing
    0.41
     Proposed
    0.40
    Chosen
    0.40
     Expected
    0.39
     perceived
    0.39
    Act Density 0.816%

    No Known Activations